arXiv subjects

Yan Zhang

Publications and source records attributed to Yan Zhang.

At least 127 records · Page 7Linked to original sources

arXiv2026

MTVCraft: Tokenizing 4D Motion for Arbitrary Character Animation

Character image animation has rapidly advanced with the rise of digital humans. However, existing methods rely largely on 2D-rendered pose images for motion guidance, which limits generalization and discards essential 4D information for open-world animation. To address this, we propose MTVCraft (Motion Tokenization Video Crafter), the first framework that directly models raw 3D motion sequences (i.e., 4D motion) for character image animation. Specifically, we introduce 4DMoT (4D motion tokenizer) to quantize 3D motion sequences into 4D motion tokens. Compared to 2D-rendered pose images, 4D motion tokens offer more robust spatial-temporal cues and avoid strict pixel-level alignment between pose images and the character, enabling more flexible and disentangled control. Next, we introduce MV-DiT (Motion-aware Video DiT). By designing unique motion attention with 4D positional encodings, MV-DiT can effectively leverage motion tokens as 4D compact yet expressive context for character image animation in the complex 4D world. We implement MTVCraft on both CogVideoX-5B (small scale) and Wan-2.1-14B (large scale), demonstrating that our framework is easily scalable and can be applied to models of varying sizes. Experiments on the TikTok and Fashion benchmarks demonstrate our state-of-the-art performance. Moreover, powered by robust motion tokens, MTVCraft showcases unparalleled zero-shot generalization. It can animate arbitrary characters in full-body and half-body forms, and even non-human objects across diverse styles and scenarios. Hence, it marks a significant step forward in this field and opens a new direction for pose-guided video generation. Our project page is available at https://github.com/DINGYANB/MTVCrafter. A scaled version has been commercially deployed and is available at https://telestudio.teleagi.cn/generatevideo/creativeWorkshop.

cs.CV↗

arXiv2026

Mem-T: Densifying Rewards for Long-Horizon Memory Agents

Memory agents, which depart from predefined memory-processing pipelines by endogenously managing the processing, storage, and retrieval of memories, have garnered increasing attention for their autonomy and adaptability. However, existing training paradigms remain constrained: agents often traverse long-horizon sequences of memory operations before receiving sparse and delayed rewards, which hinders truly end-to-end optimization of memory management policies. To address this limitation, we introduce Mem-T, an autonomous memory agent that interfaces with a lightweight hierarchical memory database to perform dynamic updates and multi-turn retrieval over streaming inputs. To effectively train long-horizon memory management capabilities, we further propose MoT-GRPO, a tree-guided reinforcement learning framework that transforms sparse terminal feedback into dense, step-wise supervision via memory operation tree backpropagation and hindsight credit assignment, thereby enabling the joint optimization of memory construction and retrieval. Extensive experiments demonstrate that Mem-T is (1) high-performing, surpassing frameworks such as A-Mem and Mem0 by up to $14.92\%$, and (2) economical, operating on a favorable accuracy-efficiency Pareto frontier and reducing inference tokens per query by $\sim24.45\%$ relative to GAM without sacrificing performance.

cs.LG↗

arXiv2026

Automated Thematic Analysis for Clinical Qualitative Data: Iterative Codebook Refinement with Full Provenance

Thematic analysis (TA) is widely used in health research to extract patterns from patient interviews, yet manual TA faces challenges in scalability and reproducibility. LLM-based automation can help, but existing approaches produce codebooks with limited generalizability and lack analytic auditability. We present an automated TA framework combining iterative codebook refinement with full provenance tracking. Evaluated on five corpora spanning clinical interviews, social media, and public transcripts, the framework achieves the highest composite quality score on four of five datasets compared to six baselines. Iterative refinement yields statistically significant improvements on four datasets with large effect sizes, driven by gains in code reusability and distributional consistency while preserving descriptive quality. On two clinical corpora (pediatric cardiology), generated themes align with expert-annotated themes.

cs.CL↗

arXiv2026

Robustness-Aware Tool Selection and Manipulation Planning with Learned Energy-Informed Guidance

Humans subconsciously choose robust ways of selecting and using tools, for example, choosing a ladle over a flat spatula to serve meatballs. However, robustness under external disturbances remains underexplored in robotic tool-use planning. This paper presents a robustness-aware method that jointly selects tools and plans contact-rich manipulation trajectories, explicitly optimizing for robustness against disturbances. At the core of our method is an energy-based robustness metric that guides the planner toward robust manipulation behaviors. We formulate a hierarchical optimization pipeline that first identifies a tool and configuration that optimizes robustness, and then plans a corresponding manipulation trajectory that maintains robustness throughout execution. We evaluate our method across three representative tool-use tasks. Simulation and real-world results demonstrate that our method consistently selects robust tools and generates disturbance-resilient manipulation plans.

cs.RO↗

arXiv2026

UniVBench: Towards Unified Evaluation for Video Foundation Models

Video foundation models aim to integrate video understanding, generation, editing, and instruction following within a single framework, making them a central direction for next-generation multimodal systems. However, existing evaluation benchmarks remain fragmented and limited in scope, as they each target a single task, rely on task-specific metrics, and typically use short or simple video clips. As a result, they do not capture the unified capabilities that these models are designed to deliver. To address this gap, we introduce UniVBench, a benchmark purpose-built for evaluating video foundation models across four core abilities: video understanding, video generation, video editing, and a newly proposed task, video reconstruction, which assesses how faithfully a model can reproduce video content it has encountered. Our benchmark substantially expands the complexity of evaluation by incorporating 200 high-quality, diverse and multi-shot videos, each paired with detailed captions, multi-format editing instructions, and reference images. All videos are human-created and carefully validated, offering richer cinematic information than prior benchmarks. In addition, we develop a unified agentic evaluation system (UniV-Eval) that standardizes prompting, instruction parsing, and scoring across all tasks, enabling fair, scalable, and reproducible comparisons of unified video models. By grounding evaluation in instruction-based multi-shot video tasks, UniVBench provides the first framework for measuring the integrated capabilities that video foundation models aim to achieve. Extensive human annotations ensure our evaluation aligns with human judgment, enabling rigorous assessment and accelerating progress toward robust video intelligence.

cs.CV↗

arXiv2026

Non-Markovian giant-atom dynamics in a disordered lattice

While ideal lattice models have been widely used to study giant-atom systems, fabrication-induced defects inevitably introduce disorder in realistic platforms. Here, we study non-Markovian dynamics of a giant atom coupled to a discrete photonic lattice with on-site frequency disorder. Using time-domain and spectral analyses, we show that the overall population-decay envelope and global photon-transport patterns remain robust against moderate lattice disorder, while the quantified non-Markovian memory can be significantly enhanced within the explored disorder range. We characterize the memory using a normalized geometrical non-Markovianity measure tailored to delayed giant-atom feedback and demonstrate how the coupling-point separation and the disorder strength serve as complementary parameters that shape the delay timescale and the complexity of coherent-feedback interference. Spectral analysis reveals that scattering-band transport is relatively insensitive to disorder, whereas disorder-sensitive bound-state branches and localization features reshape revival windows and promote information backflow. Our results establish a disorder-aware framework for understanding and engineering non-Markovian feedback effects of giant atoms in structured reservoirs.

quant-ph↗

arXiv2026

SSKG Hub: An Expert-Guided Platform for LLM-Empowered Sustainability Standards Knowledge Graphs

Sustainability disclosure standards (e.g., GRI, SASB, TCFD, IFRS S2) are comprehensive yet lengthy, terminology-dense, and highly cross-referential, hindering structured analysis and downstream use. We present SSKG Hub (Sustainability Standards Knowledge Graph Hub), a research prototype and interactive web platform that transforms standards into auditable knowledge graphs (KGs) through an LLM-centered, expert-guided pipeline. The system integrates automatic standard identification, configurable chunking, standard-specific prompting, robust triple parsing, and provenance-aware Neo4j storage with fine-grained audit metadata. LLM extraction produces a provenance-linked Draft KG, which is reviewed, curated, and formally promoted to a Certified KG through meta-expert adjudication. A role-based governance framework covering read-only guest access, expert review and CRUD operations, meta-expert certification, and administrative oversight ensures traceability and accountability across draft and certified states. Beyond graph exploration and triple-level evidence tracing, SSKG Hub supports cross-KG fusion, KG-driven tasks, and dedicated modules for insights and curated resources. We validate the platform through a comprehensive expert-led KG review case study that demonstrates end-to-end curation and quality assurance. The web application is publicly available at www.sskg-hub.com.

cs.CL↗

arXiv2026

AI-driven Large-scale Electron Microscopy enables Whole-tissue Subcellular Digitization

The distribution and interactions of cellular organelles play a critical role in mediating cellular physiology and pathology. Large-scale electron microscopy enables visualization of organelle distribution and interactions at the tissue level with nanometer resolution, but robust and efficient computational analysis tools are lacking. Here, we present a deep learning tool for universal large-scale 2D/3D electron microscopy analysis, DeepOrganelle. This new tool enables high-throughput, cell-resolved spatiotemporal mapping and digitization of organelle distribution and interactions. When applied to spermatogenesis across 12 stages and 22 differentiation status of the germ cells, DeepOrganelle uncovered previously unrecognized, stage-dependent dynamics of mitochondria-endoplasmic reticulum contact sites within one subphase of prophase I during meiosis. It also revealed coordinated organelle redistribution in Sertoli cells towards the blood-testis barrier, digitizing the remodeling dynamics of the tissue. This study demonstrates that DeepOrganelle provides a powerful framework that captures subcellular dynamics at the whole-tissue level.

physics.bio-ph↗

arXiv2026

Particle Thermal Inertia Delays the Onset of Convection in Particulate Rayleigh-Bénard System

We investigate the linear stability of a thermally stratified fluid layer confined between horizontal walls and subject to continuous injection of dilute thermal particles at one boundary and extraction at the opposite, forming a particulate Rayleigh-Bénard (pRB) system. The analysis focuses on the influence of thermal coupling between the dispersed and carrier phases, quantified by the specific heat capacity ratio $ε$. Increasing $ε$ systematically enhances stability, with this effect persisting across a wide range of conditions, including heavy and light particles, variations in volumetric flux, injection velocity and direction, and injection temperature. The stabilizing influence saturates when the volumetric heat capacity of the particles approaches that of the fluid, $ε= O(1)$. The physical mechanism is attributed to a modification of the base-state temperature profile caused by interphase heat exchange, which reduces thermal gradients near the injection wall and weakens buoyancy-driven motion.

physics.flu-dyn↗

arXiv2026

Scale Contrastive Learning with Selective Attentions for Blind Image Quality Assessment

Human visual perception naturally evaluates image quality across multiple scales, a hierarchical process that existing blind image quality assessment (BIQA) algorithms struggle to replicate effectively. This limitation stems from a fundamental misunderstanding: current multi-scale approaches fail to recognize that quality perception varies dramatically between scales -- what appears degraded when viewed closely may look acceptable from a distance. This inconsistency not only creates misleading ``visual illusions'' during feature fusion but also introduces substantial redundant information that dilutes quality-critical features and leads to imprecise assessments. Our CSFIQA framework advances multi-scale BIQA via two key innovations: (1) a selective focus attention mechanism that mimics human visual attention by filtering out redundant cross-scale information that would otherwise mask subtle quality indicators, and (2) a scale contrastive learning strategy that explicitly learns to distinguish quality variations both across and within scales. By incorporating an adaptive noise sample matching mechanism, CSFIQA effectively identifies perceptual quality discrepancies in the same content viewed at different scales. Experiments demonstrate substantial improvements over state-of-the-art methods across seven datasets, achieving up to 8.8% SRCC improvement on challenging real-world distortions, confirming CSFIQA's superior alignment with human quality perception.

cs.CV↗

arXiv2026

UniFit: Towards Universal Virtual Try-on with MLLM-Guided Semantic Alignment

Image-based virtual try-on (VTON) aims to synthesize photorealistic images of a person wearing specified garments. Despite significant progress, building a universal VTON framework that can flexibly handle diverse and complex tasks remains a major challenge. Recent methods explore multi-task VTON frameworks guided by textual instructions, yet they still face two key limitations: (1) semantic gap between text instructions and reference images, and (2) data scarcity in complex scenarios. To address these challenges, we propose UniFit, a universal VTON framework driven by a Multimodal Large Language Model (MLLM). Specifically, we introduce an MLLM-Guided Semantic Alignment Module (MGSA), which integrates multimodal inputs using an MLLM and a set of learnable queries. By imposing a semantic alignment loss, MGSA captures cross-modal semantic relationships and provides coherent and explicit semantic guidance for the generative process, thereby reducing the semantic gap. Moreover, by devising a two-stage progressive training strategy with a self-synthesis pipeline, UniFit is able to learn complex tasks from limited data. Extensive experiments show that UniFit not only supports a wide range of VTON tasks, including multi-garment and model-to-model try-on, but also achieves state-of-the-art performance. The source code and pretrained models are available at https://github.com/zwplus/UniFit.

cs.CV↗

arXiv2026

EAGLE: Elevating Geometric Reasoning through LLM-empowered Visual Instruction Tuning

Multi-modal Large Language Models (MLLMs) have advanced greatly in general tasks. However, they still face challenges in geometric reasoning, a task that requires synergistic integration of visual recognition proficiency and complex reasoning strength. Existing MLLMs prioritize optimizing the LLM backbone to enhance problem-solving capabilities, while rarely emphasizing improvements in discerning visual elements. However, we reveal that MLLMs suffer from severe visual perception deficiencies, including inaccurate geometric comprehension and severe visual hallucinations, which constrain their reasoning performance. To address this issue, we revisit geometric reasoning through a visual-centric lens that highlights the role of visual perception. To achieve this, we propose EAGLE, a novel coarse-to-fine visual enhancement framework that progressively leverages LLMs' guidance to improve perception proficiency. Specifically, given the substantial disparity between geometric diagrams and natural images, we first introduce Geometric Knowledge Injection. This process explores fundamental knowledge from diagram-caption data to enhance recognition capabilities and improve geometry-language alignments. Then, recognizing that different elements contribute unequally in the reasoning process, we introduce Geometric Knowledge Refinement. This stage leverages LLM-driven chain-of-thought solutions to guide the vision encoder in adaptively prioritizing key elements, fostering a synergistic interplay between visual comprehension and mathematical reasoning. Finally, we develop EAGLE, a geometry expert with strong perception and reasoning capabilities. Extensive experiments demonstrate its effectiveness on three popular benchmarks.

cs.CV↗

arXiv2026

Reliable Explanations or Random Noise? A Reliability Metric for XAI

In recent years, explaining decisions made by complex machine learning models has become essential in high-stakes domains such as energy systems, healthcare, finance, and autonomous systems. However, the reliability of these explanations, namely, whether they remain stable and consistent under realistic, non-adversarial changes, remains largely unmeasured. Widely used methods such as SHAP and Integrated Gradients (IG) are well-motivated by axiomatic notions of attribution, yet their explanations can vary substantially even under system-level conditions, including small input perturbations, correlated representations, and minor model updates. Such variability undermines explanation reliability, as reliable explanations should remain consistent across equivalent input representations and small, performance-preserving model changes. We introduce the Explanation Reliability Index (ERI), a family of metrics that quantifies explanation stability under four reliability axioms: robustness to small input perturbations, consistency under feature redundancy, smoothness across model evolution, and resilience to mild distributional shifts. For each axiom, we derive formal guarantees, including Lipschitz-type bounds and temporal stability results. We further propose ERI-T, a dedicated measure of temporal reliability for sequential models, and introduce ERI-Bench, a benchmark designed to systematically stress-test explanation reliability across synthetic and real-world datasets. Experimental results reveal widespread reliability failures in popular explanation methods, showing that explanations can be unstable under realistic deployment conditions. By exposing and quantifying these instabilities, ERI enables principled assessment of explanation reliability and supports more trustworthy explainable AI (XAI) systems.

cs.LG↗

arXiv2026

The orbital parameters of gamma-ray binary PSR~J2032+4127

PSR~J2032+4127 is the only one of gamma-ray binary, that exhibits pulsations in gamma-ray. Previous research has indicated that the pulsar and the Be star MT91 213 orbit each other in a highly eccentric orbit with an extremely long period, with the pulsar reaching its periastron on November 13, 2017. Since its launch, the \fermi{} satellite has been monitoring this pulsar for 16 years, covering the 8 years before and the 8 years after the pulsar passed its periastron. Using these data, we present an analysis of pulse arrival times, and precisely determine the orbital parameters for the first time: the orbital period of $P_{\rm orb} \sim 52.3$ yr, the eccentricity of $e \sim 0.98$, the semimajor axis of $a$sin$i \sim 25.3$ AU, and the orbital inclination of $\sim$ 47.1$^\circ$ -- 55.1$^\circ$. We also reveal another small glitch occurred in 2021, MJD $\sim$ 59500.

astro-ph.HE↗

arXiv2026

Adaptive Quantum-Safe Cryptography for 6G Vehicular Networks via Context-Aware Optimization

Powerful quantum computers in the future may be able to break the security used for communication between vehicles and other devices (Vehicle-to-Everything, or V2X). New security methods called post-quantum cryptography can help protect these systems, but they often require more computing power and can slow down communication, posing a challenge for fast 6G vehicle networks. In this paper, we propose an adaptive post-quantum cryptography (PQC) framework that predicts short-term mobility and channel variations and dynamically selects suitable lattice-, code-, or hash-based PQC configurations using a predictive multi-objective evolutionary algorithm (APMOEA) to meet vehicular latency and security constraints.However, frequent cryptographic reconfiguration in dynamic vehicular environments introduces new attack surfaces during algorithm transitions. A secure monotonic-upgrade protocol prevents downgrade, replay, and desynchronization attacks during transitions. Theoretical results show decision stability under bounded prediction error, latency boundedness under mobility drift, and correctness under small forecast noise. These results demonstrate a practical path toward quantum-safe cryptography in future 6G vehicular networks. Through extensive experiments based on realistic mobility (LuST), weather (ERA5), and NR-V2X channel traces, we show that the proposed framework reduces end-to-end latency by up to 27\%, lowers communication overhead by up to 65\%, and effectively stabilizes cryptographic switching behavior using reinforcement learning. Moreover, under the evaluated adversarial scenarios, the monotonic-upgrade protocol successfully prevents downgrade, replay, and desynchronization attacks.

cs.CR↗

arXiv2026

Open-Vocabulary Functional 3D Human-Scene Interaction Generation

Generating 3D humans that functionally interact with 3D scenes remains an open problem with applications in embodied AI, robotics, and interactive content creation. The key challenge involves reasoning about both the semantics of functional elements in 3D scenes and the 3D human poses required to achieve functionality-aware interaction. Unfortunately, existing methods typically lack explicit reasoning over object functionality and the corresponding human-scene contact, resulting in implausible or functionally incorrect interactions. In this work, we propose FunHSI, a training-free, functionality-driven framework that enables functionally correct human-scene interactions from open-vocabulary task prompts. Given a task prompt, FunHSI performs functionality-aware contact reasoning to identify functional scene elements, reconstruct their 3D geometry, and model high-level interactions via a contact graph. We then leverage vision-language models to synthesize a human performing the task in the image and estimate proposed 3D body and hand poses. Finally, the proposed 3D body configuration is refined via stage-wise optimization to ensure physical plausibility and functional correctness. In contrast to existing methods, FunHSI not only synthesizes more plausible general 3D interactions, such as "sitting on a sofa'', while supporting fine-grained functional human-scene interactions, e.g., "increasing the room temperature''. Extensive experiments demonstrate that FunHSI consistently generates functionally correct and physically plausible human-scene interactions across diverse indoor and outdoor scenes.

cs.CV↗

arXiv2026

Hidden-charm and -bottom tetraquark states with $J^{PC}=1^{-+}$ via QCD sum rules

We investigate the $1^{-+}$ hidden-charm and hidden-bottom tetraquark states within the framework of QCD sum rules. The mass spectra are computed by including condensates up to dimension eight in the operator product expansion. Our results indicate the possible existence of four $1^{-+}$ hidden-charm tetraquark states, with predicted masses of $(4.83 \pm 0.15)$ GeV, $(4.88 \pm 0.18)$ GeV, $(4.72 \pm 0.16)$ GeV, and $(4.79 \pm 0.12)$ GeV, while their hidden-bottom counterparts are estimated to have masses of $(11.08 \pm 0.16)$ GeV, $(11.16 \pm 0.14)$ GeV, $(10.99 \pm 0.16)$ GeV, and $(11.03 \pm 0.15)$ GeV, respectively. We also analyze the possible decay modes of these tetraquark states, which may be accessible in future experiments at BESIII, Belle~II, LHCb, and future STCF. These findings provide valuable guidance for the experimental search for exotic $1^{-+}$ tetraquark states in both the charm and bottom sectors.

hep-ph↗

arXiv2026

GeoDiff3D: Self-Supervised 3D Scene Generation with Geometry-Constrained 2D Diffusion Guidance

3D scene generation is a core technology for gaming, film/VFX, and VR/AR. Growing demand for rapid iteration, high-fidelity detail, and accessible content creation has further increased interest in this area. Existing methods broadly follow two paradigms - indirect 2D-to-3D reconstruction and direct 3D generation - but both are limited by weak structural modeling and heavy reliance on large-scale ground-truth supervision, often producing structural artifacts, geometric inconsistencies, and degraded high-frequency details in complex scenes. We propose GeoDiff3D, an efficient self-supervised framework that uses coarse geometry as a structural anchor and a geometry-constrained 2D diffusion model to provide texture-rich reference images. Importantly, GeoDiff3D does not require strict multi-view consistency of the diffusion-generated references and remains robust to the resulting noisy, inconsistent guidance. We further introduce voxel-aligned 3D feature aggregation and dual self-supervision to maintain scene coherence and fine details while substantially reducing dependence on labeled data. GeoDiff3D also trains with low computational cost and enables fast, high-quality 3D scene generation. Extensive experiments on challenging scenes show improved generalization and generation quality over existing baselines, offering a practical solution for accessible and efficient 3D scene construction.

cs.CV↗