arXiv subjects

Lei Yang

Publications and source records attributed to Lei Yang.

At least 181 records · Page 10Linked to original sources

arXiv2025

DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior

We present DPoser-X, a diffusion-based prior model for 3D whole-body human poses. Building a versatile and robust full-body human pose prior remains challenging due to the inherent complexity of articulated human poses and the scarcity of high-quality whole-body pose datasets. To address these limitations, we introduce a Diffusion model as body Pose prior (DPoser) and extend it to DPoser-X for expressive whole-body human pose modeling. Our approach unifies various pose-centric tasks as inverse problems, solving them through variational diffusion sampling. To enhance performance on downstream applications, we introduce a novel truncated timestep scheduling method specifically designed for pose data characteristics. We also propose a masked training mechanism that effectively combines whole-body and part-specific datasets, enabling our model to capture interdependencies between body parts while avoiding overfitting to specific actions. Extensive experiments demonstrate DPoser-X's robustness and versatility across multiple benchmarks for body, hand, face, and full-body pose modeling. Our model consistently outperforms state-of-the-art alternatives, establishing a new benchmark for whole-body human pose prior modeling.

cs.CV↗

arXiv2025

Stable at Any Speed: Speed-Driven Multi-Object Tracking with Learnable Kalman Filtering

Multi-object tracking (MOT) enables autonomous vehicles to continuously perceive dynamic objects, supplying essential temporal cues for prediction, behavior understanding, and safe planning. However, conventional tracking-by-detection methods typically rely on static coordinate transformations based on ego-vehicle poses, disregarding ego-vehicle speed-induced variations in observation noise and reference frame changes, which degrades tracking stability and accuracy in dynamic, high-speed scenarios. In this paper, we investigate the critical role of ego-vehicle speed in MOT and propose a Speed-Guided Learnable Kalman Filter (SG-LKF) that dynamically adapts uncertainty modeling to ego-vehicle speed, significantly improving stability and accuracy in highly dynamic scenarios. Central to SG-LKF is MotionScaleNet (MSNet), a decoupled token-mixing and channel-mixing MLP that adaptively predicts key parameters of SG-LKF. To enhance inter-frame association and trajectory continuity, we introduce a self-supervised trajectory consistency loss jointly optimized with semantic and positional constraints. Extensive experiments show that SG-LKF ranks first among all vision-based methods on KITTI 2D MOT with 79.59% HOTA, delivers strong results on KITTI 3D MOT with 82.03% HOTA, and outperforms SimpleTrack by 2.2% AMOTA on nuScenes 3D MOT.

cs.CV↗

arXiv2025

Who Owns This Sample: Cross-Client Membership Inference Attack in Federated Graph Neural Networks

Graph-structured data is prevalent in many real-world applications, including social networks, financial systems, and molecular biology. Graph Neural Networks (GNNs) have become the de facto standard for learning from such data due to their strong representation capabilities. As GNNs are increasingly deployed in federated learning (FL) settings to preserve data locality and privacy, new privacy threats arise from the interaction between graph structures and decentralized training. In this paper, we present the first systematic study of cross-client membership inference attacks (CC-MIA) against node classification tasks of federated GNNs (FedGNNs), where a malicious client aims to infer which client owns the given data. Unlike prior centralized-focused work that focuses on whether a sample was included in training, our attack targets sample-to-client attribution, a finer-grained privacy risk unique to federated settings. We design a general attack framework that exploits FedGNNs' aggregation behaviors, gradient updates, and embedding proximity to link samples to their source clients across training rounds. We evaluate our attack across multiple graph datasets under realistic FL setups. Results show that our method achieves high performance on both membership inference and ownership identification. Our findings highlight a new privacy threat in federated graph learning-client identity leakage through structural and model-level cues, motivating the need for attribution-robust GNN design.

cs.LG↗

arXiv2025

Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding

Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hardware-aware model-system co-design optimized for minimizing decoding costs. Step-3 innovates in two key dimensions: (1) A novel Multi-Matrix Factorization Attention (MFA) mechanism that significantly reduces both KV cache size and computation while maintaining high attention expressiveness, and (2) Attention-FFN Disaggregation (AFD), a distributed inference system that decouples attention and Feed-Forward Network (FFN) layers into specialized subsystems. This co-design achieves unprecedented cost efficiency: Step-3 significantly reduces theoretical decoding costs compared with models like DeepSeek-V3 and Qwen3 MoE 235B, with the gains widening at longer context. Step-3 achieves low cost while activating 38B parameters per token (more than DeepSeek-V3 and Qwen3 MoE 235B), demonstrating that hardware-aligned attention arithmetic intensity, MoE sparsity, and AFD are critical to cost-effectiveness. We perform a head-to-head comparison with DeepSeek-V3 in its favorable scenarios. Our implementation on Hopper GPUs achieves a decoding throughput of up to 4,039 tokens per second per GPU under 50ms TPOT SLA (4K context, FP8, no MTP). It is higher than DeepSeek-V3's 2,324 in the same setup and sets a new Pareto frontier for LLM decoding.

cs.LG↗

arXiv2025

Computational Performance Bounds Prediction in Quantum Computing with Unstable Noise

Quantum computing has significantly advanced in recent years, boasting devices with hundreds of quantum bits (qubits), hinting at its potential quantum advantage over classical computing. Yet, noise in quantum devices poses significant barriers to realizing this supremacy. Understanding noise's impact is crucial for reproducibility and application reuse; moreover, the next-generation quantum-centric supercomputing essentially requires efficient and accurate noise characterization to support system management (e.g., job scheduling), where ensuring correct functional performance (i.e., fidelity) of jobs on available quantum devices can even be higher-priority than traditional objectives. However, noise fluctuates over time, even on the same quantum device, which makes predicting the computational bounds for on-the-fly noise is vital. Noisy quantum simulation can offer insights but faces efficiency and scalability issues. In this work, we propose a data-driven workflow, namely QuBound, to predict computational performance bounds. It decomposes historical performance traces to isolate noise sources and devises a novel encoder to embed circuit and noise information processed by a Long Short-Term Memory (LSTM) network. For evaluation, we compare QuBound with a state-of-the-art learning-based predictor, which only generates a single performance value instead of a bound. Experimental results show that the result of the existing approach falls outside of performance bounds, while all predictions from our QuBound with the assistance of performance decomposition better fit the bounds. Moreover, QuBound can efficiently produce practical bounds for various circuits with over 106 speedup over simulation; in addition, the range from QuBound is over 10x narrower than the state-of-the-art analytical approach.

quant-ph↗

arXiv2025

Effective equidistribution in rank 2 homogeneous spaces and values of quadratic forms

We establish effective equidistribution theorems, with a polynomial error rate, for orbits of unipotent subgroups in quotients of quasi-split, almost simple Linear algebraic groups of absolute rank 2. As an application, inspired by the results of Eskin, Margulis and Mozes, we establish quantitative results regarding the distribution of values of an indefinite ternary quadratic form at integer points, giving in particular an effective and quantitative proof of the Oppenheim Conjecture.

math.DS↗

arXiv2025

TokensGen: Harnessing Condensed Tokens for Long Video Generation

Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-term inconsistency. In this paper, we propose TokensGen, a novel two-stage framework that leverages condensed tokens to address these issues. Our method decomposes long video generation into three core tasks: (1) inner-clip semantic control, (2) long-term consistency control, and (3) inter-clip smooth transition. First, we train To2V (Token-to-Video), a short video diffusion model guided by text and video tokens, with a Video Tokenizer that condenses short clips into semantically rich tokens. Second, we introduce T2To (Text-to-Token), a video token diffusion transformer that generates all tokens at once, ensuring global consistency across clips. Finally, during inference, an adaptive FIFO-Diffusion strategy seamlessly connects adjacent clips, reducing boundary artifacts and enhancing smooth transitions. Experimental results demonstrate that our approach significantly enhances long-term temporal and content coherence without incurring prohibitive computational overhead. By leveraging condensed tokens and pre-trained short video models, our method provides a scalable, modular solution for long video generation, opening new possibilities for storytelling, cinematic production, and immersive simulations. Please see our project page at https://vicky0522.github.io/tokensgen-webpage/ .

cs.CV↗

arXiv2025

Fully Unified Motion Planning for End-to-End Autonomous Driving

Current end-to-end autonomous driving methods typically learn only from expert planning data collected from a single ego vehicle, severely limiting the diversity of learnable driving policies and scenarios. However, a critical yet overlooked fact is that in any driving scenario, multiple high-quality trajectories from other vehicles coexist with a specific ego vehicle's trajectory. Existing methods fail to fully exploit this valuable resource, missing important opportunities to improve the models' performance (including long-tail scenarios) through learning from other experts. Intuitively, Jointly learning from both ego and other vehicles' expert data is beneficial for planning tasks. However, this joint learning faces two critical challenges. (1) Different scene observation perspectives across vehicles hinder inter-vehicle alignment of scene feature representations; (2) The absence of partial modality in other vehicles' data (e.g., vehicle states) compared to ego-vehicle data introduces learning bias. To address these challenges, we propose FUMP (Fully Unified Motion Planning), a novel two-stage trajectory generation framework. Building upon probabilistic decomposition, we model the planning task as a specialized subtask of motion prediction. Specifically, our approach decouples trajectory planning into two stages. In Stage 1, a shared decoder jointly generates initial trajectories for both tasks. In Stage 2, the model performs planning-specific refinement conditioned on an ego-vehicle's state. The transition between the two stages is bridged by a state predictor trained exclusively on ego-vehicle data. To address the cross-vehicle discrepancy in observational perspectives, we propose an Equivariant Context-Sharing Adapter (ECSA) before Stage 1 for improving cross-vehicle generalization of scene representations.

cs.CV↗

arXiv2025

Half Spatially Coupled Turbo-Like Codes

This paper presents a new class of spatially coupled turbo-like codes (SC-TCs), namely half spatially coupled braided convolutional codes (HSC-BCCs) and half spatially coupled parallel concatenated codes (HSC-PCCs). Different from the conventional SC-TCs, the proposed codes have simpler and deterministic coupling structures. Most notably, the coupling of HSC-BCCs is performed by re-encoding the whole coupling sequence in the component encoder of one time instant, rather than spreading the coupling bits to component encoders of multiple time instants. This simplification not only addresses the window decoding threshold loss issue in existing BCCs, but also allows the proposed codes to attain very close-to-capacity performance with a coupling memory as small as 2. Both theoretical and numerical results are provided to demonstrate the performance advantages of the proposed codes over existing spatially coupled codes.

cs.IT↗

arXiv2025

Nuclear Physics at BRIF

The Beijing Radioactive Ion-beam Facility (BRIF), which is based on Isotope Separation On-Line (ISOL) technique, consists of a 100 MeV proton cyclotron as the driving accelerator, a two-stage ISOL system for ion separation, a 13-MV tandem accelerator for post-acceleration, a superconducting linac for further boosting beam energies. It is capable of providing ISOL beams in the energy range from 60 to 300 keV, and post-accelerated beams in the energy range from 3 to 10 MeV/u for nuclei with mass numbers of A < 80 by Isotope Separation On-Line (ISOL) technique. For nuclei with A up to 170, energies are still able to reach 3 MeV/u. This facility offers opportunities to address key questions of current interest in nuclear astrophysics, nuclear structure and reactions of unstable nuclei. In this review we present a comprehensive introduction to the BRIF and the typical experimental instruments installed on it, and then summarize current experimental results on unstable Na and Rb isotopes and future plan for further development of the BRIF to improve its performance.

physics.acc-ph↗

arXiv2025

From 2D to 3D Cognition: A Brief Survey of General World Models

World models have garnered increasing attention in the development of artificial general intelligence (AGI), serving as computational frameworks for learning representations of the external world and forecasting future states. While early efforts focused on 2D visual perception and simulation, recent 3D-aware generative world models have demonstrated the ability to synthesize geometrically consistent, interactive 3D environments, marking a shift toward 3D spatial cognition. Despite rapid progress, the field lacks systematic analysis to categorize emerging techniques and clarify their roles in advancing 3D cognitive world models. This survey addresses this need by introducing a conceptual framework, providing a structured and forward-looking review of world models transitioning from 2D perception to 3D cognition. Within this framework, we highlight two key technological drivers, particularly advances in 3D representations and the incorporation of world knowledge, as fundamental pillars. Building on these, we dissect three core cognitive capabilities that underpin 3D world modeling: 3D physical scene generation, 3D spatial reasoning, and 3D spatial interaction. We further examine the deployment of these capabilities in real-world applications, including embodied AI, autonomous driving, digital twin, and gaming/VR. Finally, we identify challenges across data, modeling, and deployment, and outline future directions for advancing more robust and generalizable 3D world models.

cs.CV↗

arXiv2025

Collaborative Perception Datasets for Autonomous Driving: A Review

Collaborative perception has attracted growing interest from academia and industry due to its potential to enhance perception accuracy, safety, and robustness in autonomous driving through multi-agent information fusion. With the advancement of Vehicle-to-Everything (V2X) communication, numerous collaborative perception datasets have emerged, varying in cooperation paradigms, sensor configurations, data sources, and application scenarios. However, the absence of systematic summarization and comparative analysis hinders effective resource utilization and standardization of model evaluation. As the first comprehensive review focused on collaborative perception datasets, this work reviews and compares existing resources from a multi-dimensional perspective. We categorize datasets based on cooperation paradigms, examine their data sources and scenarios, and analyze sensor modalities and supported tasks. A detailed comparative analysis is conducted across multiple dimensions. We also outline key challenges and future directions, including dataset scalability, diversity, domain adaptation, standardization, privacy, and the integration of large language models. To support ongoing research, we provide a continuously updated online repository of collaborative perception datasets and related literature: https://github.com/frankwnb/Collaborative-Perception-Datasets-for-Autonomous-Driving.

cs.CV↗

arXiv2025

Latent Factorization of Tensors with Threshold Distance Weighted Loss for Traffic Data Estimation

Intelligent transportation systems (ITS) rely heavily on complete and high-quality spatiotemporal traffic data to achieve optimal performance. Nevertheless, in real-word traffic data collection processes, issues such as communication failures and sensor malfunctions often lead to incomplete or corrupted datasets, thereby posing significant challenges to the advancement of ITS. Among various methods for imputing missing spatiotemporal traffic data, the latent factorization of tensors (LFT) model has emerged as a widely adopted and effective solution. However, conventional LFT models typically employ the standard L2-norm in their learning objective, which makes them vulnerable to the influence of outliers. To overcome this limitation, this paper proposes a threshold distance weighted (TDW) loss-incorporated Latent Factorization of Tensors (TDWLFT) model. The proposed loss function effectively reduces the model's sensitivity to outliers by assigning differentiated weights to individual samples. Extensive experiments conducted on two traffic speed datasets sourced from diverse urban environments confirm that the proposed TDWLFT model consistently outperforms state-of-the-art approaches in terms of both in both prediction accuracy and computational efficiency.

cs.LG↗

arXiv2025

Spherical Phase Metalenses: Intrinsic Suppression of Spherical Aberration via Equiphase Surface Modulation

Recent progress in large-scale metasurfaces requires phase profiles beyond traditional hyperbolic designs. We show hyperbolic phase distributions cause spherical aberration from mismatched light propagation geometry and unrealistic phase assumptions. By analyzing metalens fundamentals via isophase surfaces, we develop a spherical phase profile based on spherical wavefront theory. This method prevents spherical aberration, essential for wide-aperture metalenses. Simulations prove superior focusing: spherical phase reduces FWHM by 7.3% and increases peak intensity by 20.4% versus hyperbolic designs at 31.46 micron radius. Spherical phase maintains consistent focusing across radii, while hyperbolic phase shows strong correlation (R squared = 0.95) with aberration. We also propose a normal vector tracing metric to measure design aberrations. This work establishes a scalable framework for diffraction-limited metalenses.

physics.optics↗

arXiv2025

S2R-Bench: A Sim-to-Real Evaluation Benchmark for Autonomous Driving

Safety is a long-standing and the final pursuit in the development of autonomous driving systems, with a significant portion of safety challenge arising from perception. How to effectively evaluate the safety as well as the reliability of perception algorithms is becoming an emerging issue. Despite its critical importance, existing perception methods exhibit a limitation in their robustness, primarily due to the use of benchmarks are entierly simulated, which fail to align predicted results with actual outcomes, particularly under extreme weather conditions and sensor anomalies that are prevalent in real-world scenarios. To fill this gap, in this study, we propose a Sim-to-Real Evaluation Benchmark for Autonomous Driving (S2R-Bench). We collect diverse sensor anomaly data under various road conditions to evaluate the robustness of autonomous driving perception methods in a comprehensive and realistic manner. This is the first corruption robustness benchmark based on real-world scenarios, encompassing various road conditions, weather conditions, lighting intensities, and time periods. By comparing real-world data with simulated data, we demonstrate the reliability and practical significance of the collected data for real-world applications. We hope that this dataset will advance future research and contribute to the development of more robust perception models for autonomous driving. This dataset is released on https://github.com/adept-thu/S2R-Bench.

cs.RO↗

arXiv2025

ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization

Human mesh recovery (HMR) from a single image is inherently ill-posed due to depth ambiguity and occlusions. Probabilistic methods have tried to solve this by generating numerous plausible 3D human mesh predictions, but they often exhibit misalignment with 2D image observations and weak robustness to in-the-wild images. To address these issues, we propose ADHMR, a framework that Aligns a Diffusion-based HMR model in a preference optimization manner. First, we train a human mesh prediction assessment model, HMR-Scorer, capable of evaluating predictions even for in-the-wild images without 3D annotations. We then use HMR-Scorer to create a preference dataset, where each input image has a pair of winner and loser mesh predictions. This dataset is used to finetune the base model using direct preference optimization. Moreover, HMR-Scorer also helps improve existing HMR models by data cleaning, even with fewer training samples. Extensive experiments show that ADHMR outperforms current state-of-the-art methods. Code is available at: https://github.com/shenwenhao01/ADHMR.

cs.CV↗

arXiv2025

The Feasibility Study of the GeV-Energy Muon Source Based on HIAF

Generating a mono-energetic, high-energy muon beam using accelerator facilities can be very attractive for many purposes, for example, improving muon tomography currently limited by the low flux and wide energy spread of cosmic ray muons, and searching for muon related new physics beyond the Standard Model. One potential accelerator facility is the High Intensity Heavy-Ion Accelerator Facility (HIAF), which is currently under construction in Huizhou City, China. Considering the projectile energy and beamline length, a high-intensity and GeV-energy muon flux could be produced and delivered by the High Energy Fragment Separator beamline of the HIAF facility. In this paper, the flux intensity and purity of muon beam based on HIAF are discussed in detail. For the $μ^+$ beam, the highest muon yield reaches $8.2 \times 10^6 ~ μ$/s with the purity of approximately $2\%$ at a momentum of 3.5 GeV/c; meanwhile, for the $μ^-$ beam, the maximum muon yield is 4.2 $\times 10^6 ~ μ$/s with the purity of around $20\%$ at a momentum of 1.5 GeV/c. The results also indicate that, for muon beams with an energy of several GeV, by applying a suitable purification strategy, we can get a muon beam with a purity of 100\% and an intensity of the order of $10^5 ~ μ$/s.

physics.acc-ph↗

arXiv2025

Internal State Estimation in Groups via Active Information Gathering

Accurately estimating human internal states, such as personality traits or behavioral patterns, is critical for enhancing the effectiveness of human-robot interaction, particularly in group settings. These insights are key in applications ranging from social navigation to autism diagnosis. However, prior methods are limited by scalability and passive observation, making real-time estimation in complex, multi-human settings difficult. In this work, we propose a practical method for active human personality estimation in groups, with a focus on applications related to Autism Spectrum Disorder (ASD). Our method combines a personality-conditioned behavior model, based on the Eysenck 3-Factor theory, with an active robot information gathering policy that triggers human behaviors through a receding-horizon planner. The robot's belief about human personality is then updated via Bayesian inference. We demonstrate the effectiveness of our approach through simulations, user studies with typical adults, and preliminary experiments involving participants with ASD. Our results show that our method can scale to tens of humans and reduce personality prediction error by 29.2% and uncertainty by 79.9% in simulation. User studies with typical adults confirm the method's ability to generalize across complex personality distributions. Additionally, we explore its application in autism-related scenarios, demonstrating that the method can identify the difference between neurotypical and autistic behavior, highlighting its potential for diagnosing ASD. The results suggest that our framework could serve as a foundation for future ASD-specific interventions.

cs.RO↗