BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Zi Wang

Zi Wang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine Learningphysics.med-phBiological PhysicsComputer Visioneess.SPArtificial Intelligencecond-mat.mes-halleess.IVcond-mat.mtrl-sciCryptography and Securitymath.SPphysics.app-phphysics.chem-phphysics.plasm-phProgramming Languagesquant-phSoftware Engineering

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
18works
0followers
17topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

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

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

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.

Published work

18 published item(s)

preprint2026arXiv

PaceVGGT: Pre-Alternating-Attention Token Pruning for Visual Geometry Transformers

Visual Geometry Transformer (VGGT) is a strong feed-forward model for multiple 3D tasks, but its Alternating-Attention (AA) stack scales quadratically in the total token count, making long clips expensive. Existing token-reduction accelerators operate inside AA, leaving the patch grid that enters AA uncompressed. We introduce PaceVGGT, a pre-AA token pruning framework that prunes DINO patch tokens before the first AA block of a frozen VGGT. PaceVGGT trains a lightweight Token Scorer that estimates per-token importance from DINO features. The scorer is first distilled against an AA-internal attention target from the unpruned backbone, then refined under downstream camera, depth, and point-map losses. A per-frame keep budget fixes the backbone-visible sequence length, while an importance-adaptive merge/prune assignment preserves residual content from high-saliency frames under a fixed total merge budget. A Feature-guided Restoration module reconstructs the dense spatial grid required by the prediction heads. On ScanNet-50 and 7-Scenes, PaceVGGT remains on the reconstruction quality--latency frontier while reducing inference latency. On ScanNet-50, it reduces latency by \(5.1\times\) over unmodified VGGT at \(N=300\) and \(1.47\times\) over LiteVGGT at \(N=1000\). These results identify pre-AA pruning as a viable acceleration route for frozen VGGT-style geometry transformers.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

PhysDepth: Plug-and-Play Physical Refinement for Monocular Depth Estimation in Challenging Environments

State-of-the-art monocular depth estimation (MDE) models often struggle in challenging environments, primarily because they overlook robust physical information. To demonstrate this, we first conduct an empirical study by computing the covariance between a model's prediction error and atmospheric attenuation. We find that the error of existing SOTAs increases with atmospheric attenuation. Based on this finding, we propose PhysDepth, a plug-and-play framework that solves this fragility by infusing physical priors into modern SOTA backbones. PhysDepth incorporates two key components: a Physical Prior Module (PPM) that leverages Rayleigh Scattering theory to extract robust features from the high-SNR red channel, and a physics-derived Red Channel Attenuation Loss (RCA) that enforces model to learn the Beer-Lambert law. Extensive evaluations demonstrate that PhysDepth achieves SOTA accuracy in challenging conditions.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Self-Supervised Spatial And Zero-Shot Angular Super-Resolution by Spatial-Angular Implicit Representation For Rotating-View SNR-Efficient Diffusion MRI

Rotating-view thick-slice acquisition is highly SNR-efficient for mesoscale diffusion MRI (dMRI) but requires numerous rotating views to satisfy Nyquist sampling, resulting in long scan time. We propose a self-supervised Spatial-Angular Implicit Neural Representation (SA-INR) that reconstructs high-resolution dMRI from a single view per diffusion direction, representing a massive acceleration. Our model, an MLP conditioned on a b=0 structural prior and the b-direction via FiLM, is trained end-to-end on the anisotropic input. The framework not only accurately reconstructs the trained b-directions (spatial SR) but also learns a continuous q-space representation, enabling high-fidelity "zero-shot" synthesis of unseen b-directions (angular SR). On simulated data, our method achieved high fidelity for both trained (34.82 dB) and unseen (33.08 dB) directions. Most importantly, the synthesized angular data also improved the quantitative accuracy of downstream DTI model fitting. Our SA-INR framework breaks the classical sampling limits, paving the way for fast, quantitative high-resolution dMRI.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Sparse Model-inspired Deep Thresholding Network for Exponential Signal Reconstruction -- Application in Fast Biological Spectroscopy

The non-uniform sampling is a powerful approach to enable fast acquisition but requires sophisticated reconstruction algorithms. Faithful reconstruction from partial sampled exponentials is highly expected in general signal processing and many applications. Deep learning has shown astonishing potential in this field but many existing problems, such as lack of robustness and explainability, greatly limit its applications. In this work, by combining merits of the sparse model-based optimization method and data-driven deep learning, we propose a deep learning architecture for spectra reconstruction from undersampled data, called MoDern. It follows the iterative reconstruction in solving a sparse model to build the neural network and we elaborately design a learnable soft-thresholding to adaptively eliminate the spectrum artifacts introduced by undersampling. Extensive results on both synthetic and biological data show that MoDern enables more robust, high-fidelity, and ultra-fast reconstruction than the state-of-the-art methods. Remarkably, MoDern has a small number of network parameters and is trained on solely synthetic data while generalizing well to biological data in various scenarios. Furthermore, we extend it to an open-access and easy-to-use cloud computing platform (XCloud-MoDern), contributing a promising strategy for further development of biological applications.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Ear Wearable (Earable) User Authentication via Acoustic Toothprint

Earables (ear wearables) is rapidly emerging as a new platform encompassing a diverse range of personal applications. The traditional authentication methods hence become less applicable and inconvenient for earables due to their limited input interface. Nevertheless, earables often feature rich around-the-head sensing capability that can be leveraged to capture new types of biometrics. In this work, we proposeToothSonic which leverages the toothprint-induced sonic effect produced by users performing teeth gestures for earable authentication. In particular, we design representative teeth gestures that can produce effective sonic waves carrying the information of the toothprint. To reliably capture the acoustic toothprint, it leverages the occlusion effect of the ear canal and the inward-facing microphone of the earables. It then extracts multi-level acoustic features to reflect the intrinsic toothprint information for authentication. The key advantages of ToothSonic are that it is suitable for earables and is resistant to various spoofing attacks as the acoustic toothprint is captured via the user's private teeth-ear channel that modulates and encrypts the sonic waves. Our experiment studies with 25 participants show that ToothSonic achieves up to 95% accuracy with only one of the users' tooth gestures.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Enhancing Innate and Adaptive Immune Systems by Cold Atmospheric Plasma (CAP) and Its Antitumor Immunity

Cold atmospheric plasma (CAP) is a near room temperature ionized gas, generated under non-equilibrium discharge conditions. Here we show that a short exposure of rat peritoneal exudate macrophages and T-cells to CAP in vitro, triggered an inflammatory phenotype leading to better antigen-presenting and effector cell function respectively. Different from previous studies mainly using immortalized cell lines, both macrophage and T-cells in this study were primary cells isolated from mice. Furthermore, ex-vivo exposure of T-cells to CAP, followed by their adoptive transfer into tumor-bearing mice resulted in a strong antitumor effect in vivo. Mechanistically, CAP seems to disrupt tolerogenic pathways leading to enhanced production of pro-inflammatory cytokines while limiting the production of anti-inflammatory cytokines and the expression of inhibitory molecules such as programmed death-ligand 1 (PD-L1). CAP represents therefore a novel, non-toxic and easy to deliver technology to augment the function of immune cells and enhance antitumor responses when used as a component of T-cell adoptive immunotherapies strategies or, potentially in combination with other cancer immunotherapeutic approaches.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Geometric thermodynamic uncertainty relation in periodically driven thermoelectric heat engine

Thermodynamic uncertainty relation, quantifying a trade-off among average current, the associated fluctuation (precision), and entropy production (cost), has been formulated in nonequilibrium steady state and various stochastic systems. Herein, we study the thermodynamic uncertainty relation in generic thermoelectric heat engines under a periodic control protocol, by uncovering the underlying Berry-phase-like contribution. We show that our thermodynamic uncertainty relation breaks the seminal steady-state results, originating from the non-vanishing geometric effect. Furthermore, by deriving the consequent trade-off relation binding efficiency, power, and constancy, we prove that the periodically driven thermoelectric heat engines can generally outperform the steady-state analogies. The general bounds are illustrated by an analytically solvable two-terminal single quantum dot heat engine under the periodic modulation. Our work provides a geometric framework in bounding and optimizing a wide range of periodically driven thermoelectric thermal machines.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Physics-driven Synthetic Data Learning for Biomedical Magnetic Resonance

Deep learning has innovated the field of computational imaging. One of its bottlenecks is unavailable or insufficient training data. This article reviews an emerging paradigm, imaging physics-based data synthesis (IPADS), that can provide huge training data in biomedical magnetic resonance without or with few real data. Following the physical law of magnetic resonance, IPADS generates signals from differential equations or analytical solution models, making the learning more scalable, explainable, and better protecting privacy. Key components of IPADS learning, including signal generation models, basic deep learning network structures, enhanced data generation, and learning methods are discussed. Great potentials of IPADS have been demonstrated by representative applications in fast imaging, ultrafast signal reconstruction and accurate parameter quantification. Finally, open questions and future work have been discussed.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Plex: Towards Reliability using Pretrained Large Model Extensions

A recent trend in artificial intelligence is the use of pretrained models for language and vision tasks, which have achieved extraordinary performance but also puzzling failures. Probing these models' abilities in diverse ways is therefore critical to the field. In this paper, we explore the reliability of models, where we define a reliable model as one that not only achieves strong predictive performance but also performs well consistently over many decision-making tasks involving uncertainty (e.g., selective prediction, open set recognition), robust generalization (e.g., accuracy and proper scoring rules such as log-likelihood on in- and out-of-distribution datasets), and adaptation (e.g., active learning, few-shot uncertainty). We devise 10 types of tasks over 40 datasets in order to evaluate different aspects of reliability on both vision and language domains. To improve reliability, we developed ViT-Plex and T5-Plex, pretrained large model extensions for vision and language modalities, respectively. Plex greatly improves the state-of-the-art across reliability tasks, and simplifies the traditional protocol as it improves the out-of-the-box performance and does not require designing scores or tuning the model for each task. We demonstrate scaling effects over model sizes up to 1B parameters and pretraining dataset sizes up to 4B examples. We also demonstrate Plex's capabilities on challenging tasks including zero-shot open set recognition, active learning, and uncertainty in conversational language understanding.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Pre-training helps Bayesian optimization too

Bayesian optimization (BO) has become a popular strategy for global optimization of many expensive real-world functions. Contrary to a common belief that BO is suited to optimizing black-box functions, it actually requires domain knowledge on characteristics of those functions to deploy BO successfully. Such domain knowledge often manifests in Gaussian process priors that specify initial beliefs on functions. However, even with expert knowledge, it is not an easy task to select a prior. This is especially true for hyperparameter tuning problems on complex machine learning models, where landscapes of tuning objectives are often difficult to comprehend. We seek an alternative practice for setting these functional priors. In particular, we consider the scenario where we have data from similar functions that allow us to pre-train a tighter distribution a priori. To verify our approach in realistic model training setups, we collected a large multi-task hyperparameter tuning dataset by training tens of thousands of configurations of near-state-of-the-art models on popular image and text datasets, as well as a protein sequence dataset. Our results show that on average, our method is able to locate good hyperparameters at least 3 times more efficiently than the best competing methods.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Cycle Flux Ranking of Network Analysis in Quantum Thermal Device

Manipulating quantum thermal transport relies on uncovering the principle working cycles of quantum devices. Here, we apply the cycle flux ranking of network analysis to nonequilibrium thermal devices described by graphs of quantum state transitions. To excavate the principal mechanism out of complex transport behaviors, we decompose the quantum-transition network into cycles, calculate the cycle flux by algebraic graph theory, and pick out the dominant cycles with top-ranked fluxes, i.e., the cycle trajectories with highest probabilities. We demonstrate the cycle flux ranking in typical quantum device models, such as a thermal-drag spin-Seebeck pump, and a quantum thermal transistor as thermal switch or heat amplifier. The dominant cycle trajectories indeed elucidate the principal working mechanisms of those quantum devices. The cycle flux analysis provides an alternative perspective that naturally describes the working cycle corresponding to the main functionality of quantum thermal devices, which would further guide the device optimization with desired performance

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Exploring Adversarial Robustness of Deep Metric Learning

Deep Metric Learning (DML), a widely-used technique, involves learning a distance metric between pairs of samples. DML uses deep neural architectures to learn semantic embeddings of the input, where the distance between similar examples is small while dissimilar ones are far apart. Although the underlying neural networks produce good accuracy on naturally occurring samples, they are vulnerable to adversarially-perturbed samples that reduce performance. We take a first step towards training robust DML models and tackle the primary challenge of the metric losses being dependent on the samples in a mini-batch, unlike standard losses that only depend on the specific input-output pair. We analyze this dependence effect and contribute a robust optimization formulation. Using experiments on three commonly-used DML datasets, we demonstrate 5-76 fold increases in adversarial accuracy, and outperform an existing DML model that sought out to be robust.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Interval Universal Approximation for Neural Networks

To verify safety and robustness of neural networks, researchers have successfully applied abstract interpretation, primarily using the interval abstract domain. In this paper, we study the theoretical power and limits of the interval domain for neural-network verification. First, we introduce the interval universal approximation (IUA) theorem. IUA shows that neural networks not only can approximate any continuous function $f$ (universal approximation) as we have known for decades, but we can find a neural network, using any well-behaved activation function, whose interval bounds are an arbitrarily close approximation of the set semantics of $f$ (the result of applying $f$ to a set of inputs). We call this notion of approximation interval approximation. Our theorem generalizes the recent result of Baader et al. (2020) from ReLUs to a rich class of activation functions that we call squashable functions. Additionally, the IUA theorem implies that we can always construct provably robust neural networks under $\ell_\infty$-norm using almost any practical activation function. Second, we study the computational complexity of constructing neural networks that are amenable to precise interval analysis. This is a crucial question, as our constructive proof of IUA is exponential in the size of the approximation domain. We boil this question down to the problem of approximating the range of a neural network with squashable activation functions. We show that the range approximation problem (RA) is a $Δ_2$-intermediate problem, which is strictly harder than $\mathsf{NP}$-complete problems, assuming $\mathsf{coNP}\not\subset \mathsf{NP}$. As a result, IUA is an inherently hard problem: No matter what abstract domain or computational tools we consider to achieve interval approximation, there is no efficient construction of such a universal approximator.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Light emission from self-assembled and laser-crystallized chalcogenide metasurface

Subwavelength periodic confinement can collectively and selectively enhance local light intensity and enable control over the photo-induced phase transformations at the nanometer scale. Standard nanofabrication process can result in geometrical and compositional inhomogeneities in optical phase change materials, especially chalcogenides, as those materials exhibit poor chemical and thermal stability. Here we demonstrate the self-assembled planar chalcogenide nanostructured array with resonance enhanced light emission to create an all-dielectric optical metasurface, by taking advantage of the fluid properties associated with solution processed films. A patterned silicon membrane serves as a template for shaping the chalcogenide metasurface structure. Solution-processed arsenic sulfide metasurface structures are self-assembled in the suspended 250 nm silicon membrane templates. The periodic nanostructure dramatically manifests the local light-matter interaction such as absorption of incident photons, Raman emission, and photoluminescence. Also, the thermal distribution is modified by the boundaries and thus the photo-thermal crystallization process, leading to the formation of anisotropic nano-emitters within the field enhancement area. This hybrid structure shows wavelength selective anisotropic photoluminescence, which is a characteristic behavior of the collective response of the resonant guided modes in a periodic nanostructure. The resonance enhanced Purcell effect could manifest the quantum efficiency of localized light emission.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Review and Prospect: Deep Learning in Nuclear Magnetic Resonance Spectroscopy

Since the concept of Deep Learning (DL) was formally proposed in 2006, it had a major impact on academic research and industry. Nowadays, DL provides an unprecedented way to analyze and process data with demonstrated great results in computer vision, medical imaging, natural language processing, etc. In this Minireview, we summarize applications of DL in Nuclear Magnetic Resonance (NMR) spectroscopy and outline a perspective for DL as entirely new approaches that are likely to transform NMR spectroscopy into a much more efficient and powerful technique in chemistry and life science.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Review and Prospect: NMR Spectroscopy Denoising & Reconstruction with Low Rank Hankel Matrices and Tensors

Nuclear Magnetic Resonance (NMR) spectroscopy is an important analytical tool in chemistry, biology, and life science, but it suffers from relatively low sensitivity and long acquisition time. Thus, improving the apparent signal-to-noise ratio and accelerating data acquisition become indispensable. In this review, we summarize the recent progress on low rank Hankel matrix and tensor methods, that exploit the exponential property of free induction decay signals, to enable effective denoising and spectra reconstruction. We also outline future developments that are likely to make NMR spectroscopy a far more powerful technique.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Semantic Robustness of Models of Source Code

Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions. We study this problem for models of source code, where we want the network to be robust to source-code modifications that preserve code functionality. (1) We define a powerful adversary that can employ sequences of parametric, semantics-preserving program transformations; (2) we show how to perform adversarial training to learn models robust to such adversaries; (3) we conduct an evaluation on different languages and architectures, demonstrating significant quantitative gains in robustness.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

TOFU: Target-Oriented FUzzer

Program fuzzing---providing randomly constructed inputs to a computer program---has proved to be a powerful way to uncover bugs, find security vulnerabilities, and generate test inputs that increase code coverage. In many applications, however, one is interested in a target-oriented approach-one wants to find an input that causes the program to reach a specific target point in the program. We have created TOFU (for Target-Oriented FUzzer) to address the directed fuzzing problem. TOFU's search is biased according to a distance metric that scores each input according to how close the input's execution trace gets to the target locations. TOFU is also input-structure aware (i.e., the search makes use of a specification of a superset of the program's allowed inputs). Our experiments on xmllint show that TOFU is 28% faster than AFLGo, while reaching 45% more targets. Moreover, both distance-guided search and exploitation of knowledge of the input structure contribute significantly to TOFU's performance.

0 citations0 reviewsNo code linkedOpen access