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

Shuai Yang

Shuai Yang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionMachine LearningArtificial Intelligencecond-mat.mes-hallcond-mat.mtrl-scihep-phDistributed, Parallel, and Cluster Computinghep-exMultimediaNetworking and Internet Architecturenucl-exnucl-thquant-ph

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
20works
0followers
13topics
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

20 published item(s)

preprint2026arXiv

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

We present LongLive-2.0, an NVFP4-based parallel infrastructure throughout the full training and inference workflow of long video generation, addressing speed and memory bottlenecks. For training, we introduce sequence-parallel autoregressive (AR) training, instantiated as Balanced SP, which co-designs the efficient teacher-forcing layout with SP execution by pairing clean-history and noisy-target temporal chunks on each rank, enabling a natural teacher-forcing mask with SP-aware chunked VAE encoding. Combined with NVFP4 precision, it reduces GPU memory cost and accelerates GEMM computation during training, the proportion of which increases as video length grows. Moreover, we show that a high-quality infrastructure and dataset enable a remarkably clean training pipeline. Unlike existing Self-Forcing series methods that rely on ODE initialization and subsequent distribution matching distillation (DMD), LongLive-2.0 directly tunes a diffusion model into a long, multi-shot, interactive auto-regressive (AR) diffusion model. It can be further converted to real-time generation (4 to 2 denoising steps) with standalone LoRA weights. For inference on Blackwell GPUs, we enable W4A4 NVFP4 inference, quantize KV cache into NVFP4 for memory savings, and boost end-to-end throughput with asynchronous streaming VAE decoding. On non-Blackwell GPU architectures, we deploy SP inference to match the speed on Blackwell GPUs, while the quantized KV cache can lower inter-GPU communication of SP. Experiments show up to 2.15x speedup in training, and 1.84x in inference. LongLive-2.0-5B achieves 45.7 FPS inference while attaining strong performance on benchmarks. To our knowledge, LongLive-2.0 is the first NVFP4 training and inference system for long video generation.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

WorldMem: Long-term Consistent World Simulation with Memory

World simulation has gained increasing popularity due to its ability to model virtual environments and predict the consequences of actions. However, the limited temporal context window often leads to failures in maintaining long-term consistency, particularly in preserving 3D spatial consistency. In this work, we present WorldMem, a framework that enhances scene generation with a memory bank consisting of memory units that store memory frames and states (e.g., poses and timestamps). By employing a memory attention mechanism that effectively extracts relevant information from these memory frames based on their states, our method is capable of accurately reconstructing previously observed scenes, even under significant viewpoint or temporal gaps. Furthermore, by incorporating timestamps into the states, our framework not only models a static world but also captures its dynamic evolution over time, enabling both perception and interaction within the simulated world. Extensive experiments in both virtual and real scenarios validate the effectiveness of our approach.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification

The Graph Neural Network (GNN) has been widely used for graph data representation. However, the existing researches only consider the ideal balanced dataset, and the imbalanced dataset is rarely considered. Traditional methods such as resampling, reweighting, and synthetic samples that deal with imbalanced datasets are no longer applicable in GNN. This paper proposes an ensemble model called Boosting-GNN, which uses GNNs as the base classifiers during boosting. In Boosting-GNN, higher weights are set for the training samples that are not correctly classified by the previous classifier, thus achieving higher classification accuracy and better reliability. Besides, transfer learning is used to reduce computational cost and increase fitting ability. Experimental results indicate that the proposed Boosting-GNN model achieves better performance than GCN, GraphSAGE, GAT, SGC, N-GCN, and most advanced reweighting and resampling methods on synthetic imbalanced datasets, with an average performance improvement of 4.5%

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Efficient quantum circuit synthesis for SAT-oracle with limited ancillary qubit

How to implement quantum oracle with limited resources raises concerns these days. We design two ancilla-adjustable and efficient algorithms to synthesize SAT-oracle, the key component in solving SAT problems. The previous work takes 2m-1 ancillary qubits and O(m) elementary gates to synthesize an m clauses oracle. The first algorithm reduces the number of ancillary qubits to 2\sqrt{m}, with at most an eightfold increase in circuit size. The number of ancillary qubits can be further reduced to 3 with a quadratic increase in circuit size. The second algorithm aims to reduce the circuit depth. By leveraging of the second algorithm, the circuit depth can be reduced to O(log m) with m ancillary qubits.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer

Recent studies on StyleGAN show high performance on artistic portrait generation by transfer learning with limited data. In this paper, we explore more challenging exemplar-based high-resolution portrait style transfer by introducing a novel DualStyleGAN with flexible control of dual styles of the original face domain and the extended artistic portrait domain. Different from StyleGAN, DualStyleGAN provides a natural way of style transfer by characterizing the content and style of a portrait with an intrinsic style path and a new extrinsic style path, respectively. The delicately designed extrinsic style path enables our model to modulate both the color and complex structural styles hierarchically to precisely pastiche the style example. Furthermore, a novel progressive fine-tuning scheme is introduced to smoothly transform the generative space of the model to the target domain, even with the above modifications on the network architecture. Experiments demonstrate the superiority of DualStyleGAN over state-of-the-art methods in high-quality portrait style transfer and flexible style control.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Semantic Communication-Empowered Physical-layer Network Coding

In a two-way relay channel (TWRC), physical-layer network coding (PNC) doubles the system throughput by turning superimposed signals transmitted simultaneously by different end nodes into useful network-coded information (known as PNC decoding). Prior works indicated that the PNC decoding performance is affected by the relative phase offset between the received signals from different nodes. In particular, some "bad" relative phase offsets could lead to huge performance degradation. Previous solutions to mitigate the relative phase offset effect were limited to the conventional bit-oriented communication paradigm, aiming at delivering a given information stream as quickly and reliably as possible. In contrast, this paper puts forth the first semantic communication-empowered PNC-enabled TWRC to address the relative phase offset issue, referred to as SC-PNC. Despite the bad relative phase offsets, SC-PNC directly extracts the semantic meaning of transmitted messages rather than ensuring accurate bit stream transmission. We jointly design deep neural network (DNN)-based transceivers at the end nodes and propose a semantic PNC decoder at the relay. Taking image delivery as an example, experimental results show that the SC-PNC TWRC achieves high and stable reconstruction quality for images under different channel conditions and relative phase offsets, compared with the conventional bit-oriented counterparts.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Text2Human: Text-Driven Controllable Human Image Generation

Generating high-quality and diverse human images is an important yet challenging task in vision and graphics. However, existing generative models often fall short under the high diversity of clothing shapes and textures. Furthermore, the generation process is even desired to be intuitively controllable for layman users. In this work, we present a text-driven controllable framework, Text2Human, for a high-quality and diverse human generation. We synthesize full-body human images starting from a given human pose with two dedicated steps. 1) With some texts describing the shapes of clothes, the given human pose is first translated to a human parsing map. 2) The final human image is then generated by providing the system with more attributes about the textures of clothes. Specifically, to model the diversity of clothing textures, we build a hierarchical texture-aware codebook that stores multi-scale neural representations for each type of texture. The codebook at the coarse level includes the structural representations of textures, while the codebook at the fine level focuses on the details of textures. To make use of the learned hierarchical codebook to synthesize desired images, a diffusion-based transformer sampler with mixture of experts is firstly employed to sample indices from the coarsest level of the codebook, which then is used to predict the indices of the codebook at finer levels. The predicted indices at different levels are translated to human images by the decoder learned accompanied with hierarchical codebooks. The use of mixture-of-experts allows for the generated image conditioned on the fine-grained text input. The prediction for finer level indices refines the quality of clothing textures. Extensive quantitative and qualitative evaluations demonstrate that our proposed framework can generate more diverse and realistic human images compared to state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Unsupervised Image-to-Image Translation with Generative Prior

Unsupervised image-to-image translation aims to learn the translation between two visual domains without paired data. Despite the recent progress in image translation models, it remains challenging to build mappings between complex domains with drastic visual discrepancies. In this work, we present a novel framework, Generative Prior-guided UNsupervised Image-to-image Translation (GP-UNIT), to improve the overall quality and applicability of the translation algorithm. Our key insight is to leverage the generative prior from pre-trained class-conditional GANs (e.g., BigGAN) to learn rich content correspondences across various domains. We propose a novel coarse-to-fine scheme: we first distill the generative prior to capture a robust coarse-level content representation that can link objects at an abstract semantic level, based on which fine-level content features are adaptively learned for more accurate multi-level content correspondences. Extensive experiments demonstrate the superiority of our versatile framework over state-of-the-art methods in robust, high-quality and diversified translations, even for challenging and distant domains.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Observation of Aharonov-Bohm effect in PbTe nanowire networks

We report phase coherent electron transport in PbTe nanowire networks with a loop geometry. Magneto-conductance shows Aharonov-Bohm (AB) oscillations with periods of $h/e$ and $h/2e$ in flux. The amplitude of $h/2e$ oscillations is enhanced near zero magnetic field, possibly due to interference between time-reversal paths. Temperature dependence of the AB amplitudes suggests a phase coherence length $\sim$ 8 - 12 $μ$m at 50 mK. This length scale is larger than the typical geometry of PbTe-based hybrid semiconductor-superconductor nanowire devices.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Selective area epitaxy of PbTe-Pb hybrid nanowires on a lattice-matched substrate

Topological quantum computing is based on braiding of Majorana zero modes encoding topological qubits. A promising candidate platform for Majorana zero modes is semiconductor-superconductor hybrid nanowires. The realization of topological qubits and braiding operations requires scalable and disorder-free nanowire networks. Selective area growth of in-plane InAs and InSb nanowires, together with shadow-wall growth of superconductor structures, have demonstrated this scalability by achieving various network structures. However, the noticeable lattice mismatch at the nanowire-substrate interface, acting as a disorder source, imposes a serious obstacle along with this roadmap. Here, combining selective area and shadow-wall growth, we demonstrate the fabrication of PbTe-Pb hybrid nanowires - another potentially promising Majorana system - on a nearly perfectly lattice-matched substrate CdTe, all done in one molecular beam epitaxy chamber. Transmission electron microscopy shows the single-crystal nature of the PbTe nanowire and its atomically sharp and clean interfaces to the CdTe substrate and the Pb overlayer, without noticeable inter-diffusion or strain. The nearly ideal interface condition, together with the strong screening of charge impurities due to the large dielectric constant of PbTe, hold promise towards a clean nanowire system to study Majorana zero modes and topological quantum computing.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Towards Efficient Local Causal Structure Learning

Local causal structure learning aims to discover and distinguish direct causes (parents) and direct effects (children) of a variable of interest from data. While emerging successes have been made, existing methods need to search a large space to distinguish direct causes from direct effects of a target variable T. To tackle this issue, we propose a novel Efficient Local Causal Structure learning algorithm, named ELCS. Specifically, we first propose the concept of N-structures, then design an efficient Markov Blanket (MB) discovery subroutine to integrate MB learning with N-structures to learn the MB of T and simultaneously distinguish direct causes from direct effects of T. With the proposed MB subroutine, ELCS starts from the target variable, sequentially finds MBs of variables connected to the target variable and simultaneously constructs local causal structures over MBs until the direct causes and direct effects of the target variable have been distinguished. Using eight Bayesian networks the extensive experiments have validated that ELCS achieves better accuracy and efficiency than the state-of-the-art algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Towards Efficient Local Causal Structure Learning

Local causal structure learning aims to discover and distinguish direct causes (parents) and direct effects (children) of a variable of interest from data. While emerging successes have been made, existing methods need to search a large space to distinguish direct causes from direct effects of a target variable \emph{T}. To tackle this issue, we propose a novel Efficient Local Causal Structure learning algorithm, named ELCS. Specifically, we first propose the concept of N-structures, then design an efficient Markov Blanket (MB) discovery subroutine to integrate MB learning with N-structures to learn the MB of \emph{T} and simultaneously distinguish direct causes from direct effects of \emph{T}. With the proposed MB subroutine, ELCS starts from the target variable, sequentially finds MBs of variables connected to the target variable and simultaneously constructs local causal structures over MBs until the direct causes and direct effects of the target variable have been distinguished. Using eight Bayesian networks the extensive experiments have validated that ELCS achieves better accuracy and efficiency than the state-of-the-art algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Acoplanarity of QED pairs accompanied by nuclear dissociation in ultra-peripheral heavy ion collisions

This paper investigates the transverse momentum broadening effect for electromagnetic production of dileptons in ultra-peripheral heavy ion collisions accompanied by nuclear dissociation. The electromagnetic dissociation probability of nuclei for different neutron multiplicities is estimated, which could serve as a centrality definition (i.e. impact parameter estimate) in ultra-peripheral collisions. In the framework of lowest-order QED, the acoplanarity of dilepton pairs is calculated for different neutron emission scenarios in ultra-peripheral collisions, indicating significant impact-parameter dependence. The verification of impact-parameter dependence is crucially important to understand the broadening effect observed in hadronic heavy-ion collisions.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches

Sketch-based image editing aims to synthesize and modify photos based on the structural information provided by the human-drawn sketches. Since sketches are difficult to collect, previous methods mainly use edge maps instead of sketches to train models (referred to as edge-based models). However, sketches display great structural discrepancy with edge maps, thus failing edge-based models. Moreover, sketches often demonstrate huge variety among different users, demanding even higher generalizability and robustness for the editing model to work. In this paper, we propose Deep Plastic Surgery, a novel, robust and controllable image editing framework that allows users to interactively edit images using hand-drawn sketch inputs. We present a sketch refinement strategy, as inspired by the coarse-to-fine drawing process of the artists, which we show can help our model well adapt to casual and varied sketches without the need for real sketch training data. Our model further provides a refinement level control parameter that enables users to flexibly define how "reliable" the input sketch should be considered for the final output, balancing between sketch faithfulness and output verisimilitude (as the two goals might contradict if the input sketch is drawn poorly). To achieve the multi-level refinement, we introduce a style-based module for level conditioning, which allows adaptive feature representations for different levels in a singe network. Extensive experimental results demonstrate the superiority of our approach in improving the visual quality and user controllablity of image editing over the state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

From Design Draft to Real Attire: Unaligned Fashion Image Translation

Fashion manipulation has attracted growing interest due to its great application value, which inspires many researches towards fashion images. However, little attention has been paid to fashion design draft. In this paper, we study a new unaligned translation problem between design drafts and real fashion items, whose main challenge lies in the huge misalignment between the two modalities. We first collect paired design drafts and real fashion item images without pixel-wise alignment. To solve the misalignment problem, our main idea is to train a sampling network to adaptively adjust the input to an intermediate state with structure alignment to the output. Moreover, built upon the sampling network, we present design draft to real fashion item translation network (D2RNet), where two separate translation streams that focus on texture and shape, respectively, are combined tactfully to get both benefits. D2RNet is able to generate realistic garments with both texture and shape consistency to their design drafts. We show that this idea can be effectively applied to the reverse translation problem and present R2DNet accordingly. Extensive experiments on unaligned fashion design translation demonstrate the superiority of our method over state-of-the-art methods. Our project website is available at: https://victoriahy.github.io/MM2020/ .

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

In Situ Epitaxy of Pure Phase Ultra-Thin InAs-Al Nanowires for Quantum Devices

Hybrid semiconductor-superconductor InAs-Al nanowires with uniform and defect-free crystal interfaces are one of the most promising candidates used in the quest for Majorana zero modes (MZMs). However, InAs nanowires often exhibit a high density of randomly distributed twin defects and stacking faults, which result in an uncontrolled and non-uniform InAs-Al interface. Furthermore, this type of disorder can create potential inhomogeneity in the wire, destroy the topological gap, and form trivial sub-gap states mimicking MZM in transport experiments. Further study shows that reducing the InAs nanowire diameter from growth can significantly suppress the formation of these defects and stacking faults. Here, we demonstrate the in situ growth of ultra-thin InAs nanowires with epitaxial Al film by molecular-beam epitaxy. Our InAs diameter (~ 30 nm) is only one-third of the diameters (~ 100 nm) commonly used in literatures. The ultra-thin InAs nanowires are pure phase crystals for various different growth directions, suggesting a low level of disorder. Transmission electron microscopy confirms an atomically sharp and uniform interface between the Al shell and the InAs wire. Quantum transport study on these devices resolves a hard induced superconducting gap and $2e^-$ periodic Coulomb blockade at zero magnetic field, a necessary step for future MZM experiments. A large zero bias conductance peak with a peak height reaching 80% of $2e^2/h$ is observed.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

New opportunities at the photon energy frontier

Ultra-peripheral collisions (UPCs) involving heavy ions and protons are the energy frontier for photon-mediated interactions. UPC photons can be used for many purposes, including probing low-$x$ gluons via photoproduction of dijets and vector mesons, probes of beyond-standard-model processes, such as those enabled by light-by-light scattering, and studies of two-photon production of the Higgs.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

TE141K: Artistic Text Benchmark for Text Effect Transfer

Text effects are combinations of visual elements such as outlines, colors and textures of text, which can dramatically improve its artistry. Although text effects are extensively utilized in the design industry, they are usually created by human experts due to their extreme complexity; this is laborious and not practical for normal users. In recent years, some efforts have been made toward automatic text effect transfer; however, the lack of data limits the capabilities of transfer models. To address this problem, we introduce a new text effects dataset, TE141K, with 141,081 text effect/glyph pairs in total. Our dataset consists of 152 professionally designed text effects rendered on glyphs, including English letters, Chinese characters, and Arabic numerals. To the best of our knowledge, this is the largest dataset for text effect transfer to date. Based on this dataset, we propose a baseline approach called text effect transfer GAN (TET-GAN), which supports the transfer of all 152 styles in one model and can efficiently extend to new styles. Finally, we conduct a comprehensive comparison in which 14 style transfer models are benchmarked. Experimental results demonstrate the superiority of TET-GAN both qualitatively and quantitatively and indicate that our dataset is effective and challenging.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Towards Coding for Human and Machine Vision: A Scalable Image Coding Approach

The past decades have witnessed the rapid development of image and video coding techniques in the era of big data. However, the signal fidelity-driven coding pipeline design limits the capability of the existing image/video coding frameworks to fulfill the needs of both machine and human vision. In this paper, we come up with a novel image coding framework by leveraging both the compressive and the generative models, to support machine vision and human perception tasks jointly. Given an input image, the feature analysis is first applied, and then the generative model is employed to perform image reconstruction with features and additional reference pixels, in which compact edge maps are extracted in this work to connect both kinds of vision in a scalable way. The compact edge map serves as the basic layer for machine vision tasks, and the reference pixels act as a sort of enhanced layer to guarantee signal fidelity for human vision. By introducing advanced generative models, we train a flexible network to reconstruct images from compact feature representations and the reference pixels. Experimental results demonstrate the superiority of our framework in both human visual quality and facial landmark detection, which provide useful evidence on the emerging standardization efforts on MPEG VCM (Video Coding for Machine).

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Restricted Connection Orthogonal Matching Pursuit For Sparse Subspace Clustering

Sparse Subspace Clustering (SSC) is one of the most popular methods for clustering data points into their underlying subspaces. However, SSC may suffer from heavy computational burden. Orthogonal Matching Pursuit applied on SSC accelerates the computation but the trade-off is the loss of clustering accuracy. In this paper, we propose a noise-robust algorithm, Restricted Connection Orthogonal Matching Pursuit for Sparse Subspace Clustering (RCOMP-SSC), to improve the clustering accuracy and maintain the low computational time by restricting the number of connections of each data point during the iteration of OMP. Also, we develop a framework of control matrix to realize RCOMP-SCC. And the framework is scalable for other data point selection strategies. Our analysis and experiments on synthetic data and two real-world databases (EYaleB & Usps) demonstrate the superiority of our algorithm compared with other clustering methods in terms of accuracy and computational time.

0 citations0 reviewsNo code linkedOpen access