arXiv subjects

Hangyu Li

Publications and source records attributed to Hangyu Li.

At least 19 recordsLinked to original sources

arXiv2026

Morphology and Dynamics of Self-interstitial Clusters in Irradiated Nickel

Self-interstitial atom (SIA) clustering is a key early step in radiation damage evolution in face-centered cubic (FCC) metals, governing defect transport, recombination, and the long-term microstructural response of irradiated alloys. We combine molecular dynamics (MD) simulations and high-speed (>1000 frames/s) in situ transmission electron microscopy (TEM) to investigate the structure, energetics, and migration dynamics of SIA clusters in FCC Ni. MD simulations show that interstitials initially form disordered dumbbell clusters that evolve into either sessile Frank loops or glissile perfect (prismatic) loops; the latter progressively reorganize into compact ordered configurations with increasing mobility. Direct construction of both loop types over a wide size range, validated against MD-relaxed structures, shows that perfect loops are thermodynamically favored over Frank loops for cluster sizes N greater than or equal to 14, where N is the number of SIAs, with the energetic advantage increasing with cluster size. Nevertheless, substantial kinetic barriers allow Frank loops to persist as metastable defects. For perfect loops, diffusion coefficients computed over N = 16 to 400 reveal a nearly size-independent migration barrier of approximately 0.02 eV, while the diffusion prefactor decreases approximately as N^(-0.54). Trajectory analysis reveals a non-rigid, row-wise relay mechanism in which the number of participating atoms increases systematically with loop size, accounting for much of the observed prefactor scaling. Sub-millisecond in situ TEM observations reveal intermittent loop motion at velocities higher than previously observed but still several orders of magnitude below the intrinsic mobilities predicted by MD, indicating migration through a heterogeneous energy landscape of mobile and pinned states.

cond-mat.mtrl-sci↗

arXiv2026

CVE-SAI: Counterfactual Visual Evidence-Guided Selective Attribute Indexing for Risk-Controlled E-commerce Search

Multimodal product models can complete missing e-commerce attributes, yet current methods still optimize attribute-answer accuracy without verifying visual support, conflate transient prediction with persistent index admission, and lack explicit risk control over factually incorrect or visually unsupported values. We address these gaps with Counterfactual Visual Evidence-Guided Selective Attribute Indexing (CVE-SAI), which first infers and freezes an ontology-constrained candidate from the primary image and attribute question without catalog text, and then decides whether that candidate should enter the index. Focus-Zone Distortion (FZD) constructs an attribute-specific visual-dependence proxy through a controlled counterfactual intervention, and Evidence-Guided Attention Redistribution (EGAR) uses the proxy to refine ontology-constrained scoring. The canonical candidate is frozen before evidence necessity, evidence retention, nuisance-transformation stability, and candidate-specific catalog-text conflict audits; catalog text can only tighten admission and cannot revise the candidate. Independent family-level calibration selects one policy with a simultaneous one-sided finite-sample bound under a 5% unsafe-admission budget. Experiments on five visual attributes derived from Amazon Berkeley Objects show that CVE-SAI improves attribute inference and evidence localization, achieves the highest certified admission coverage under the shared risk protocol, and yields the strongest controlled retrieval performance with the lowest unsafe auto-induced exposure among automatic-admission systems. Separating inference from admission therefore enables visually supported attribute completion to improve retrieval while limiting persistent index contamination.

cs.AI↗

arXiv2026

Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agents

Large language model (LLM) agents must retain reusable information, control a bounded active context, and recover earlier evidence during long-horizon interaction. Existing methods commonly optimize long-term memory (LTM) and short-term memory (STM) separately, while unified policies are often trained primarily with trajectory-level feedback, which provides weak credit for individual memory decisions. We present Verifiable Memory (VerMem), a framework that represents LTM, active context, and episodic history as distinct states and controls them with one memory operation policy. Seven atomic operations let the policy add, revise, or soft-delete LTM entries; retrieve LTM into the active context; filter or summarize the active context; and restore selected episodic fragments. VerMem is initialized by supervised fine-tuning and trained with a three-stage reinforcement-learning curriculum. The local verifier scores executable memory transitions, and a global verifier assesses evidence coherence and terminal-memory consistency after task completion. These scores are combined with programmatically computed task, evidence-recall, efficiency, and constraint signals through hierarchical credit assignment. The verifiers are used only during training. Across five benchmarks and two LLM backbones, VerMem achieves the best result on the vast majority of reported metrics and consistently outperforms strong memory baselines. Under controlled online-token budgets on three interactive benchmarks, it also achieves the strongest efficiency--performance frontier among the compared methods. Code is available at https://github.com/Sun-SYSU-24/VerMem.

cs.AI↗

arXiv2026

RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation

Scaling robot learning requires massive, diverse trajectory data, yet collection is currently bottlenecked by physical teleoperation, where every demonstration binds operator time to specific hardware and workspaces. We introduce digital teleoperation, a paradigm that decouples data collection from physical constraints by replacing the real robot with a generative world model. In this framework, an operator's hand-pose stream drives a robot-centric generative world model to synthesize high-fidelity egocentric videos from a single reference image. The recorded pose stream serves as an embodiment-agnostic action label transferable to any target robot via standard retargeting, yielding complete state-action trajectories for imitation learning independent of physical hardware. We instantiate this paradigm in RynnWorld-Teleop, a system that integrates depth-aware skeletal conditioning, progressive human-to-robot training on a video Diffusion Transformer, and streaming autoregressive distillation. This pipeline compresses the generative process into a single-pass inference, enabling 40+ FPS, real-time interactive generation on a single H100 GPU. Policies trained exclusively on RynnWorld-Teleop-generated data achieve effective zero-shot Sim2Real transfer across dexterous and diverse bimanual tasks. Moreover, augmenting real-world datasets with our digitally teleoperated data consistently improves success rates, demonstrating that RynnWorld-Teleop serves as a high-fidelity, scalable data engine for the next generation of robotic agents.

cs.RO↗

arXiv2026

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping

Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective paradigm for improving the reasoning capability of Large Vision-Language Models (LVLMs). However, existing RLVR methods primarily rely on trajectory-level outcome rewards, which assign identical learning signals across all generated tokens. This coarse-grained credit assignment is fundamentally mismatched to multimodal reasoning, where only a sparse subset of tokens is causally grounded in visual evidence. Consequently, these pivotal perceptual tokens receive weak supervision and are often overwhelmed by language priors or reasoning-template tokens. To address this limitation, we propose Perception-Reinforced Policy Optimization (PRPO), a token-level reinforcement learning framework that explicitly identifies and reinforces pivotal perceptual tokens within long-horizon multimodal reasoning trajectories. PRPO introduces Robust Visual Dependency (RVD), a principled metric that identifies tokens whose predictions are both visually grounded and perturbation-stable, filtering out brittle or noisy visual tokens. Based on RVD, we further propose Perceptual Advantage Reshaping (PAR), a token-level credit assignment technique that amplifies perceptually informative tokens while preserving stable gradients for non-perceptual tokens. Extensive experiments on seven multimodal reasoning benchmarks demonstrate that PRPO consistently outperforms strong LVLM baselines across both 3B and 7B model scales, achieving average gains of 23.3% and 21.1%, respectively. PRPO achieves state-of-the-art performance with improved training efficiency and stronger cross-task generalization. Our findings highlight the importance of fine-grained credit assignment for scalable multimodal reinforcement learning.

cs.CV↗

arXiv2026

V2I Work Zone Geometry Reconstruction with Pose-Conditioned UWB Range Denoising

Reliable work zone mapping is important for connected and autonomous vehicles (CAVs) to navigate safely and smoothly through work zone areas. Cone-mounted ultra-wideband (UWB) roadside units (RSU) offer a cost-effective way for work zone layout inference, as roadside anchors and vehicle tags provide direct vehicle-to-infrastructure (V2I) range constraints for work zone geometry reconstruction. However, UWB range estimation is degraded by bursty outliers, non-line-of-sight (NLOS) errors, arbitrary anchor-ordering issues, and vehicle pose uncertainties in practical field deployments. To address these challenges, this study proposes a pose-conditioned, permutation-equivariant predictive denoiser for multi-anchor UWB ranging. The model employs shared anchor-wise temporal prediction to capture range dynamics, symmetric set aggregation to handle unordered and missing anchors, and pose-conditioned residual decoding to incorporate vehicle motion as a geometric prior. A two-stage training strategy first learns prediction from observed ranges, and then fine-tunes the denoiser with NLOS-weighted supervision. The method is evaluated on rare real-world V2I UWB field data collected with a CAV, as well as on controlled large-scale simulation benchmarks for ablative insights. Results show that the proposed method substantially improves range accuracy, cone localization, and work zone geometry reconstruction in challenging NLOS-dominated regimes, remains robust to anchor re-indexing and moderate anchor dropout, and reduces measurement-weighted field MSE by 66.9% relative to the raw input.

cs.RO↗

arXiv2026

Planar morphometry via functional shape data analysis and quasi-conformal mappings

The study of shapes is one of the most fundamental problems in life sciences. Although numerous methods have been developed for the morphometry of planar biological shapes over the past several decades, most of them focus solely on either the outer silhouettes or the interior features of the shapes without capturing the coupling between them. Moreover, many existing shape mapping techniques are limited to establishing correspondence between planar structures without further allowing for the quantitative analysis or modelling of shape changes. In this work, we introduce FDA-QC, a novel planar morphometry method that combines functional shape data analysis (FDA) techniques and quasi-conformal (QC) mappings, taking both the boundary and interior of the planar shapes into consideration. Specifically, closed planar curves are represented by their square-root velocity functions and registered by elastic matching in the function space. The induced boundary correspondence is then extended to the entire planar domains by a quasi-conformal map, optionally with landmark constraints. Moreover, the proposed FDA-QC method can naturally lead to a unified framework for shape morphing and shape variation quantification. We apply the FDA-QC method to various leaf and insect wing datasets, and the experimental results show that the proposed combined approach captures morphological variation more effectively than purely boundary-based or interior-based descriptions. Altogether, our work paves a new way for understanding the growth and form of planar biological shapes.

q-bio.QM↗

arXiv2026

RefProtoFL: Communication-Efficient Federated Learning via External-Referenced Prototype Alignment

Federated learning (FL) enables collaborative model training without sharing raw data in edge environments, but is constrained by limited communication bandwidth and heterogeneous client data distributions. Prototype-based FL mitigates this issue by exchanging class-wise feature prototypes instead of full model parameters; however, existing methods still suffer from suboptimal generalization under severe communication constraints. In this paper, we propose RefProtoFL, a communication-efficient FL framework that integrates External-Referenced Prototype Alignment (ERPA) for representation consistency with Adaptive Probabilistic Update Dropping (APUD) for communication efficiency. Specifically, we decompose the model into a private backbone and a lightweight shared adapter, and restrict federated communication to the adapter parameters only. To further reduce uplink cost, APUD performs magnitude-aware Top-K sparsification, transmitting only the most significant adapter updates for server-side aggregation. To address representation inconsistency across heterogeneous clients, ERPA leverages a small server-held public dataset to construct external reference prototypes that serve as shared semantic anchors. For classes covered by public data, clients directly align local representations to public-induced prototypes, whereas for uncovered classes, alignment relies on server-aggregated global reference prototypes via weighted averaging. Extensive experiments on standard benchmarks demonstrate that RefProtoFL attains higher classification accuracy than state-of-the-art prototype-based FL baselines.

cs.LG↗

arXiv2025

CATS-V2V: A Real-World Vehicle-to-Vehicle Cooperative Perception Dataset with Complex Adverse Traffic Scenarios

Vehicle-to-Vehicle (V2V) cooperative perception has great potential to enhance autonomous driving performance by overcoming perception limitations in complex adverse traffic scenarios (CATS). Meanwhile, data serves as the fundamental infrastructure for modern autonomous driving AI. However, due to stringent data collection requirements, existing datasets focus primarily on ordinary traffic scenarios, constraining the benefits of cooperative perception. To address this challenge, we introduce CATS-V2V, the first-of-its-kind real-world dataset for V2V cooperative perception under complex adverse traffic scenarios. The dataset was collected by two hardware time-synchronized vehicles, covering 10 weather and lighting conditions across 10 diverse locations. The 100-clip dataset includes 60K frames of 10 Hz LiDAR point clouds and 1.26M multi-view 30 Hz camera images, along with 750K anonymized yet high-precision RTK-fixed GNSS and IMU records. Correspondingly, we provide time-consistent 3D bounding box annotations for objects, as well as static scenes to construct a 4D BEV representation. On this basis, we propose a target-based temporal alignment method, ensuring that all objects are precisely aligned across all sensor modalities. We hope that CATS-V2V, the largest-scale, most supportive, and highest-quality dataset of its kind to date, will benefit the autonomous driving community in related tasks.

cs.CV↗

arXiv2025

Unveiling Uniform Shifted Power Law in Stochastic Human and Autonomous Driving Behavior

Accurately simulating rare but safety-critical driving behaviors is essential for the evaluation and certification of autonomous vehicles (AVs). However, current models often fail to reproduce realistic collision rates when calibrated on real-world data, largely due to inadequate representation of long-tailed behavioral distributions. Here, we uncover a simple yet unifying shifted power law that robustly characterizes the stochasticity of both human-driven vehicle (HV) and AV behaviors, especially in the long-tail regime. The model adopts a parsimonious analytical form with only one or two parameters, enabling efficient calibration even under data sparsity. Analyzing large-scale, micro-level trajectory data from global HV and AV datasets, the shifted power law achieves an average R2 of 0.97 and a nearly identical tail distribution, uniformly fits both frequent behaviors and rare safety-critical deviations, significantly outperforming existing Gaussian-based baselines. When integrated into an agent-based traffic simulator, it enables forward-rolling simulations that reproduce realistic crash patterns for both HVs and AVs, achieving rates consistent with real-world statistics and improving the fidelity of safety assessment without post hoc correction. This discovery offers a unified and data-efficient foundation for modeling high-risk behavior and improves the fidelity of simulation-based safety assessments for mixed AV/HV traffic. The shifted power law provides a promising path toward simulation-driven validation and global certification of AV technologies.

eess.SY↗

arXiv2025

Efficient Federated Learning with Encrypted Data Sharing for Data-Heterogeneous Edge Devices

As privacy protection gains increasing importance, more models are being trained on edge devices and subsequently merged into the central server through Federated Learning (FL). However, current research overlooks the impact of network topology, physical distance, and data heterogeneity on edge devices, leading to issues such as increased latency and degraded model performance. To address these issues, we propose a new federated learning scheme on edge devices that called Federated Learning with Encrypted Data Sharing(FedEDS). FedEDS uses the client model and the model's stochastic layer to train the data encryptor. The data encryptor generates encrypted data and shares it with other clients. The client uses the corresponding client's stochastic layer and encrypted data to train and adjust the local model. FedEDS uses the client's local private data and encrypted shared data from other clients to train the model. This approach accelerates the convergence speed of federated learning training and mitigates the negative impact of data heterogeneity, making it suitable for application services deployed on edge devices requiring rapid convergence. Experiments results show the efficacy of FedEDS in promoting model performance.

cs.LG↗

arXiv2025

NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results

This paper reports on the NTIRE 2025 XGC Quality Assessment Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2025. This challenge is to address a major challenge in the field of video and talking head processing. The challenge is divided into three tracks, including user generated video, AI generated video and talking head. The user-generated video track uses the FineVD-GC, which contains 6,284 user generated videos. The user-generated video track has a total of 125 registered participants. A total of 242 submissions are received in the development phase, and 136 submissions are received in the test phase. Finally, 5 participating teams submitted their models and fact sheets. The AI generated video track uses the Q-Eval-Video, which contains 34,029 AI-Generated Videos (AIGVs) generated by 11 popular Text-to-Video (T2V) models. A total of 133 participants have registered in this track. A total of 396 submissions are received in the development phase, and 226 submissions are received in the test phase. Finally, 6 participating teams submitted their models and fact sheets. The talking head track uses the THQA-NTIRE, which contains 12,247 2D and 3D talking heads. A total of 89 participants have registered in this track. A total of 225 submissions are received in the development phase, and 118 submissions are received in the test phase. Finally, 8 participating teams submitted their models and fact sheets. Each participating team in every track has proposed a method that outperforms the baseline, which has contributed to the development of fields in three tracks.

cs.CV↗

arXiv2025

Reverse Preference Optimization for Complex Instruction Following

Instruction following (IF) is a critical capability for large language models (LLMs). However, handling complex instructions with multiple constraints remains challenging. Previous methods typically select preference pairs based on the number of constraints they satisfy, introducing noise where chosen examples may fail to follow some constraints and rejected examples may excel in certain respects over the chosen ones. To address the challenge of aligning with multiple preferences, we propose a simple yet effective method called Reverse Preference Optimization (RPO). It mitigates noise in preference pairs by dynamically reversing the constraints within the instruction to ensure the chosen response is perfect, alleviating the burden of extensive sampling and filtering to collect perfect responses. Besides, reversal also enlarges the gap between chosen and rejected responses, thereby clarifying the optimization direction and making it more robust to noise. We evaluate RPO on two multi-turn IF benchmarks, Sysbench and Multi-IF, demonstrating average improvements over the DPO baseline of 4.6 and 2.5 points (on Llama-3.1 8B), respectively. Moreover, RPO scales effectively across model sizes (8B to 70B parameters), with the 70B RPO model surpassing GPT-4o.

cs.CL↗

arXiv2025

TeleOpBench: A Simulator-Centric Benchmark for Dual-Arm Dexterous Teleoperation

Teleoperation is a cornerstone of embodied-robot learning, and bimanual dexterous teleoperation in particular provides rich demonstrations that are difficult to obtain with fully autonomous systems. While recent studies have proposed diverse hardware pipelines-ranging from inertial motion-capture gloves to exoskeletons and vision-based interfaces-there is still no unified benchmark that enables fair, reproducible comparison of these systems. In this paper, we introduce TeleOpBench, a simulator-centric benchmark tailored to bimanual dexterous teleoperation. TeleOpBench contains 30 high-fidelity task environments that span pick-and-place, tool use, and collaborative manipulation, covering a broad spectrum of kinematic and force-interaction difficulty. Within this benchmark we implement four representative teleoperation modalities-(i) MoCap, (ii) VR device, (iii) arm-hand exoskeletons, and (iv) monocular vision tracking-and evaluate them with a common protocol and metric suite. To validate that performance in simulation is predictive of real-world behavior, we conduct mirrored experiments on a physical dual-arm platform equipped with two 6-DoF dexterous hands. Across 10 held-out tasks we observe a strong correlation between simulator and hardware performance, confirming the external validity of TeleOpBench. TeleOpBench establishes a common yardstick for teleoperation research and provides an extensible platform for future algorithmic and hardware innovation. Codes is now available at https://github.com/cyjdlhy/TeleOpBench .

cs.RO↗

arXiv2025

VMBench: A Benchmark for Perception-Aligned Video Motion Generation

Video generation has advanced rapidly, improving evaluation methods, yet assessing video's motion remains a major challenge. Specifically, there are two key issues: 1) current motion metrics do not fully align with human perceptions; 2) the existing motion prompts are limited. Based on these findings, we introduce VMBench--a comprehensive Video Motion Benchmark that has perception-aligned motion metrics and features the most diverse types of motion. VMBench has several appealing properties: 1) Perception-Driven Motion Evaluation Metrics, we identify five dimensions based on human perception in motion video assessment and develop fine-grained evaluation metrics, providing deeper insights into models' strengths and weaknesses in motion quality. 2) Meta-Guided Motion Prompt Generation, a structured method that extracts meta-information, generates diverse motion prompts with LLMs, and refines them through human-AI validation, resulting in a multi-level prompt library covering six key dynamic scene dimensions. 3) Human-Aligned Validation Mechanism, we provide human preference annotations to validate our benchmarks, with our metrics achieving an average 35.3% improvement in Spearman's correlation over baseline methods. This is the first time that the quality of motion in videos has been evaluated from the perspective of human perception alignment. Additionally, we will soon release VMBench at https://github.com/GD-AIGC/VMBench, setting a new standard for evaluating and advancing motion generation models.

cs.CV↗

arXiv2024

Preference Alignment for Diffusion Model via Explicit Denoised Distribution Estimation

Diffusion models have shown remarkable success in text-to-image generation, making preference alignment for these models increasingly important. The preference labels are typically available only at the terminal of denoising trajectories, which poses challenges in optimizing the intermediate denoising steps. In this paper, we propose to conduct Denoised Distribution Estimation (DDE) that explicitly connects intermediate steps to the terminal denoised distribution. Therefore, preference labels can be used for the entire trajectory optimization. To this end, we design two estimation strategies for our DDE. The first is stepwise estimation, which utilizes the conditional denoised distribution to estimate the model denoised distribution. The second is single-shot estimation, which converts the model output into the terminal denoised distribution via DDIM modeling. Analytically and empirically, we reveal that DDE equipped with two estimation strategies naturally derives a novel credit assignment scheme that prioritizes optimizing the middle part of the denoising trajectory. Extensive experiments demonstrate that our approach achieves superior performance, both quantitatively and qualitatively.

cs.CV↗

arXiv2024

Knowledge-Enhanced Facial Expression Recognition with Emotional-to-Neutral Transformation

Existing facial expression recognition (FER) methods typically fine-tune a pre-trained visual encoder using discrete labels. However, this form of supervision limits to specify the emotional concept of different facial expressions. In this paper, we observe that the rich knowledge in text embeddings, generated by vision-language models, is a promising alternative for learning discriminative facial expression representations. Inspired by this, we propose a novel knowledge-enhanced FER method with an emotional-to-neutral transformation. Specifically, we formulate the FER problem as a process to match the similarity between a facial expression representation and text embeddings. Then, we transform the facial expression representation to a neutral representation by simulating the difference in text embeddings from textual facial expression to textual neutral. Finally, a self-contrast objective is introduced to pull the facial expression representation closer to the textual facial expression, while pushing it farther from the neutral representation. We conduct evaluation with diverse pre-trained visual encoders including ResNet-18 and Swin-T on four challenging facial expression datasets. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art FER methods. The code will be publicly available.

cs.CV↗

arXiv2024

EvLight++: Low-Light Video Enhancement with an Event Camera: A Large-Scale Real-World Dataset, Novel Method, and More

Event cameras offer significant advantages for low-light video enhancement, primarily due to their high dynamic range. Current research, however, is severely limited by the absence of large-scale, real-world, and spatio-temporally aligned event-video datasets. To address this, we introduce a large-scale dataset with over 30,000 pairs of frames and events captured under varying illumination. This dataset was curated using a robotic arm that traces a consistent non-linear trajectory, achieving spatial alignment precision under 0.03mm and temporal alignment with errors under 0.01s for 90% of the dataset. Based on the dataset, we propose \textbf{EvLight++}, a novel event-guided low-light video enhancement approach designed for robust performance in real-world scenarios. Firstly, we design a multi-scale holistic fusion branch to integrate structural and textural information from both images and events. To counteract variations in regional illumination and noise, we introduce Signal-to-Noise Ratio (SNR)-guided regional feature selection, enhancing features from high SNR regions and augmenting those from low SNR regions by extracting structural information from events. To incorporate temporal information and ensure temporal coherence, we further introduce a recurrent module and temporal loss in the whole pipeline. Extensive experiments on our and the synthetic SDSD dataset demonstrate that EvLight++ significantly outperforms both single image- and video-based methods by 1.37 dB and 3.71 dB, respectively. To further explore its potential in downstream tasks like semantic segmentation and monocular depth estimation, we extend our datasets by adding pseudo segmentation and depth labels via meticulous annotation efforts with foundation models. Experiments under diverse low-light scenes show that the enhanced results achieve a 15.97% improvement in mIoU for semantic segmentation.

cs.CV↗