Researcher profile

Cong Wang

Cong Wang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

68works

0followers

27topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

Amplitude analysis and branching fraction measurement of $J/ψ\to Λ\barΣ^0η+\mathrm{c.c}$

Based on a sample of $(10087\pm44)\times10^{6}$ $J/ψ$ events collected with the BESIII detector, a partial-wave analysis of $ J/ψ\to Λ\bar{ Σ}^0η+\mathrm{c.c} $ is performed for the first time. The dominant contributions are found to be excited $Λ$ states with $J^P=1/2^-$ and $J^P=1/2^+$ in the $ηΛ$ mass spectra. The measured masses and widths are $M=1668.8\pm3.1\pm21.2$ MeV/$c^2$ and $Γ=52.7\pm4.2\pm17.8$ MeV for the $Λ(1670)$, and $M=1881.5\pm16.5\pm20.3$ MeV/$c^2$ and $Γ=82.4\pm18.2\pm8.9$ MeV for the $Λ(1810)$, respectively. The branching fraction is determined to be $ \mathcal{B}(J/ψ\to Λ\bar{ Σ}^0η+\mathrm{c.c}) $ = $(3.44 \pm 0.11 \pm 0.13) \times 10^{-5}$. The first uncertainties are statistical and the second systematic.

preprint2026arXiv

CMTA: Leveraging Cross-Modal Temporal Artifacts for Generalizable AI-Generated Video Detection

The proliferation of advanced AI video synthesis techniques poses an unprecedented challenge to digital video authenticity. Existing AI-generated video (AIGV) detection methods primarily focus on uni-modal or spatiotemporal artifacts, but they overlook the rich cues within the visual-textual cross-modal space, especially the temporal stability of semantic alignment. In this work, we identify a distinctive fingerprint in AIGVs, termed cross-modal temporal artifact (CMTA). Unlike real videos that exhibit natural temporal fluctuations in cross-modal alignment due to semantic variations, AIGVs display unnaturally stable semantic trajectories governed by given input prompts. To bridge this gap, we propose the CMTA framework, a cross-modal detection approach that captures these unique temporal artifacts through joint cross-modal embedding and multi-grained temporal modeling. Specifically, CMTA leverages BLIP to generate frame-level image captions and utilizes CLIP to extract corresponding visual-textual representations. A coarse-grained temporal modeling branch is then designed to characterize temporal fluctuations in cross-modal alignment with a GRU. In parallel, a fine-grained branch is constructed to capture intricate inter-frame variations from integrated visual-textual features with a Transformer encoder. Extensive experiments on 40 subsets across four large-scale datasets, including GenVideo, EvalCrafter, VideoPhy, and VidProM, validate that our approach sets a new state-of-the-art while exhibiting superior cross-generator generalization. Code and models of CMTA will be released at https://github.com/hwang-cs-ime/CMTA

preprint2026arXiv

Cross section measurement of $e^{+}e^{-}\rightarrow π^{0}π^{0}ψ(3686)$ from $\sqrt{s}=$ 4.008 GeV to 4.951 GeV

Using data samples with a total integrated luminosity of $22.1~\rm fb^{-1}$ at center-of-mass energies between 4.008 and 4.951~GeV collected with the BESIII detector, the cross sections of $e^{+}e^{-}\rightarrow π^{0}π^{0}ψ(3686)$ process are measured. The obtained cross sections are found to be approximately one-half of those of $e^{+}e^{-}\rightarrow π^{+}π^{-}ψ(3686)$, consistent with the isospin symmetry expectation. A coherent fit to the dressed cross sections is performed, with the $Y(4230)$~parameters fixed at the values measured in $e^{+}e^{-}\rightarrow π^{+}π^{-}ψ(3686)$. The significances of the $Y(4390)$ and $Y(4660)$ are both larger than $5σ$, and their masses and widths are consistent with the previous measurement in the $e^{+}e^{-}\rightarrow π^{+}π^{-}ψ(3686)$ process.

preprint2026arXiv

Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding

Speculative decoding (SD) accelerates large language model inference by leveraging a draft-then-verify paradigm. To maximize the acceptance rate, recent methods construct expansive draft trees, which unfortunately incur severe VRAM bandwidth and computational overheads that bottleneck end-to-end speedups. While dynamic-depth pruning can reduce this latency by removing marginal branches, it also discards potentially valid candidates, preventing the acceptance rate from reaching the upper bound of dense trees. In this paper, we identify a critical opportunity in resource allocation: the transition from dense to pruned drafting frees up significant computational budget. To break this Pareto tradeoff, we introduce Graft, a compensation framework that couples pruning and retrieval as mutually reinforcing operations. Pruning supplies sufficient budget for retrieval, while retrieval compensates for pruning-induced coverage loss and recovers accepted length. By employing a sequential `prune-then-graft' mechanism, Graft attaches highly predictive retrieved tokens into positions opened by pruning, filling the topological gaps with near-zero overhead. Graft is entirely training-free and lossless. Comprehensive evaluations show that Graft establishes a new Pareto frontier across practical deployment settings, including short-context generation, long-context generation, and large-scale models. On short-context benchmarks, it achieves up to 5.41$\times$ speedup and improves average speedup over EAGLE-3 by up to 21.8% on the large-scale Qwen3-235B. We also provide a preliminary exploration of applying Graft to the DFlash-style block drafting paradigm, offering initial evidence and insights for extending grafting beyond autoregressive draft trees.

preprint2026arXiv

Embody4D: A Generalist 4D World Model for Embodied AI

World models have made significant progress in modeling dynamic environments; however, most embodied world models are still restricted to 2D representations, lacking the comprehensive multi-view information essential for embodied spatial reasoning. Bridging this gap is non-trivial, primarily due to challenges from severe scarcity of paired multi-view data, the difficulty of maintaining spatiotemporal consistency in generated 3D geometries, and the tendency to hallucinate manipulation details. To address these challenges, we propose Embody4D, a dedicated video-to-video world model for embodied scenarios, capable of synthesizing arbitrary novel views from a monocular video. First, to tackle data scarcity, we introduce a 3D-aware compositional synthesis pipeline to curate a heterogeneous dataset compositing cross-embodiment robotic arms with diverse backgrounds, guaranteeing broad generalization. Second, to enforce geometric stability, we devise an adaptive noise injection strategy; by leveraging confidence disparities across image regions, this method selectively regularizes the diffusion process to ensure strict spatiotemporal consistency. Finally, to guarantee manipulation fidelity, we incorporate an interaction-aware attention mechanism that explicitly attends to the robotic interaction regions. Extensive experiments demonstrate that Embody4D achieves state-of-the-art performance, serving as a robust world model that synthesizes high-fidelity, view-consistent videos to empower downstream robotic planning and learning.

preprint2026arXiv

First Measurement of the Absolute Branching Fraction of $η_c \to γγ$

We apply a tag-and-probe method to precisely measure the absolute branching fraction of the decay $η_c \to γγ$ with the BESIII experiment at BEPCII. Starting with a large initial sample of $2712.4\pm 14.3$ million $ψ(3686)$ events, a sample of 0.16 million $η_c$ events are tagged via the golden channel $ψ(3686)\to π^0 h_c$, $h_c\to γη_c$, effectively avoiding interference effects. The absolute branching fraction of $η_c \to γγ$ is measured for the first time to be $\mathcal{B}(η_c \to γγ) = (2.45 \pm 0.48_{\rm stat.} \pm 0.09_{\rm syst.}) \times 10^{-4}$. Using the world average value of the total width of the $η_c$, the partial decay width of $η_c \to γγ$ is calculated to be $Γ(η_c \to γγ) = (7.48 \pm 1.48_{\rm stat.} \pm 0.30_{\rm syst.})~{\rm keV}$.

preprint2026arXiv

First Observation of $D^{0(+)}\to \bar Kωe^+ν_e$ and Determination of the Branching Fraction of $\bar K_1(1270)\to \bar K ω$

Using 20.3~fb$^{-1}$ of $e^+e^-$ annihilation data collected at a center-of-mass energy of 3.773~GeV with the BESIII detector, we report the first observation of the semileptonic decays $D^0\to K^-ωe^+ν_e$ and $D^+\to K_S^0ωe^+ν_e$ with significances of $8.0σ$ and $5.8σ$, respectively, including systematic uncertainties. Their decay branching fractions are measured to be ${\cal B}(D^0\to K^-ωe^+ν_e)=(9.3^{+2.1}_{-1.9}\pm 0.7)\times10^{-5}$ and ${\cal B}(D^+\to K_S^0ωe^+ν_e)=(6.6^{+2.0}_{-1.8}\pm 0.6)\times10^{-5}$. Combining with the latest measurements of $D^{0(+)}\to K^-π^+π^{-(0)} e^+ν_e$ and assuming $\bar{K}_1(1270)$ to be the sole mediating resonance in all processes, the branching ratios are determined to be $\frac{Γ(K_1(1270)^-\to K^-π^+π^-)}{Γ(K_1(1270)^-\to K^-ω)} = 3.4^{+0.8}_{-0.7} \pm 0.3$ and $\frac{Γ(\bar{K}_1(1270)^0\to K^-π^+π^0)}{Γ(\bar{K}_1(1270)^0\to \bar{K}^0ω)} = 9.6^{+3.0}_{-2.7} \pm 0.8$. The combined branching fraction is determined to be $\mathcal B(\bar{K}_1(1270)\to \bar{K}ω) = (7.5\pm 1.3 \pm 0.5)\%$, which is the most precise measurement from a collider experiment. The first uncertainties are statistical, and the second are systematic.

preprint2026arXiv

GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusion

Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of domains including spatial intelligence, embodied intelligence, and autonomous driving. While achieving remarkable progress, existing approaches to 3D world generation typically prioritize appearance prediction with limited modeling of the underlying geometry, leading to issues such as unreliable scene structure estimation and degraded cross-view consistency. To address these limitations, motivated by the coarse-to-fine nature of human visual perception, we propose GTA, a novel image-to-3D world generation method following a Geometry-Then-Appearance paradigm. Specifically, given a single input image, to improve the structural fidelity of synthesized 3D scenes, GTA adopts a two-stage framework with two dedicated video diffusion models, which first generate coarse geometric structure from novel viewpoints and then synthesize fine-grained appearance conditioned on the predicted geometry. To further enhance cross-view appearance consistency, we introduce a random latent shuffle strategy during the training process, along with a test-time scaling scheme that improves perceptual quality without compromising quantitative performance. Extensive experiments have demonstrated that our proposed method consistently outperforms existing approaches in terms of fidelity, visual quality, and geometric accuracy. Moreover, GTA is shown to be effective as a general enhancement module that further improves the generation quality of existing image-to-3D world pipelines, as well as supporting multiple downstream applications and exhibiting favorable data efficiency during model training, highlighting its versatility and broad applicability. Project page: https://hanxinzhu-lab.github.io/GTA/.

preprint2026arXiv

Investigating More Explainable and Partition-Free Compositionality Estimation for LLMs: A Rule-Generation Perspective

Compositional generalization tests are often used to estimate the compositionality of LLMs. However, such tests have the following limitations: (1) they only focus on the output results without considering LLMs' understanding of sample compositionality, resulting in explainability defects; (2) they rely on dataset partition to form the test set with combinations unseen in the training set, suffering from combination leakage issues. In this work, we propose a novel rule-generation perspective for compositionality estimation for LLMs. It requires LLMs to generate a program as rules for dataset mapping and provides estimates of the compositionality of LLMs using complexity-based theory. The perspective addresses the limitations of compositional generalization tests and provides a new way to analyze the compositionality characterization of LLMs. We conduct experiments and analysis of existing advanced LLMs based on this perspective on a string-to-grid task, and find various compositionality characterizations and compositionality deficiencies exhibited by LLMs.

preprint2026arXiv

Measurements of the absolute branching fractions of the $Λ_{c}^{+}$ hadronic decays

Based on 4.5 fb$^{-1}$ of $e^+e^-$ collision data collected at center-of-mass energies between 4599.53 MeV and 4698.82 MeV with the BESIII detector, the absolute branching fractions of twelve $Λ_{c}^{+}$ hadronic decay modes are measured with a double-tag technique. A global least-square fit is implemented simultaneously among different decay modes at different energy points. This paper gives the most precise results on the branching fractions of different decay modes to date, with precision improved by a factor of 2 to 3. Among them, the branching fraction of $Λ_{c}^{+}\to pK^{-}π^+$ is determined to be $(6.61\pm0.11\pm0.12)\%$, where the first uncertainty is statistical and the second is systematic. In addition, the $e^+e^-\toΛ_c^+\barΛ_c^-$ Born cross sections and the effective form factors ($|G_{\rm eff}|$) at different energy points have been determined with the highest precision to date.

preprint2026arXiv

Measurements of the branching fractions of $χ_{cJ}\to 2K^+ 2K^- ω$ and $ϕK^+ K^- ω$ decays

Using a data sample of $(2712.4 \pm 14.3) \times 10^{6}$ $ψ(3686)$ events collected with the BESIII detector operating at the BEPCII collider, we report the first observation of the decays $χ_{cJ}\to 2K^+ 2K^- ω$ and $χ_{cJ}\to ϕK^{+}K^{-} ω$ ($J = 0,1,2$) via the radiative transitions $ψ(3686) \to γχ_{cJ}$. The branching fractions of these decays are measured for the first time, and the statistical significance for each signal exceeds $10σ$.

preprint2026arXiv

Multi-pathline flow visualization using PIV images

One of the oldest flow visualization techniques is through multiple pathlines generated by the movement of seeding particles spatially distributed in the flow. In the computerized era, particle images are used in quantitative measurements, such as particle image and particle tracking velocimetry (PIV and PTV). Here, we present several methods for post-processing raw particle images to generate enhanced flow visualization without a need for conducting additional experiments. Three post-processing methods will be shown: 1) controlling the exposure time, 2) color-coding temporal information, and 3) changing the frame of reference. We showcase how employing these three methods can highlight different flow features in three canonical flow cases: vortex ring, leading edge vortex, and turbulent boundary layer. In addition to the quantitative flow field, the multi-pathline visualization is expected to augment our ability to observe fluid flow from many different perspectives.

preprint2026arXiv

Observation of Polarization and Determination of Electric and Magnetic Moments of $Ξ(1530)^0$ in $ψ(3686)\toΞ(1530)^0\barΞ(1530)^0$

Using the data sample of $2.7\times10^9$ $ψ(3686)$ events collected with the BESIII detector at the BEPCII collider, we present an observation of the $Ξ(1530)^0$ polarization in the decay $ψ(3686)\toΞ(1530)^0\barΞ(1530)^0$ with a significance larger than $20σ$ compared with all other tested hypotheses. The helicity amplitudes for the process $ψ(3686)\toΞ(1530)^0\barΞ(1530)^0$ and the moduli of form factors including electric charge, magnetic dipole, electric quadrupole, and magnetic octupole are measured for the first time by performing an angular distribution analysis. Additionally, the polarization correlations between $Ξ(1530)^0$ and $\barΞ(1530)^0$ are measured.

preprint2026arXiv

Search for a dark baryon in the $Ξ^-\rightarrowπ^-+{\rm invisible}$ decay

A search for a dark baryon is performed for the first time in the two-body decay $Ξ^-\rightarrowπ^-+{\rm invisible}$ using $(10.087\pm0.044)\times10^{9}$ $J/ψ$ events collected at a center-of-mass energy of $\sqrt{s}=3.097\,\mbox{GeV}$ with the BESIII detector at the BEPCII collider. No significant signal is observed, and the 90% (95%) confidence level upper limits on the branching fraction $B(Ξ^-\rightarrowπ^-+{\rm invisible})$ are determined to be $4.2\times10^{-5}$ ($5.2\times10^{-5}$), $6.9\times10^{-5}$ ($8.4\times10^{-5}$), $6.5\times10^{-4}$ ($7.6\times10^{-4}$), $1.1\times10^{-4}$ ($1.3\times10^{-4}$) and $4.5\times10^{-5}$ ($5.5\times10^{-5}$), under the dark baryon mass hypotheses of 1.07$\,\mbox{GeV}/c^2$, 1.10$\,\mbox{GeV}/c^2$, $m_Λ$ (1.116$\,\mbox{GeV}/c^2$), 1.13$\,\mbox{GeV}/c^2$, and 1.16$\,\mbox{GeV}/c^2$, respectively. The constraints obtained on the Wilson coefficients $C_{u s, s}^L$ and $C_{u s, s}^R$ are more stringent than the previous limits derived from the LHC searches for the colored mediators.

preprint2026arXiv

What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis

Agent memory failures are silent: an LLM-based agent can produce a fluent response even when it fails to extract, retain, or retrieve the information needed across sessions. The write-manage-read loop describes the external pipeline of these systems but leaves open which internal computations implement each stage. Tracing feature circuits across the Qwen-3 family (0.6B--14B) and two memory frameworks (mem0 and A-MEM), we report two mechanistic findings and one deliverable. First, control is detectable before content: routing circuitry is causally active at 0.6B, while content circuitry produces no detectable signal until 4B, exposing a deployment regime where small models route memory decisions before they can reliably extract or ground the underlying facts. Second, the shared hub is recruited, not created: Write and Read converge on a late-layer hub that already exists in the base model as a context-grounding substrate, and memory framing recruits a memory-specific functional direction on this substrate rather than building one of its own. Both findings transfer across mem0 and A-MEM, indicating that the underlying computations are properties of the base model rather than of any particular interface. Building on this circuit structure, we develop an unsupervised stage-level diagnostic that localizes silent failures to the responsible operation up to 76.2% accuracy, outperforming the strongest supervised baseline by 13 points. Together, these results point to circuit-level signatures as a practical handle for monitoring and structurally-guided design of agent memory.

preprint2025arXiv

Anomalous Hall effect and rich magnetic phase diagram of Mn$_{100-x}$Rh$_{x}$ epitaxial films

A series of Mn$_{100-x}$Rh$_x$ ($20 \le x \le 50$) thin films were epitaxially grown on the MgO substrate using magnetron sputtering technique, and were systematically investigated by magnetization, longitudinal electrical resistivity, and transverse Hall resistivity. After optimizing the growth conditions, phase-pure Mn$_{100-x}$Rh$_x$ films with a cubic CsCl-type structure were obtained, and their magnetic phase diagram was built. The manipulation of Rh content leads to a rich magnetic phase diagram, where three different regimes can be identified: for $x < 40$, Mn$_{100-x}$Rh$_x$ films undergo a ferromagnetic (FM) transition below $T_\mathrm{C} \approx$ 330-350 K; for $40 \le x \le 45$, in addition to the FM transition at $T_\mathrm{C} \approx$ 200 K, Mn$_{100-x}$Rh$_x$ films undergo a FM-to-antiferromagnetic (AFM) transition at $T_\mathrm{N} \approx$ 120 K; finally for $x > 45$, only one AFM transition at $T_\mathrm{N} \approx$ 150 K can be tracked. All the Mn$_{100-x}$Rh$_x$ films exhibit distinct anomalous Hall effect in their magnetically ordered state, which is most likely due to the intrinsic Berry-curvature mechanism. In addition, all the anomalous Hall transport properties, including the resistivity, conductivity, and angle exhibit a strong correlation with the magnetic properties of Mn$_{100-x}$Rh$_x$ films, which become most evident for $x$ = 35. Our systematic investigations suggest a strong correlation between magnetic properties and electronic band topology in Mn$_{100-x}$Rh$_x$ films, highlighting their great potential for AFM spintronics.

preprint2025arXiv

FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensing

Large vision-language models (VLMs) exhibit strong performance across various tasks. However, these VLMs encounter significant challenges when applied to the remote sensing domain due to the inherent differences between remote sensing images and natural images. Existing remote sensing VLMs often fail to extract fine-grained visual features and suffer from visual forgetting during deep language processing. To address this, we introduce MF-RSVLM, a Multi-Feature Fusion Remote Sensing Vision--Language Model that effectively extracts and fuses visual features for RS understanding. MF-RSVLM learns multi-scale visual representations and combines global context with local details, improving the capture of small and complex structures in RS scenes. A recurrent visual feature injection scheme ensures the language model remains grounded in visual evidence and reduces visual forgetting during generation. Extensive experiments on diverse RS benchmarks show that MF-RSVLM achieves state-of-the-art or highly competitive performance across remote sensing classification, image captioning, and VQA tasks. Our code is publicly available at https://github.com/Yunkaidang/RSVLM.

preprint2025arXiv

Kinetically accessible 1D magnetic chains of transition-metal chalcogenides and halides on van der Waals surfaces

One-dimensional (1D) chains offer unique opportunities for nanoelectronics and spintronics, yet their experimental realization remains challenging because 1D motifs are often thermodynamically disfavored relative to higher-dimensional phases. Here we present a high-throughput first-principles exploration of 1D single-atomic transition-metal chalcogenide and halide chains, screening 6,832 candidates constructed from binary combinations of 28 metals and 8 non-metals. To assess kinetic accessibility, we compare the formation energetics of 1D chains with competing two-dimensional polymorphs at the nucleation stage across relevant chemical-potential windows, using nucleation-stage thermodynamic selectivity as a proxy. This workflow identifies 183 kinetically accessible 1D chains. Interpretable machine-learning analysis reveals two simple stability descriptors as key drivers of 1D stabilization. The accessible chains exhibit diverse magnetic configurations with different magnetic characters. We further uncover their pronounced magnetoelastic couplings, exemplified by CrTe with giant magnetostriction reaching 5.93%. Finally, we show that selected metallic ferromagnetic chains retain robust edge magnetism on superconducting substrates, laying the groundwork for proximity-induced topological superconductivity and Majorana zero modes.

preprint2023arXiv

Forecasting subcritical cylinder wakes with Fourier Neural Operators

We apply Fourier neural operators (FNOs), a state-of-the-art operator learning technique, to forecast the temporal evolution of experimentally measured velocity fields. FNOs are a recently developed machine learning method capable of approximating solution operators to systems of partial differential equations through data alone. The learned FNO solution operator can be evaluated in milliseconds, potentially enabling faster-than-real-time modeling for predictive flow control in physical systems. Here we use FNOs to predict how physical fluid flows evolve in time, training with particle image velocimetry measurements depicting cylinder wakes in the subcritical vortex shedding regime. We train separate FNOs at Reynolds numbers ranging from Re = 240 to Re = 3060 and study how increasingly turbulent flow phenomena impact prediction accuracy. We focus here on a short prediction horizon of ten non-dimensionalized time-steps, as would be relevant for problems of predictive flow control. We find that FNOs are capable of accurately predicting the evolution of experimental velocity fields throughout the range of Reynolds numbers tested (L2 norm error < 0.1) despite being provided with limited and imperfect flow observations. Given these results, we conclude that this method holds significant potential for real-time predictive flow control of physical systems.

preprint2023arXiv

Interior estimates of derivatives and a Liouville type theorem for Parabolic $k$-Hessian equations

In this paper, we establish the gradient and Pogorelov estimates for $k$-convex-monotone solutions to parabolic $k$-Hessian equations of the form $-u_tσ_k(λ(D^2u))=ψ(x,t,u)$. We also apply such estimates to obtain a Liouville type result, which states that any $k$-convex-monotone and $C^{4,2}$ solution $u$ to $-u_tσ_k(λ(D^2u))=1$ in $\mathbb{R}^n\times(-\infty,0]$ must be a linear function of $t$ plus a quadratic polynomial of $x$, under some growth assumptions on $u$.

preprint2023arXiv

On the exterior Dirichlet problem for Hessian type fully nonlinear elliptic equations

We treat the exterior Dirichlet problem for a class of fully nonlinear elliptic equations of the form $$f(λ(D^2u))=g(x),$$ with prescribed asymptotic behavior at infinity. The equations of this type had been studied extensively by Caffarelli--Nirenberg--Spruck \cite{Caffarelli1985}, Trudinger \cite{Trudinger1995} and many others, and there had been significant discussions on the solvability of the classical Dirichlet problem via the continuity method, under the assumption that $f$ is a concave function. In this paper, based on the Perron's method, we establish an exterior existence and uniqueness result for viscosity solutions of the equations by assuming $f$ to satisfy certain structure conditions as in \cite{Caffarelli1985,Trudinger1995}, which may embrace the well-known Monge--Ampère equations, Hessian equations and Hessian quotient equations as special cases but do not require the concavity.

preprint2022arXiv

A Transferable Legged Mobile Manipulation Framework Based on Disturbance Predictive Control

Due to their ability to adapt to different terrains, quadruped robots have drawn much attention in the research field of robot learning. Legged mobile manipulation, where a quadruped robot is equipped with a robotic arm, can greatly enhance the performance of the robot in diverse manipulation tasks. Several prior works have investigated legged mobile manipulation from the viewpoint of control theory. However, modeling a unified structure for various robotic arms and quadruped robots is a challenging task. In this paper, we propose a unified framework disturbance predictive control where a reinforcement learning scheme with a latent dynamic adapter is embedded into our proposed low-level controller. Our method can adapt well to various types of robotic arms with a few random motion samples and the experimental results demonstrate the effectiveness of our method.

preprint2022arXiv

Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization

Federated learning has recently emerged as a paradigm promising the benefits of harnessing rich data from diverse sources to train high quality models, with the salient features that training datasets never leave local devices. Only model updates are locally computed and shared for aggregation to produce a global model. While federated learning greatly alleviates the privacy concerns as opposed to learning with centralized data, sharing model updates still poses privacy risks. In this paper, we present a system design which offers efficient protection of individual model updates throughout the learning procedure, allowing clients to only provide obscured model updates while a cloud server can still perform the aggregation. Our federated learning system first departs from prior works by supporting lightweight encryption and aggregation, and resilience against drop-out clients with no impact on their participation in future rounds. Meanwhile, prior work largely overlooks bandwidth efficiency optimization in the ciphertext domain and the support of security against an actively adversarial cloud server, which we also fully explore in this paper and provide effective and efficient mechanisms. Extensive experiments over several benchmark datasets (MNIST, CIFAR-10, and CelebA) show our system achieves accuracy comparable to the plaintext baseline, with practical performance.

preprint2022arXiv

An Optimization Problem in Heat Conduction With Volume Constraint and Double Obstacles

We consider the optimization problem of minimizing $\int_{\mathbb{R}^n}|\nabla u|^2\,\mathrm{d}x$ with double obstacles $ϕ\leq u\leqψ$ a.e. in $D$ and a constraint on the volume of $\{u>0\}\setminus\overline{D}$, where $D\subset\mathbb{R}^n$ is a bounded domain. By studying a penalization problem that achieves the constrained volume for small values of penalization parameter, we prove that every minimizer is $C^{1,1}$ locally in $D$ and Lipschitz continuous in $\mathbb{R}^n$ and that the free boundary $\partial\{u>0\}\setminus\overline{D}$ is smooth. Moreover, when the boundary of $D$ has a plane portion, we show that the minimizer is $C^{1,\frac{1}{2}}$ up to the plane portion.

preprint2022arXiv

BCS-Net: Boundary, Context and Semantic for Automatic COVID-19 Lung Infection Segmentation from CT Images

The spread of COVID-19 has brought a huge disaster to the world, and the automatic segmentation of infection regions can help doctors to make diagnosis quickly and reduce workload. However, there are several challenges for the accurate and complete segmentation, such as the scattered infection area distribution, complex background noises, and blurred segmentation boundaries. To this end, in this paper, we propose a novel network for automatic COVID-19 lung infection segmentation from CT images, named BCS-Net, which considers the boundary, context, and semantic attributes. The BCS-Net follows an encoder-decoder architecture, and more designs focus on the decoder stage that includes three progressively Boundary-Context-Semantic Reconstruction (BCSR) blocks. In each BCSR block, the attention-guided global context (AGGC) module is designed to learn the most valuable encoder features for decoder by highlighting the important spatial and boundary locations and modeling the global context dependence. Besides, a semantic guidance (SG) unit generates the semantic guidance map to refine the decoder features by aggregating multi-scale high-level features at the intermediate resolution. Extensive experiments demonstrate that our proposed framework outperforms the existing competitors both qualitatively and quantitatively.

preprint2022arXiv

Convolutional Embedding Makes Hierarchical Vision Transformer Stronger

Vision Transformers (ViTs) have recently dominated a range of computer vision tasks, yet it suffers from low training data efficiency and inferior local semantic representation capability without appropriate inductive bias. Convolutional neural networks (CNNs) inherently capture regional-aware semantics, inspiring researchers to introduce CNNs back into the architecture of the ViTs to provide desirable inductive bias for ViTs. However, is the locality achieved by the micro-level CNNs embedded in ViTs good enough? In this paper, we investigate the problem by profoundly exploring how the macro architecture of the hybrid CNNs/ViTs enhances the performances of hierarchical ViTs. Particularly, we study the role of token embedding layers, alias convolutional embedding (CE), and systemically reveal how CE injects desirable inductive bias in ViTs. Besides, we apply the optimal CE configuration to 4 recently released state-of-the-art ViTs, effectively boosting the corresponding performances. Finally, a family of efficient hybrid CNNs/ViTs, dubbed CETNets, are released, which may serve as generic vision backbones. Specifically, CETNets achieve 84.9% Top-1 accuracy on ImageNet-1K (training from scratch), 48.6% box mAP on the COCO benchmark, and 51.6% mIoU on the ADE20K, substantially improving the performances of the corresponding state-of-the-art baselines.

preprint2022arXiv

Defeating Misclassification Attacks Against Transfer Learning

Transfer learning is prevalent as a technique to efficiently generate new models (Student models) based on the knowledge transferred from a pre-trained model (Teacher model). However, Teacher models are often publicly available for sharing and reuse, which inevitably introduces vulnerability to trigger severe attacks against transfer learning systems. In this paper, we take a first step towards mitigating one of the most advanced misclassification attacks in transfer learning. We design a distilled differentiator via activation-based network pruning to enervate the attack transferability while retaining accuracy. We adopt an ensemble structure from variant differentiators to improve the defence robustness. To avoid the bloated ensemble size during inference, we propose a two-phase defence, in which inference from the Student model is firstly performed to narrow down the candidate differentiators to be assembled, and later only a small, fixed number of them can be chosen to validate clean or reject adversarial inputs effectively. Our comprehensive evaluations on both large and small image recognition tasks confirm that the Student models with our defence of only 5 differentiators are immune to over 90% of the adversarial inputs with an accuracy loss of less than 10%. Our comparison also demonstrates that our design outperforms prior problematic defences.

preprint2022arXiv

Energy Minimization for Federated Asynchronous Learning on Battery-Powered Mobile Devices via Application Co-running

Energy is an essential, but often forgotten aspect in large-scale federated systems. As most of the research focuses on tackling computational and statistical heterogeneity from the machine learning algorithms, the impact on the mobile system still remains unclear. In this paper, we design and implement an online optimization framework by connecting asynchronous execution of federated training with application co-running to minimize energy consumption on battery-powered mobile devices. From a series of experiments, we find that co-running the training process in the background with foreground applications gives the system a deep energy discount with negligible performance slowdown. Based on these results, we first study an offline problem assuming all the future occurrences of applications are available, and propose a dynamic programming-based algorithm. Then we propose an online algorithm using the Lyapunov framework to explore the solution space via the energy-staleness trade-off. The extensive experiments demonstrate that the online optimization framework can save over 60% energy with 3 times faster convergence speed compared to the previous schemes.

preprint2022arXiv

Fault Detection and Isolation of Uncertain Nonlinear Parabolic PDE Systems

This paper proposes a novel fault detection and isolation (FDI) scheme for distributed parameter systems modeled by a class of parabolic partial differential equations (PDEs) with nonlinear uncertain dynamics. A key feature of the proposed FDI scheme is its capability of dealing with the effects of system uncertainties for accurate FDI. Specifically, an approximate ordinary differential equation (ODE) system is first derived to capture the dominant dynamics of the original PDE system. An adaptive dynamics identification approach using radial basis function neural network is then proposed based on this ODE system, so as to achieve locally-accurate identification of the uncertain system dynamics under normal and faulty modes. A bank of FDI estimators with associated adaptive thresholds are finally designed for real-time FDI decision making. Rigorous analysis on the FDI performance in terms of fault detectability and isolatability is provided. Simulation study on a representative transport-reaction process is conducted to demonstrate the effectiveness and advantage of the proposed approach.

preprint2022arXiv

Imitation and Adaptation Based on Consistency: A Quadruped Robot Imitates Animals from Videos Using Deep Reinforcement Learning

The essence of quadrupeds' movements is the movement of the center of gravity, which has a pattern in the action of quadrupeds. However, the gait motion planning of the quadruped robot is time-consuming. Animals in nature can provide a large amount of gait information for robots to learn and imitate. Common methods learn animal posture with a motion capture system or numerous motion data points. In this paper, we propose a video imitation adaptation network (VIAN) that can imitate the action of animals and adapt it to the robot from a few seconds of video. The deep learning model extracts key points during animal motion from videos. The VIAN eliminates noise and extracts key information of motion with a motion adaptor, and then applies the extracted movements function as the motion pattern into deep reinforcement learning (DRL). To ensure similarity between the learning result and the animal motion in the video, we introduce rewards that are based on the consistency of the motion. DRL explores and learns to maintain balance from movement patterns from videos, imitates the action of animals, and eventually, allows the model to learn the gait or skills from short motion videos of different animals and to transfer the motion pattern to the real robot.

preprint2022arXiv

Influence of Binomial Crossover on Approximation Error of Evolutionary Algorithms

Although differential evolution (DE) algorithms perform well on a large variety of complicated optimization problems, only a few theoretical studies are focused on the working principle of DE algorithms. To make the first attempt to reveal the function of binomial crossover, this paper aims to answer whether it can reduce the approximation error of evolutionary algorithms. By investigating the expected approximation error and the probability of not finding the optimum, we conduct a case study comparing two evolutionary algorithms with and without binomial crossover on two classical benchmark problems: OneMax and Deceptive. It is proven that using binomial crossover leads to the dominance of transition matrices. As a result, the algorithm with binomial crossover asymptotically outperforms that without crossover on both OneMax and Deceptive, and outperforms on OneMax, however, not on Deceptive. Furthermore, an adaptive parameter strategy is proposed which can strengthen the superiority of binomial crossover on Deceptive.

preprint2022arXiv

Layer-dependent interlayer antiferromagnetic spin reorientation in air-stable semiconductor CrSBr

Magnetic van der Waals (vdW) materials offer a fantastic platform to investigate and exploit rich spin configurations stabilized in reduced dimensions. One tantalizing magnetic order is the interlayer antiferromagnetism in A-type vdW antiferromagnet, which may be effectively modified by the magnetic field, stacking order and thickness scaling. However, atomically revealing the interlayer spin orientation in the vdW antiferromagnet is highly challenging, because most of the material candidates exhibit an insulating ground state or instability in ambient conditions. Here, we report the layer-dependent interlayer antiferromagnetic reorientation in air-stable semiconductor CrSBr using magnetotransport characterization and first-principles calculations. We reveal a pronounced odd-even layer effect of interlayer reorientation, which originates from the competitions among interlayer exchange, magnetic anisotropy energy and extra Zeeman energy of uncompensated magnetization. Furthermore, we quantitatively constructed the layer-dependent magnetic phase diagram with the help of a linear-chain model. Our work uncovers the layer-dependent interlayer antiferromagnetic reorientation engineered by magnetic field in the air-stable semiconductor, which could contribute to future vdW spintronic devices.

preprint2022arXiv

Learning to Classify Open Intent via Soft Labeling and Manifold Mixup

Open intent classification is a practical yet challenging task in dialogue systems. Its objective is to accurately classify samples of known intents while at the same time detecting those of open (unknown) intents. Existing methods usually use outlier detection algorithms combined with K-class classifier to detect open intents, where K represents the class number of known intents. Different from them, in this paper, we consider another way without using outlier detection algorithms. Specifically, we directly train a (K+1)-class classifier for open intent classification, where the (K+1)-th class represents open intents. To address the challenge that training a (K+1)-class classifier with training samples of only K classes, we propose a deep model based on Soft Labeling and Manifold Mixup (SLMM). In our method, soft labeling is used to reshape the label distribution of the known intent samples, aiming at reducing model's overconfident on known intents. Manifold mixup is used to generate pseudo samples for open intents, aiming at well optimizing the decision boundary of open intents. Experiments on four benchmark datasets demonstrate that our method outperforms previous methods and achieves state-of-the-art performance. All the code and data of this work can be obtained at https://github.com/zifengcheng/SLMM.

preprint2022arXiv

Liouville property and existence of entire solutions of Hessian equations

In this paper, we establish the existence and uniqueness theorem for entire solutions of Hessian equations with prescribed asymptotic behavior at infinity. This extends the previous results on Monge-Ampère equations. Our approach also makes the prescribed asymptotic order optimal within the range preset in exterior Dirichlet problems. In addition, we show a Liouville type result for $k$-convex solutions. This partly removes the $(k+1)$- or $n$-convexity restriction imposed in existing work.

preprint2022arXiv

Load-Flow Solvability under Security Constraints in DC Distribution Networks

We present sufficient conditions for the load-flow solvability under security constraints in DC distribution networks. In addition, we show that a load-flow solution that fulfills security constraints can be obtained via a convex optimization.

preprint2022arXiv

Online-updated High-order Collaborative Networks for Single Image Deraining

Single image deraining is an important and challenging task for some downstream artificial intelligence applications such as video surveillance and self-driving systems. Most of the existing deep-learning-based methods constrain the network to generate derained images but few of them explore features from intermediate layers, different levels, and different modules which are beneficial for rain streaks removal. In this paper, we propose a high-order collaborative network with multi-scale compact constraints and a bidirectional scale-content similarity mining module to exploit features from deep networks externally and internally for rain streaks removal. Externally, we design a deraining framework with three sub-networks trained in a collaborative manner, where the bottom network transmits intermediate features to the middle network which also receives shallower rainy features from the top network and sends back features to the bottom network. Internally, we enforce multi-scale compact constraints on the intermediate layers of deep networks to learn useful features via a Laplacian pyramid. Further, we develop a bidirectional scale-content similarity mining module to explore features at different scales in a down-to-up and up-to-down manner. To improve the model performance on real-world images, we propose an online-update learning approach, which uses real-world rainy images to fine-tune the network and update the deraining results in a self-supervised manner. Extensive experiments demonstrate that our proposed method performs favorably against eleven state-of-the-art methods on five public synthetic datasets and one real-world dataset. The source code will be available at \url{https://supercong94.wixsite.com/supercong94}.

preprint2022arXiv

Poisoning Semi-supervised Federated Learning via Unlabeled Data: Attacks and Defenses

Semi-supervised Federated Learning (SSFL) has recently drawn much attention due to its practical consideration, i.e., the clients may only have unlabeled data. In practice, these SSFL systems implement semi-supervised training by assigning a "guessed" label to the unlabeled data near the labeled data to convert the unsupervised problem into a fully supervised problem. However, the inherent properties of such semi-supervised training techniques create a new attack surface. In this paper, we discover and reveal a simple yet powerful poisoning attack against SSFL. Our attack utilizes the natural characteristic of semi-supervised learning to cause the model to be poisoned by poisoning unlabeled data. Specifically, the adversary just needs to insert a small number of maliciously crafted unlabeled samples (e.g., only 0.1\% of the dataset) to infect model performance and misclassification. Extensive case studies have shown that our attacks are effective on different datasets and common semi-supervised learning methods. To mitigate the attacks, we propose a defense, i.e., a minimax optimization-based client selection strategy, to enable the server to select the clients who hold the correct label information and high-quality updates. Our defense further employs a quality-based aggregation rule to strengthen the contributions of the selected updates. Evaluations under different attack conditions show that the proposed defense can well alleviate such unlabeled poisoning attacks. Our study unveils the vulnerability of SSFL to unlabeled poisoning attacks and provides the community with potential defense methods.

preprint2022arXiv

Push-sum Distributed Dual Averaging for Convex Optimization in Multi-agent Systems with Communication Delays

The distributed convex optimization problem over the multi-agent system is considered in this paper, and it is assumed that each agent possesses its own cost function and communicates with its neighbours over a sequence of time-varying directed graphs. However, due to some reasons there exist communication delays while agents receive information from other agents, and we are going to seek the optimal value of the sum of agents' loss functions in this case. We desire to handle this problem with the push-sum distributed dual averaging (PS-DDA) algorithm. It is proved that this algorithm converges and the error decays at a rate $\mathcal{O}\left(T^{-0.5}\right)$ with proper step size, where $T$ is iteration span. The main result presented in this paper also illustrates the convergence of the proposed algorithm is related to the maximum value of the communication delay on one edge. We finally apply the theoretical results to numerical simulations to show the PS-DDA algorithm's performance.

preprint2022arXiv

Strain Effect on Air-Stability of Monolayer CrSe2

The discovery of two dimensional (2D) magnetic materials has brought great research value for spintronics and data storage devices. However, their air-stability as well as the oxidation mechanism has not been unveiled, which limits their further applications. Here, by first-principles calculations, we carried out a detailed study on the oxidation process of monolayer CrSe2 and biaxial tensile strain effect. We found dissociation process of O2 on pristine CrSe2 sheet is an endothermic reaction with a reaction energy barrier of 0.53 eV, indicating its thermodynamics stability. However, such a process becomes exothermic under a biaxial tensile strain reaching 1%, accompanying with a decreased reaction barrier, leading to reduced stability. These results manifest that in-plane strain plays a significant role in modifying air-stability in CrSe2 and shed considerable light on searching appropriate substrate to stabilize 2D magnetic materials.

preprint2022arXiv

Structural Prior Guided Generative Adversarial Transformers for Low-Light Image Enhancement

We propose an effective Structural Prior guided Generative Adversarial Transformer (SPGAT) to solve low-light image enhancement. Our SPGAT mainly contains a generator with two discriminators and a structural prior estimator (SPE). The generator is based on a U-shaped Transformer which is used to explore non-local information for better clear image restoration. The SPE is used to explore useful structures from images to guide the generator for better structural detail estimation. To generate more realistic images, we develop a new structural prior guided adversarial learning method by building the skip connections between the generator and discriminators so that the discriminators can better discriminate between real and fake features. Finally, we propose a parallel windows-based Swin Transformer block to aggregate different level hierarchical features for high-quality image restoration. Experimental results demonstrate that the proposed SPGAT performs favorably against recent state-of-the-art methods on both synthetic and real-world datasets.

preprint2022arXiv

Teacher Model Fingerprinting Attacks Against Transfer Learning

Transfer learning has become a common solution to address training data scarcity in practice. It trains a specified student model by reusing or fine-tuning early layers of a well-trained teacher model that is usually publicly available. However, besides utility improvement, the transferred public knowledge also brings potential threats to model confidentiality, and even further raises other security and privacy issues. In this paper, we present the first comprehensive investigation of the teacher model exposure threat in the transfer learning context, aiming to gain a deeper insight into the tension between public knowledge and model confidentiality. To this end, we propose a teacher model fingerprinting attack to infer the origin of a student model, i.e., the teacher model it transfers from. Specifically, we propose a novel optimization-based method to carefully generate queries to probe the student model to realize our attack. Unlike existing model reverse engineering approaches, our proposed fingerprinting method neither relies on fine-grained model outputs, e.g., posteriors, nor auxiliary information of the model architecture or training dataset. We systematically evaluate the effectiveness of our proposed attack. The empirical results demonstrate that our attack can accurately identify the model origin with few probing queries. Moreover, we show that the proposed attack can serve as a stepping stone to facilitating other attacks against machine learning models, such as model stealing.

preprint2022arXiv

The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining

In Machine Learning, the emergence of \textit{the right to be forgotten} gave birth to a paradigm named \textit{machine unlearning}, which enables data holders to proactively erase their data from a trained model. Existing machine unlearning techniques focus on centralized training, where access to all holders' training data is a must for the server to conduct the unlearning process. It remains largely underexplored about how to achieve unlearning when full access to all training data becomes unavailable. One noteworthy example is Federated Learning (FL), where each participating data holder trains locally, without sharing their training data to the central server. In this paper, we investigate the problem of machine unlearning in FL systems. We start with a formal definition of the unlearning problem in FL and propose a rapid retraining approach to fully erase data samples from a trained FL model. The resulting design allows data holders to jointly conduct the unlearning process efficiently while keeping their training data locally. Our formal convergence and complexity analysis demonstrate that our design can preserve model utility with high efficiency. Extensive evaluations on four real-world datasets illustrate the effectiveness and performance of our proposed realization.

preprint2022arXiv

Towards Private Learning on Decentralized Graphs with Local Differential Privacy

Many real-world networks are inherently decentralized. For example, in social networks, each user maintains a local view of a social graph, such as a list of friends and her profile. It is typical to collect these local views of social graphs and conduct graph learning tasks. However, learning over graphs can raise privacy concerns as these local views often contain sensitive information. In this paper, we seek to ensure private graph learning on a decentralized network graph. Towards this objective, we propose {\em Solitude}, a new privacy-preserving learning framework based on graph neural networks (GNNs), with formal privacy guarantees based on edge local differential privacy. The crux of {\em Solitude} is a set of new delicate mechanisms that can calibrate the introduced noise in the decentralized graph collected from the users. The principle behind the calibration is the intrinsic properties shared by many real-world graphs, such as sparsity. Unlike existing work on locally private GNNs, our new framework can simultaneously protect node feature privacy and edge privacy, and can seamlessly incorporate with any GNN with privacy-utility guarantees. Extensive experiments on benchmarking datasets show that {\em Solitude} can retain the generalization capability of the learned GNN while preserving the users' data privacy under given privacy budgets.

preprint2022arXiv

Towards Robust 3D Object Recognition with Dense-to-Sparse Deep Domain Adaptation

Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense point clouds and performance drops significantly for sparse point clouds. Unsupervised domain adaption allows to minimise the discrepancy between dense and sparse point clouds with minimal unlabelled sparse point clouds, thereby saving additional sparse data collection, annotation and retraining costs. In this work, we propose a novel method for point cloud based object recognition with competitive performance with state-of-art methods on dense and sparse point clouds while being trained only with dense point clouds.

preprint2022arXiv

Variational Distillation for Multi-View Learning

Information Bottleneck (IB) based multi-view learning provides an information theoretic principle for seeking shared information contained in heterogeneous data descriptions. However, its great success is generally attributed to estimate the multivariate mutual information which is intractable when the network becomes complicated. Moreover, the representation learning tradeoff, {\it i.e.}, prediction-compression and sufficiency-consistency tradeoff, makes the IB hard to satisfy both requirements simultaneously. In this paper, we design several variational information bottlenecks to exploit two key characteristics ({\it i.e.}, sufficiency and consistency) for multi-view representation learning. Specifically, we propose a Multi-View Variational Distillation (MV$^2$D) strategy to provide a scalable, flexible and analytical solution to fitting MI by giving arbitrary input of viewpoints but without explicitly estimating it. Under rigorously theoretical guarantee, our approach enables IB to grasp the intrinsic correlation between observations and semantic labels, producing predictive and compact representations naturally. Also, our information-theoretic constraint can effectively neutralize the sensitivity to heterogeneous data by eliminating both task-irrelevant and view-specific information, preventing both tradeoffs in multiple view cases. To verify our theoretically grounded strategies, we apply our approaches to various benchmarks under three different applications. Extensive experiments to quantitatively and qualitatively demonstrate the effectiveness of our approach against state-of-the-art methods.

preprint2021arXiv

CHEETAH: An Ultra-Fast, Approximation-Free, and Privacy-Preserved Neural Network Framework based on Joint Obscure Linear and Nonlinear Computations

Machine Learning as a Service (MLaaS) is enabling a wide range of smart applications on end devices. However, such convenience comes with a cost of privacy because users have to upload their private data to the cloud. This research aims to provide effective and efficient MLaaS such that the cloud server learns nothing about user data and the users cannot infer the proprietary model parameters owned by the server. This work makes the following contributions. First, it unveils the fundamental performance bottleneck of existing schemes due to the heavy permutations in computing linear transformation and the use of communication intensive Garbled Circuits for nonlinear transformation. Second, it introduces an ultra-fast secure MLaaS framework, CHEETAH, which features a carefully crafted secret sharing scheme that runs significantly faster than existing schemes without accuracy loss. Third, CHEETAH is evaluated on the benchmark of well-known, practical deep networks such as AlexNet and VGG-16 on the MNIST and ImageNet datasets. The results demonstrate more than 100x speedup over the fastest GAZELLE (Usenix Security'18), 2000x speedup over MiniONN (ACM CCS'17) and five orders of magnitude speedup over CryptoNets (ICML'16). This significant speedup enables a wide range of practical applications based on privacy-preserved deep neural networks.

preprint2021arXiv

Chirality locking charge density waves in a chiral crystal

In Weyl semimetals, charge density wave (CDW) order can spontaneously break the chiral symmetry, gap out the Weyl nodes, and drive the material into the axion insulating phase. Investigations have however been limited since CDWs are rarely seen in Weyl semimetals. Here, using scanning tunneling microscopy/spectroscopy, we report the discovery of a novel unidirectional CDW order on the (001) surface of chiral crystal CoSi - a unique Weyl semimetal with unconventional chiral fermions. The CDW is incommensurate with both lattice momentum and crystalline symmetry directions, and exhibits an intra unit cell π phase shift in the layer stacking direction. The tunneling spectrum shows a particle-hole asymmetric V-shaped energy gap around the Fermi level that modulates spatially with the CDW wave vector. Combined with first-principle calculations, we identify that the CDW is locked to the crystal chirality and is related by a mirror reflection between the two enantiomers of the chiral crystal. Our findings reveal a novel correlated topological quantum state in chiral CoSi crystals and raise the potential for realizing an axion insulator and exploring the unprecedented physical behaviors of unconventional chiral fermions.

preprint2021arXiv

FWB-Net:Front White Balance Network for Color Shift Correction in Single Image Dehazing via Atmospheric Light Estimation

In recent years, single image dehazing deep models based on Atmospheric Scattering Model (ASM) have achieved remarkable results. But the dehazing outputs of those models suffer from color shift. Analyzing the ASM model shows that the atmospheric light factor (ALF) is set as a scalar which indicates ALF is constant for whole image. However, for images taken in real-world, the illumination is not uniformly distributed over whole image which brings model mismatch and possibly results in color shift of the deep models using ASM. Bearing this in mind, in this study, first, a new non-homogeneous atmospheric scattering model (NH-ASM) is proposed for improving image modeling of hazy images taken under complex illumination conditions. Second, a new U-Net based front white balance module (FWB-Module) is dedicatedly designed to correct color shift before generating dehazing result via atmospheric light estimation. Third, a new FWB loss is innovatively developed for training FWB-Module, which imposes penalty on color shift. In the end, based on NH-ASM and front white balance technology, an end-to-end CNN-based color-shift-restraining dehazing network is developed, termed as FWB-Net. Experimental results demonstrate the effectiveness and superiority of our proposed FWB-Net for dehazing on both synthetic and real-world images.

preprint2021arXiv

Global existence and spatial analyticity for a nonlocal flux with fractional diffusion

In this paper, we study a one dimensional nonlinear equation with diffusion $-ν(-\partial_{xx})^{\fracα{2}}$ for $0\leq α\leq 2$ and $ν>0$. We use a viscous-splitting algorithm to obtain global nonnegative weak solutions in space $L^1(\mathbb{R})\cap H^{1/2}(\mathbb{R})$ when $0\leqα\leq 2$. For subcritical $1<α\leq 2$ and critical case $α=1$, we obtain global existence and uniqueness of nonnegative spatial analytic solutions. We use a fractional bootstrap method to improve the regularity of mild solutions in Bessel potential spaces for subcritical case $1<α\leq 2$. Then, we show that the solutions are spatial analytic and can be extended globally. For the critical case $α=1$, if the initial data $ρ_0$ satisfies $-ν<\infρ_0<0$, we use the characteristics methods for complex Burgers equation to obtain a unique spatial analytic solution to our target equation in some bounded time interval. If $ρ_0\geq0$, the solution exists globally and converges to steady state.

preprint2021arXiv

ORBBuf: A Robust Buffering Method for Remote Visual SLAM

The data loss caused by unreliable network seriously impacts the results of remote visual SLAM systems. From our experiment, a loss of less than 1 second of data can cause a visual SLAM algorithm to lose tracking. We present a novel buffering method, ORBBuf, to reduce the impact of data loss on remote visual SLAM systems. We model the buffering problem as an optimization problem by introducing a similarity metric between frames. To solve the buffering problem, we present an efficient greedy-like algorithm to discard the frames that have the least impact on the quality of SLAM results. We implement our ORBBuf method on ROS, a widely used middleware framework. Through an extensive evaluation on real-world scenarios and tens of gigabytes of datasets, we demonstrate that our ORBBuf method can be applied to different state-estimation algorithms (DSO and VINS-Fusion), different sensor data (both monocular images and stereo images), different scenes (both indoor and outdoor), and different network environments (both WiFi networks and 4G networks). Our experimental results indicate that the network losses indeed affect the SLAM results, and our ORBBuf method can reduce the RMSE up to 50 times comparing with the Drop-Oldest and Random buffering methods.

preprint2021arXiv

SUOD: Accelerating Large-Scale Unsupervised Heterogeneous Outlier Detection

Outlier detection (OD) is a key machine learning (ML) task for identifying abnormal objects from general samples with numerous high-stake applications including fraud detection and intrusion detection. Due to the lack of ground truth labels, practitioners often have to build a large number of unsupervised, heterogeneous models (i.e., different algorithms with varying hyperparameters) for further combination and analysis, rather than relying on a single model. How to accelerate the training and scoring on new-coming samples by outlyingness (referred as prediction throughout the paper) with a large number of unsupervised, heterogeneous OD models? In this study, we propose a modular acceleration system, called SUOD, to address it. The proposed system focuses on three complementary acceleration aspects (data reduction for high-dimensional data, approximation for costly models, and taskload imbalance optimization for distributed environment), while maintaining performance accuracy. Extensive experiments on more than 20 benchmark datasets demonstrate SUOD's effectiveness in heterogeneous OD acceleration, along with a real-world deployment case on fraudulent claim analysis at IQVIA, a leading healthcare firm. We open-source SUOD for reproducibility and accessibility.

preprint2020arXiv

A Framework for Behavioral Biometric Authentication using Deep Metric Learning on Mobile Devices

Mobile authentication using behavioral biometrics has been an active area of research. Existing research relies on building machine learning classifiers to recognize an individual's unique patterns. However, these classifiers are not powerful enough to learn the discriminative features. When implemented on the mobile devices, they face new challenges from the behavioral dynamics, data privacy and side-channel leaks. To address these challenges, we present a new framework to incorporate training on battery-powered mobile devices, so private data never leaves the device and training can be flexibly scheduled to adapt the behavioral patterns at runtime. We re-formulate the classification problem into deep metric learning to improve the discriminative power and design an effective countermeasure to thwart side-channel leaks by embedding a noise signature in the sensing signals without sacrificing too much usability. The experiments demonstrate authentication accuracy over 95% on three public datasets, a sheer 15% gain from multi-class classification with less data and robustness against brute-force and side-channel attacks with 99% and 90% success, respectively. We show the feasibility of training with mobile CPUs, where training 100 epochs takes less than 10 mins and can be boosted 3-5 times with feature transfer. Finally, we profile memory, energy and computational overhead. Our results indicate that training consumes lower energy than watching videos and slightly higher energy than playing games.

preprint2020arXiv

A Gd@C82-based single molecular electret device with switchable electrical polarization

Single molecular electrets exhibiting single molecule electric polarization switching have been long desired as a platform for extremely small non-volatile storage devices, although it is controversial because of the poor stability of single molecular electric dipoles. Here we study the single molecular device of GdC82, where the encapsulated Gd atom forms a charge center, and we have observed a gate controlled switching behavior between two sets of single electron transport stability diagrams. The switching is operated in a hysteresis loop with a coercive gate field of around 0.5Vnm. Theoretical calculations have assigned the two conductance diagrams to corresponding energy levels of two states that the Gd atom is trapped at two different sites of the C82 cage, which possess two different permanent electrical dipole orientations. The two dipole states are stabilized by the anisotropic energy and separated by a transition energy barrier of 70 meV. Such switching is then accessed to the electric field driven reorientation of individual dipole while overcoming the barriers by the coercive gate field, and demonstrates the creation of a single molecular electret.

preprint2020arXiv

A novel sentence embedding based topic detection method for micro-blog

Topic detection is a challenging task, especially without knowing the exact number of topics. In this paper, we present a novel approach based on neural network to detect topics in the micro-blogging dataset. We use an unsupervised neural sentence embedding model to map the blogs to an embedding space. Our model is a weighted power mean word embedding model, and the weights are calculated by attention mechanism. Experimental result shows our embedding method performs better than baselines in sentence clustering. In addition, we propose an improved clustering algorithm referred as relationship-aware DBSCAN (RADBSCAN). It can discover topics from a micro-blogging dataset, and the topic number depends on dataset character itself. Moreover, in order to solve the problem of parameters sensitive, we take blog forwarding relationship as a bridge of two independent clusters. Finally, we validate our approach on a dataset from sina micro-blog. The result shows that we can detect all the topics successfully and extract keywords in each topic.

preprint2020arXiv

Bethe-Slater-curve-like behavior and interlayer spin-exchange coupling mechanisms in two-dimensional magnetic bilayers

Layered magnets have recently received tremendous attention, however, spin-exchange coupling mechanism across their interlayer regions is yet to be revealed. Here, we report a Bethe-Slater-curve (BSC) like behavior in nine transition metal dichalcogenide bilayers (MX2, M=V, Cr, Mn; X=S, Se, Te) and established interlayer spin-exchange coupling mechanisms at their van der Waals gaps using first-principle calculations. The BSC-like behavior offers a distance-dependent interlayer anti-ferromagnetic (AFM) to ferromagnetic (FM) transition. This phenomenon is explained with the spin-exchange coupling mechanisms established using bilayer CrSe2 as a prototype in this work. The Se pz wavefunctions from two adjacent interfacial Se sublayers overlap at the interlayer region. The spin alignment of the region determines interlayer magnetic coupling. At a shorter interlayer distance, Pauli repulsion at the overlapped region dominates and thus favors anti-parallel oriented spins leading to interlayer AFM. For a longer distance, kinetic energy gain of polarized electrons across the bilayer balances the Pauli repulsion and the bilayer thus prefers an interlayer FM state. In light of this, the AFM-FM transition is a result of competition between Pauli and Coulomb repulsion and kinetic energy gain. All these results open a new route to tune interlayer magnetism and the revealed spin-exchange coupling mechanisms are paramount additions to those previously established ones.

preprint2020arXiv

DCSFN: Deep Cross-scale Fusion Network for Single Image Rain Removal

Rain removal is an important but challenging computer vision task as rain streaks can severely degrade the visibility of images that may make other visions or multimedia tasks fail to work. Previous works mainly focused on feature extraction and processing or neural network structure, while the current rain removal methods can already achieve remarkable results, training based on single network structure without considering the cross-scale relationship may cause information drop-out. In this paper, we explore the cross-scale manner between networks and inner-scale fusion operation to solve the image rain removal task. Specifically, to learn features with different scales, we propose a multi-sub-networks structure, where these sub-networks are fused via a crossscale manner by Gate Recurrent Unit to inner-learn and make full use of information at different scales in these sub-networks. Further, we design an inner-scale connection block to utilize the multi-scale information and features fusion way between different scales to improve rain representation ability and we introduce the dense block with skip connection to inner-connect these blocks. Experimental results on both synthetic and real-world datasets have demonstrated the superiority of our proposed method, which outperforms over the state-of-the-art methods. The source code will be available at https://supercong94.wixsite.com/supercong94.

preprint2020arXiv

Gate-tunable van der Waals heterostructure for reconfigurable neural network vision sensor

Early processing of visual information takes place in the human retina. Mimicking neurobiological structures and functionalities of the retina provide a promising pathway to achieving vision sensor with highly efficient image processing. Here, we demonstrate a prototype vision sensor that operates via the gate-tunable positive and negative photoresponses of the van der Waals (vdW) vertical heterostructures. The sensor emulates not only the neurobiological functionalities of bipolar cells and photoreceptors but also the unique synaptic connectivity between bipolar cells and photoreceptors. By tuning gate voltage for each pixel, we achieve reconfigurable vision sensor for simultaneously image sensing and processing. Furthermore, our prototype vision sensor itself can be trained to classify the input images, via updating the gate voltages applied individually to each pixel in the sensor. Our work indicates that vdW vertical heterostructures offer a promising platform for the development of neural network vision sensor.

preprint2020arXiv

Joint Self-Attention and Scale-Aggregation for Self-Calibrated Deraining Network

In the field of multimedia, single image deraining is a basic pre-processing work, which can greatly improve the visual effect of subsequent high-level tasks in rainy conditions. In this paper, we propose an effective algorithm, called JDNet, to solve the single image deraining problem and conduct the segmentation and detection task for applications. Specifically, considering the important information on multi-scale features, we propose a Scale-Aggregation module to learn the features with different scales. Simultaneously, Self-Attention module is introduced to match or outperform their convolutional counterparts, which allows the feature aggregation to adapt to each channel. Furthermore, to improve the basic convolutional feature transformation process of Convolutional Neural Networks (CNNs), Self-Calibrated convolution is applied to build long-range spatial and inter-channel dependencies around each spatial location that explicitly expand fields-of-view of each convolutional layer through internal communications and hence enriches the output features. By designing the Scale-Aggregation and Self-Attention modules with Self-Calibrated convolution skillfully, the proposed model has better deraining results both on real-world and synthetic datasets. Extensive experiments are conducted to demonstrate the superiority of our method compared with state-of-the-art methods. The source code will be available at \url{https://supercong94.wixsite.com/supercong94}.

preprint2020arXiv

Kullback-Leibler Divergence-Based Fuzzy $C$-Means Clustering Incorporating Morphological Reconstruction and Wavelet Frames for Image Segmentation

Although spatial information of images usually enhance the robustness of the Fuzzy C-Means (FCM) algorithm, it greatly increases the computational costs for image segmentation. To achieve a sound trade-off between the segmentation performance and the speed of clustering, we come up with a Kullback-Leibler (KL) divergence-based FCM algorithm by incorporating a tight wavelet frame transform and a morphological reconstruction operation. To enhance FCM's robustness, an observed image is first filtered by using the morphological reconstruction. A tight wavelet frame system is employed to decompose the observed and filtered images so as to form their feature sets. Considering these feature sets as data of clustering, an modified FCM algorithm is proposed, which introduces a KL divergence term in the partition matrix into its objective function. The KL divergence term aims to make membership degrees of each image pixel closer to those of its neighbors, which brings that the membership partition becomes more suitable and the parameter setting of FCM becomes simplified. On the basis of the obtained partition matrix and prototypes, the segmented feature set is reconstructed by minimizing the inverse process of the modified objective function. To modify abnormal features produced in the reconstruction process, each reconstructed feature is reassigned to the closest prototype. As a result, the segmentation accuracy of KL divergence-based FCM is further improved. What's more, the segmented image is reconstructed by using a tight wavelet frame reconstruction operation. Finally, supporting experiments coping with synthetic, medical and color images are reported. Experimental results exhibit that the proposed algorithm works well and comes with better segmentation performance than other comparative algorithms. Moreover, the proposed algorithm requires less time than most of the FCM-related algorithms.

preprint2020arXiv

Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping

Agile control of mobile manipulator is challenging because of the high complexity coupled by the robotic system and the unstructured working environment. Tracking and grasping a dynamic object with a random trajectory is even harder. In this paper, a multi-task reinforcement learning-based mobile manipulation control framework is proposed to achieve general dynamic object tracking and grasping. Several basic types of dynamic trajectories are chosen as the task training set. To improve the policy generalization in practice, random noise and dynamics randomization are introduced during the training process. Extensive experiments show that our policy trained can adapt to unseen random dynamic trajectories with about 0.1m tracking error and 75\% grasping success rate of dynamic objects. The trained policy can also be successfully deployed on a real mobile manipulator.

preprint2020arXiv

Physical Model Guided Deep Image Deraining

Single image deraining is an urgent task because the degraded rainy image makes many computer vision systems fail to work, such as video surveillance and autonomous driving. So, deraining becomes important and an effective deraining algorithm is needed. In this paper, we propose a novel network based on physical model guided learning for single image deraining, which consists of three sub-networks: rain streaks network, rain-free network, and guide-learning network. The concatenation of rain streaks and rain-free image that are estimated by rain streaks network, rain-free network, respectively, is input to the guide-learning network to guide further learning and the direct sum of the two estimated images is constrained with the input rainy image based on the physical model of rainy image. Moreover, we further develop the Multi-Scale Residual Block (MSRB) to better utilize multi-scale information and it is proved to boost the deraining performance. Quantitative and qualitative experimental results demonstrate that the proposed method outperforms the state-of-the-art deraining methods. The source code will be available at \url{https://supercong94.wixsite.com/supercong94}.

preprint2020arXiv

Towards Efficient Scheduling of Federated Mobile Devices under Computational and Statistical Heterogeneity

Originated from distributed learning, federated learning enables privacy-preserved collaboration on a new abstracted level by sharing the model parameters only. While the current research mainly focuses on optimizing learning algorithms and minimizing communication overhead left by distributed learning, there is still a considerable gap when it comes to the real implementation on mobile devices. In this paper, we start with an empirical experiment to demonstrate computation heterogeneity is a more pronounced bottleneck than communication on the current generation of battery-powered mobile devices, and the existing methods are haunted by mobile stragglers. Further, non-identically distributed data across the mobile users makes the selection of participants critical to the accuracy and convergence. To tackle the computational and statistical heterogeneity, we utilize data as a tuning knob and propose two efficient polynomial-time algorithms to schedule different workloads on various mobile devices, when data is identically or non-identically distributed. For identically distributed data, we combine partitioning and linear bottleneck assignment to achieve near-optimal training time without accuracy loss. For non-identically distributed data, we convert it into an average cost minimization problem and propose a greedy algorithm to find a reasonable balance between computation time and accuracy. We also establish an offline profiler to quantify the runtime behavior of different devices, which serves as the input to the scheduling algorithms. We conduct extensive experiments on a mobile testbed with two datasets and up to 20 devices. Compared with the common benchmarks, the proposed algorithms achieve 2-100x speedup epoch-wise, 2-7% accuracy gain and boost the convergence rate by more than 100% on CIFAR10.

preprint2020arXiv

Towards Privacy-assured and Lightweight On-chain Auditing of Decentralized Storage

How to audit outsourced data in centralized storage like cloud is well-studied, but it is largely under-explored for the rising decentralized storage network (DSN) that bodes well for a billion-dollar market. To realize DSN as a usable service in a truly decentralized manner, the blockchain comes in handy -- to record and verify audit trails in forms of proof of storage, and based on that, to handle fair payments with necessary dispute resolution. Leaving the audit trails on the blockchain offers transparency and fairness, yet it 1) sacrifices privacy, as they may leak information about the data under audit, and 2) overwhelms on-chain resources, as they may be practically large in size and expensive to verify. Prior auditing designs in centralized settings are not directly applicable here. A handful of proposals targeting DSN cannot satisfactorily address these issues either. We present an auditing solution that addresses on-chain privacy and efficiency, from a synergy of homomorphic linear authenticators with polynomial commitments for succinct proofs, and the sigma protocol for provable privacy. The solution results in, per audit, 288-byte proof written to the blockchain, and constant verification cost. It can sustain long-term operation and easily scale to thousands of users on Ethereum.

preprint2020arXiv

Two-path interference for enantiomer-selective state transfer of chiral molecules

With a microwave-regime cyclic three-state configuration, an enantiomer-selective state transfer~(ESST) is carried out through the two-path interference between a direct one-photon coupling and an effective two-photon coupling. The $π$-phase difference in the one-photon process between two enantiomers makes the interference constructive for one enantiomer but destructive for the other. Therefore only one enantiomer is excited into a higher rotational state while the other remains in the ground state. The scheme is of flexibility in the pulse waveforms and the time order of two paths. We simulate the scheme in a sample of cyclohexylmethanol~(C$_7$H$_{14}$O) molecules. Simulative results show the robust and high-fidelity ESST can be obtained when experimental concerns are considered. Finally, we propose to employ the finished ESST in implementing enantio-separation and determining enantiomeric excess.

preprint2019arXiv

Domain wall pinning and hard magnetic phase in Co-doped bulk single crystalline Fe3GeTe2

We report the effects of cobalt doping on the magnetic properties of two-dimensional van der Waals ferromagnet Fe3GeTe2. Single crystals of (Fe{1-x}Cox)3GeTe2 with x=0-0.78 were successfully synthesized and characterized with x-ray diffraction, energy dispersive x-ray spectroscopy and magnetization measurements. Both the Curie-Weiss temperature and ferromagnetic (FM) ordered moment of Fe3GeTe2 are gradually suppressed upon Co doping. A kink in zero-field-cooling low field M(T) curve which is previously explained as an antiferromagnetic transition is observed for samples with x=0-0.58. Our detailed magnetization measurements and theoretical calculations strongly suggest that this kink is originated from the pinning of magnetic domain walls. The domain pinning effects are suddenly enhanced when the doping concentration of cobalt is around 50%, both the coercive field Hc and the magnetic remanence to saturated magnetization ratio MR/MS are largely improved and a hard magnetic phase emerges in bulk single crystal samples. The strong doping dependent magnetic properties suggest more spintronic applications of Fe3GeTe2.

preprint2019arXiv

Hierarchical Clustering Supported by Reciprocal Nearest Neighbors

Clustering is a fundamental analysis tool aiming at classifying data points into groups based on their similarity or distance. It has found successful applications in all natural and social sciences, including biology, physics, economics, chemistry, astronomy, psychology, and so on. Among numerous existent algorithms, hierarchical clustering algorithms are of a particular advantage as they can provide results under different resolutions without any predetermined number of clusters and unfold the organization of resulted clusters. At the same time, they suffer a variety of drawbacks and thus are either time-consuming or inaccurate. We propose a novel hierarchical clustering approach on the basis of a simple hypothesis that two reciprocal nearest data points should be grouped in one cluster. Extensive tests on data sets across multiple domains show that our method is much faster and more accurate than the state-of-the-art benchmarks. We further extend our method to deal with the community detection problem in real networks, achieving remarkably better results in comparison with the well-known Girvan-Newman algorithm.

preprint2019arXiv

Single-Layer CrI3 Grown by Molecular Beam Epitaxy

Single- and few-layer chromium triiodide (CrI3), which has been intensively investigated as a promising platform for two-dimensional magnetism, was usually prepared by mechanical exfoliation. Here, we report on the growth of single-layer CrI3 by molecular beam epitaxy under ultrahigh vacuum. The atomic structures and local density of states have been revealed by scanning tunneling microscopy (STM). Iodine trimers, each of which consists of three I atoms surrounding a three-fold Cr honeycomb center, have been identified as the basic units of the topmost I layer. Different superstructures of single-layer CrI3 with characteristic periodicity around 2-4 nm were obtained on Au(111), but only pristine structure was observed on graphite. At elevated temperatures (423 K), CrI3 was partially decomposed, resulting in the formation of single-layer chromium diiodide. Our bias-dependent STM images suggest that the unoccupied and occupied states are distributed spatial-separately, which is consistent with our density functional theory calculations. The effect of charge distribution on the superexchange interaction in single-layer CrI3 was discussed.

preprint2019arXiv

Strain tunable pudding-mold-type band structure and thermoelectric properties of SnP$_3$ monolayer

Recent studies indicated the interesting metal-to-semiconductor transition when layered bulk GeP3 and SnP3 are restricted to the monolayer or bilayer, and SnP3 monolayer has been predicted to possess high carrier mobility and promising thermoelectric performance. Here, we investigate the biaxial strain effect on the electronic and thermoelectric properties of SnP3 monolayer. Our first-principles calculations combined with Boltzmann transport theory indicate that SnP3 monolayer has the pudding-mold-type valence band structure, giving rise to a large p-type Seebeck coefficient and a high p-type power factor. The compressive biaxial strain can decrease the energy gap and result in the metallicity. In contrast, the tensile biaxial strain increases the energy gap, and increases the n-type Seebeck coefficient and decreases the n-type electrical conductivity. Although the lattice thermal conductivity becomes larger at a tensile biaxial strain due to the increased maximum frequency of the acoustic phonon modes and the increased phonon group velocity, it is still low, only e.g. 3.1 W/(mK) at room temperature with the 6% tensile biaxial strain. Therefore, SnP3 monolayer is a good thermoelectric material with low lattice thermal conductivity even at the 6% tensile strain, and the tensile strain is beneficial to the increase of the n-type Seebeck coefficient.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Source provenance

Where this author record came from

arxivconfidence 95%

external id: arxiv:2507.10370:author:7:cong-wang

Imported May 21, 2026Synced May 21, 2026

arxivconfidence 95%

external id: arxiv:2512.10291:author:1:cong-wang

Imported May 21, 2026Synced May 21, 2026

arxivconfidence 95%

external id: arxiv:2512.24022:author:7:cong-wang

Imported May 21, 2026Synced May 21, 2026

arxivconfidence 95%

external id: arxiv:2605.20104:author:12:cong-wang

Imported May 20, 2026Synced May 21, 2026

arxivconfidence 95%

external id: arxiv:2604.27340:author:2:cong-wang