Searcharxiv⌕ Search

arXiv subjects

Yuting Zhang

Publications and source records attributed to Yuting Zhang.

At least 19 recordsLinked to original sources
arXiv2026

Vorch-Omni: Multi-Task Orchestration of Sight and Sound

Recent advances in generative video modeling have enabled diverse generation, reference-based synthesis, extension, and editing, but existing approaches often rely on fragmented task-specific models. A general model must distinguish heterogeneous target, source, and reference signals to determine what to generate, preserve, or use as guidance, while reducing interference among tasks. Joint audio-visual generation further increases this challenge by introducing diverse conditioning and output configurations across modalities. We present Vorch-Omni, a unified multi-task framework for audio-visual synthesis based on an arbitrary-condition-to-arbitrary-output formulation. It flexibly treats video and audio signals as either conditioning inputs or generation targets. Token-level conditioning masks and task identifiers distinguish targets, source content, and references, while position types separate temporal context from independent conditions. To capture semantic and structural information, Vorch-Omni employs complementary visual conditioning pathways: a vision-language model interprets sampled frames with text instructions, and a video VAE encodes conditions into latent tokens for direct guidance. We further build a distributed data pipeline to curate diverse temporally aligned audio-visual clips, generate structured captions and metadata, and balance heterogeneous task distributions. Built on a single flow-matching diffusion transformer without task-specific architectural changes, Vorch-Omni supports over 10 tasks, including text-to-video, text-to-audio-video, image- and reference-conditioned generation, temporal extension, audio-driven generation, video transformation, and audio-visual editing. This unified framework provides a scalable foundation for general-purpose audio-visual generation and manipulation.

cs.CV↗
arXiv2026

SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport

Self-supervised Continual Graph Learning (CGL) aims to successively learn from a graph sequence with different tasks without label supervision - a paradigm that has attracted widespread attention. Most existing self-supervised CGL methods rely on instance-level consistency objectives that enforce stability of individual node (or node-pair) embeddings. Due to optimizing nodes in isolation, these methods fail to maintain global relational structure, causing inter-node correspondences to progressively distort under continual learning. To this end, we propose a novel Structure-Aware Optimal Transport (SAOT) framework that explicitly captures and preserves relational structure within graph representations across sequential tasks. Specifically, SAOT leverages optimal transport theory to capture global inter-node correspondences, thereby facilitating and enhancing graph representation learning. Simultaneously, SAOT incorporates a cross-task knowledge distillation mechanism to preserve the previous structural knowledge. Extensive experiments on four CGL benchmark datasets demonstrate that SAOT outperforms existing self-supervised baselines. In particular, SAOT achieves significant performance gains, improving average accuracy by up to 5% on CoraFull-CL and over 15% on Products-CL compared with state-of-the-art methods in the Class-IL setting.

cs.LG↗
arXiv2026

StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns

We introduce StaminaBench, a benchmark that measures the stamina of coding agents: how many consecutive interaction turns (change requests) they can handle before failing. Unlike the prevailing fraction-of-tasks-solved metric, this matches real vibe-coding where sessions run dozens or hundreds of turns. In StaminaBench, agents implement a REST API server and modify it across a tunable number of procedurally generated follow-up change requests - 100 in our experiments, resulting in codebases of up to 6,000 lines. Tests are generated fully programmatically without LLM involvement, ensuring reproducibility and reliability; change sequences are drawn from either a hardcoded or LLM-driven sampler, both constrained to a structured action space to ensure changes are valid. The agent and the server run in an isolated environment and communicate with the benchmark through HTTP, making testing fully black-box and language-agnostic. We evaluate six agent harnesses paired with seven open-source LLMs across 20 scenarios of 100 turns each and find that: (1) all the tested models fail within 5-6 turns, confirming that vibe-coding-style programming without thorough testing produces bugs; (2) passing test feedback back to the agent and allowing it to retry improves passed turn count by up to 12x; and (3) a good harness is required for strong performance: stronger models exhibit up to a 6x gap between their best and worst harness, while weaker models fail with any harness. We release the benchmark and the generated tasks to enable further research into multi-turn coding agent behavior. Benchmark code and data: github.com/amazon-science/StaminaBench.

cs.SE↗
arXiv2026

Are Large Language Models Suitable for Graph Computation? Progress and Prospects

Large language models (LLMs) have been increasingly explored for graph computation, where tasks require reasoning over structured relationships and algorithmic operations. Yet, it remains unclear when LLMs can reliably support such computation and how they should be incorporated into graph-solving pipelines. Existing surveys at the intersection of LLMs and graphs primarily focus on graph learning, text-attributed graphs, or graph-language modeling. To bridge this gap, we provide a comprehensive review of LLMs for graph computation through a role-based taxonomy. Specifically, we identify two major paradigms: i) LLMs as executors, where models directly solve graph tasks from graph descriptions and instructions; and ii) LLMs as planners, where models formulate problems, decompose reasoning steps, and invoke external tools or agents for execution. Based on this taxonomy, we analyze the strengths and limitations of current methods. Our review indicates that LLMs are promising for simple, small-scale tasks, but remain unreliable for large-scale and exactness-demanding tasks. Finally, we summarize available datasets and suggest four future directions.

cs.CL↗
arXiv2026

Non-local low energy neutral excitations in a strongly disordered triangular Mott magnet Cr$_3$Se$_2$Br$_5$

Understanding if low-energy excitations can remain itinerant in the presence of strong disorder remains a central challenge in frustrated quantum magnets, where disorder is generally expected to localize excitations through Anderson-like mechanisms. Here we report the emergence of charge-neutral itinerant excitations in a van der Waals compound Cr$_3$Se$_2$Br$_5$, a strongly disordered $S = 3/2$ Mott insulator with a frustrated triangular lattice. Structural analysis reveals substantial intrinsic disorder arising from Cr-site deficiency and Se/Br-site mixing, which appear to be fixed and cannot be readily tuned. No long-range magnetic order or conventional glassy behavior is observed. In addition to its highly insulating nature, the magnetic specific heat C_mag/T and thermal conductivity \k{appa}_xx/T both exhibit linear temperature dependencies with substantial finite intercepts. In particular, a sizeable field-independent residual term $\kappa/T \approx 0.03~\mathrm{W\,m^{-1}\,K^{-2}}$ is observed, providing compelling evidence of itinerant low-energy excitations that carry entropy without charge. These findings conceptually advance our understanding of quantum matter by demonstrating a rare regime where the interplay of disorder, frustration, and electronic correlations actively reshapes the nature of low-energy excitations, allowing itinerant neutral excitations to coexist with strong intrinsic disorder.

cond-mat.str-el↗
arXiv2026

OpenEvoShield: Dual Non-Stationary Continual Defense for Open-World Multi-Agent System Attacks

LLM-based multi-agent systems (LLM-MAS) are increasingly deployed in safety-critical applications, where adversaries inject malicious instructions through inter-agent communication to propagate harmful behaviors. Unlike static threats, these attacks are doubly dynamic: adversaries refine injection strategies against deployed defenses while normal-agent behavior drifts with system expansion. Existing defenses treat deployment as a closed-world problem and degrade rapidly once either distribution shifts beyond training coverage. We propose OpenEvoShield, a co-evolutionary continual defense framework for LLM-MAS. An asymmetric rate controller (M1) decouples fast attack-side and slow normal-side learning rates from dual drift signals. A normal-boundary updater (M2) maintains a dynamic behavioral boundary at the slow rate, while an EWC-regularized policy ensemble (M3) fast-adapts without catastrophic forgetting. An energy-based multi-granularity detector (M4) fuses node-, subgraph-, and graph-level evidence to classify novel attacks as out-of-distribution. Experiments over 100 deployment rounds across five benchmarks and four MAS topologies show that OpenEvoShield outperforms static and continual baselines, detecting most previously unseen attacks while keeping false positive rates low.

cs.AI↗
arXiv2026

Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models

We introduce Mutual Reinforcement Learning, a framework for concurrent RL post-training in which heterogeneous LLM policies exchange typed experience while keeping separate parameters, objectives, and tokenizers. The framework combines a Shared Experience Exchange (SEE), Multi-Worker Resource Allocation (MWRA), and a Tokenizer Heterogeneity Layer (THL) that retokenizes text and aligns token-level traces across incompatible vocabularies. This substrate makes the experience-sharing design question operational across model families. We instantiate three controlled probes on top of GRPO: data-level rollout sharing via Peer Rollout Pooling (PRP), value-level advantage sharing via Cross-Policy GRPO Advantage Sharing (XGRPO), and outcome-level success transfer via Success-Gated Transfer (SGT). A contextual-bandit analysis characterizes their structural positions on a stability-support trade-off: PRP pays density-ratio variance and THL residual costs, XGRPO preserves on-policy actor support while changing scalar baselines, and SGT supplies a rescue-set score direction toward verified peer successes. In the evaluated regime, outcome-level sharing occupies the favorable point of this trade-off.

cs.LG↗
arXiv2026

Discrete Preference Learning for Personalized Multimodal Generation

The emergence of generative models enables the creation of texts and images tailored to users' preferences. Existing personalized generative models have two critical limitations: lacking a dedicated paradigm for accurate preference modeling, and generating unimodal content despite real-world multimodal-driven user interactions. Therefore, we propose personalized multimodal generation, which captures modal-specific preferences via a dedicated preference model from multimodal interactions, and then feeds them into downstream generators for personalized multimodal content. However, this task presents two challenges: (1) Gap between continuous preferences from dedicated modeling and discrete token inputs intrinsic to generator architectures; (2) Potential inconsistency between generated images and texts. To tackle these, we present a two-stage framework called Discrete Preference learning for Personalized Multimodal Generation (DPPMG). In the first stage, to accurately learn discrete modal-specific preferences, we introduce a modal-specific graph neural network (a dedicated preference model) to learn users' modal-specific preferences, which preferences are then quantized into discrete preference tokens. In the second stage, the discrete modal-specific preference tokens are injected into downstream text and image generators. To further enhance cross-modal consistency while preserving personalization, we design a cross-modal consistent and personalized reward to fine-tune token-associated parameters. Extensive experiments on two real-world datasets demonstrate the effectiveness of our model in generating personalized and consistent multimodal content.

cs.IR↗
arXiv2026

Surg-R1: A Hierarchical Reasoning Foundation Model for Scalable and Interpretable Surgical Decision Support with Multi-Center Clinical Validation

Surgical scene understanding demands not only accurate predictions but also interpretable reasoning that surgeons can verify against clinical expertise. However, existing surgical vision-language models generate predictions without reasoning chains, and general-purpose reasoning models fail on compositional surgical tasks without domain-specific knowledge. We present Surg-R1, a surgical Vision-Language Model that addresses this gap through hierarchical reasoning trained via a four-stage pipeline. Our approach introduces three key contributions: (1) a three-level reasoning hierarchy decomposing surgical interpretation into perceptual grounding, relational understanding, and contextual reasoning; (2) the largest surgical chain-of-thought dataset with 320,000 reasoning pairs; and (3) a four-stage training pipeline progressing from supervised fine-tuning to group relative policy optimization and iterative self-improvement. Evaluation on SurgBench, comprising six public benchmarks and six multi-center external validation datasets from five institutions, demonstrates that Surg-R1 achieves the highest Arena Score (64.9%) on public benchmarks versus Gemini 3.0 Pro (46.1%) and GPT-5.1 (37.9%), outperforming both proprietary reasoning models and specialized surgical VLMs on the majority of tasks spanning instrument localization, triplet recognition, phase recognition, action recognition, and critical view of safety assessment, with a 15.2 percentage point improvement over the strongest surgical baseline on external validation.

cs.CV↗
arXiv2026

RoboPocket: Improve Robot Policies Instantly with Your Phone

Scaling imitation learning is fundamentally constrained by the efficiency of data collection. While handheld interfaces have emerged as a scalable solution for in-the-wild data acquisition, they predominantly operate in an open-loop manner: operators blindly collect demonstrations without knowing the underlying policy's weaknesses, leading to inefficient coverage of critical state distributions. Conversely, interactive methods like DAgger effectively address covariate shift but rely on physical robot execution, which is costly and difficult to scale. To reconcile this trade-off, we introduce RoboPocket, a portable system that enables Robot-Free Instant Policy Iteration using single consumer smartphones. Its core innovation is a Remote Inference framework that visualizes the policy's predicted trajectory via Augmented Reality (AR) Visual Foresight. This immersive feedback allows collectors to proactively identify potential failures and focus data collection on the policy's weak regions without requiring a physical robot. Furthermore, we implement an asynchronous Online Finetuning pipeline that continuously updates the policy with incoming data, effectively closing the learning loop in minutes. Extensive experiments demonstrate that RoboPocket adheres to data scaling laws and doubles the data efficiency compared to offline scaling strategies, overcoming their long-standing efficiency bottleneck. Moreover, our instant iteration loop also boosts sample efficiency by up to 2$\times$ in distributed environments a small number of interactive corrections per person. Project page and videos: https://robo-pocket.github.io.

cs.RO↗
arXiv2026

Reinforcement-aware Knowledge Distillation for LLM Reasoning

Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most existing knowledge distillation (KD) methods are designed for supervised fine-tuning (SFT), relying on fixed teacher traces or teacher-student Kullback-Leibler (KL) divergence-based regularization. When combined with RL, these approaches often suffer from distribution mismatch and objective interference: teacher supervision may not align with the student's evolving rollout distribution, and the KL regularizer can compete with reward maximization and require careful loss balancing. To address these issues, we propose RL-aware distillation (RLAD), which performs selective imitation during RL -- guiding the student toward the teacher only when it improves the current policy update. Our core component, Trust Region Ratio Distillation (TRRD), replaces the teacher-student KL regularizer with a PPO/GRPO-style likelihood-ratio objective anchored to a teacher--old-policy mixture, yielding advantage-aware, trust-region-bounded distillation on student rollouts and naturally balancing exploration, exploitation, and imitation. Across diverse logic reasoning and math benchmarks, RLAD consistently outperforms offline distillation, standard GRPO, and KL-based on-policy teacher-student knowledge distillation.

cs.LG↗
arXiv2026

EvoMAS: Evolutionary Generation of Multi-Agent Systems

Large language model (LLM)-based multi-agent systems (MAS) show strong promise for complex reasoning, planning, and tool-augmented tasks, but designing effective MAS architectures remains labor-intensive, brittle, and hard to generalize. Existing automatic MAS generation methods either rely on code generation, which often leads to executability and robustness failures, or impose rigid architectural templates that limit expressiveness and adaptability. We propose Evolutionary Generation of Multi-Agent Systems (EvoMAS), which formulates MAS generation as structured configuration generation. EvoMAS performs evolutionary generation in configuration space. Specifically, EvoMAS selects initial configurations from a pool, applies feedback-conditioned mutation and crossover guided by execution traces, and iteratively refines both the candidate pool and an experience memory. We evaluate EvoMAS on diverse benchmarks, including BBEH, SWE-Bench, and WorkBench, covering reasoning, software engineering, and tool-use tasks. EvoMAS consistently improves task performance over both human-designed MAS and prior automatic MAS generation methods, while producing generated systems with higher executability and runtime robustness. EvoMAS outperforms the agent evolution method EvoAgent by +10.5 points on BBEH reasoning and +7.1 points on WorkBench. With Claude-4.5-Sonnet, EvoMAS also reaches 79.1% on SWE-Bench-Verified, matching the top of the leaderboard. Code is available at https://github.com/amazon-science/EvoMAS

cs.LG↗
arXiv2026

Enhancing LLM-based Recommendation with Preference Hint Discovery from Knowledge Graph

LLMs have garnered substantial attention in recommendation systems. Yet they fall short of traditional recommenders when capturing complex preference patterns. Recent works have tried integrating traditional recommendation embeddings into LLMs to resolve this issue, yet a core gap persists between their continuous embedding and discrete semantic spaces. Intuitively, textual attributes derived from interactions can serve as critical preference rationales for LLMs' recommendation logic. However, directly inputting such attribute knowledge presents two core challenges: (1) Deficiency of sparse interactions in reflecting preference hints for unseen items; (2) Substantial noise introduction from treating all attributes as hints. To this end, we propose a preference hint discovery model based on the interaction-integrated knowledge graph, enhancing LLM-based recommendation. It utilizes traditional recommendation principles to selectively extract crucial attributes as hints. Specifically, we design a collaborative preference hint extraction schema, which utilizes semantic knowledge from similar users' explicit interactions as hints for unseen items. Furthermore, we develop an instance-wise dual-attention mechanism to quantify the preference credibility of candidate attributes, identifying hints specific to each unseen item. Using these item- and user-based hints, we adopt a flattened hint organization method to shorten input length and feed the textual hint information to the LLM for commonsense reasoning. Extensive experiments on both pair-wise and list-wise recommendation tasks verify the effectiveness of our proposed framework, indicating an average relative improvement of over 3.02% against baselines.

cs.IR↗
arXiv2026

How Real is Your Jailbreak? Fine-grained Jailbreak Evaluation with Anchored Reference

Jailbreak attacks present a significant challenge to the safety of Large Language Models (LLMs), yet current automated evaluation methods largely rely on coarse classifications that focus mainly on harmfulness, leading to substantial overestimation of attack success. To address this problem, we propose FJAR, a fine-grained jailbreak evaluation framework with anchored references. We first categorized jailbreak responses into five fine-grained categories: Rejective, Irrelevant, Unhelpful, Incorrect, and Successful, based on the degree to which the response addresses the malicious intent of the query. This categorization serves as the basis for FJAR. Then, we introduce a novel harmless tree decomposition approach to construct high-quality anchored references by breaking down the original queries. These references guide the evaluator in determining whether the response genuinely fulfills the original query. Extensive experiments demonstrate that FJAR achieves the highest alignment with human judgment and effectively identifies the root causes of jailbreak failures, providing actionable guidance for improving attack strategies.

cs.CR↗
arXiv2025

PHASE: Physiology-Aware Hyperspectral Reconstruction via Object-to-Human Domain Adaptation

Although hyperspectral imaging offers unparalleled non-invasive physiological insight, its bulky hardware, slow acquisition, and regulatory burden severely limit its clinical availability. A natural workaround is to reconstruct hyperspectral information from ubiquitous RGB or CASSI measurements. However, existing paradigms, developed for object-centric scenes, rely on reflectance-based feature alignment, assuming that spectral similarity preserves semantic meaning. This assumption breaks down in physiological imaging, where visually similar RGB responses may arise from distinct and entangled physiological states. This mismatch motivates a shift from reflectance alignment to physiology-aware representation learning, grounded in shared light-matter interaction principles -- a shift that introduces fundamental challenges from cross-channel semantic shifts (C1) and irreversible information loss in RGB-based acquisition (C2). We therefore design PHASE, a physiology-aware hyperspectral reconstruction paradigm that fundamentally redefines object-to-human transfer by disentangling cross-channel physiological semantics via Physiological Channel Reinterpretation and restricting reconstruction to physiologically plausible solutions through Physiologically Constrained Alignment. Under two source-to-target transfer protocols, PHASE consistently outperforms state-of-the-art methods by up to +2.20 SSIM and -3.06 in SAM with merely 1.5% labeled supervision.

cs.CV↗
arXiv2025

A Language-Signal-Vision Multimodal Framework for Multitask Cardiac Analysis

Contemporary cardiovascular management involves complex consideration and integration of multimodal cardiac datasets, where each modality provides distinct but complementary physiological characteristics. While the effective integration of multiple modalities could yield a holistic clinical profile that accurately models the true clinical situation with respect to data modalities and their relatives weightings, current methodologies remain limited by: 1) the scarcity of patient- and time-aligned multimodal data; 2) reliance on isolated single-modality or rigid multimodal input combinations; 3) alignment strategies that prioritize cross-modal similarity over complementarity; and 4) a narrow single-task focus. In response to these limitations, a comprehensive multimodal dataset was curated for immediate application, integrating laboratory test results, electrocardiograms, and echocardiograms with clinical outcomes. Subsequently, a unified framework, Textual Guidance Multimodal fusion for Multiple cardiac tasks (TGMM), was proposed. TGMM incorporated three key components: 1) a MedFlexFusion module designed to capture the unique and complementary characteristics of medical modalities and dynamically integrate data from diverse cardiac sources and their combinations; 2) a textual guidance module to derive task-relevant representations tailored to diverse clinical objectives, including heart disease diagnosis, risk stratification and information retrieval; and 3) a response module to produce final decisions for all these tasks. Furthermore, this study systematically explored key features across multiple modalities and elucidated their synergistic contributions in clinical decision-making. Extensive experiments showed that TGMM outperformed state-of-the-art methods across multiple clinical tasks, with additional validation confirming its robustness on another public dataset.

cs.AI↗
arXiv2025

CardAIc-Agents: A Multimodal Framework with Hierarchical Adaptation for Cardiac Care Support

Cardiovascular diseases (CVDs) remain the foremost cause of mortality worldwide, a burden worsened by a severe deficit of healthcare workers. Artificial intelligence (AI) agents have shown potential to alleviate this gap through automated detection and proactive screening, yet their clinical application remains limited by: 1) rigid sequential workflows, whereas clinical care often requires adaptive reasoning that select specific tests and, based on their results, guides personalised next steps; 2) reliance solely on intrinsic model capabilities to perform role assignment without domain-specific tool support; 3) general and static knowledge bases without continuous learning capability; and 4) fixed unimodal or bimodal inputs and lack of on-demand visual outputs when clinicians require visual clarification. In response, a multimodal framework, CardAIc-Agents, was proposed to augment models with external tools and adaptively support diverse cardiac tasks. First, a CardiacRAG agent generated task-aware plans from updatable cardiac knowledge, while the Chief agent integrated tools to autonomously execute these plans and deliver decisions. Second, to enable adaptive and case-specific customization, a stepwise update strategy was developed to dynamically refine plans based on preceding execution results, once the task was assessed as complex. Third, a multidisciplinary discussion team was proposed which was automatically invoked to interpret challenging cases, thereby supporting further adaptation. In addition, visual review panels were provided to assist validation when clinicians raised concerns. Experiments across three datasets showed the efficiency of CardAIc-Agents compared to mainstream Vision-Language Models (VLMs) and state-of-the-art agentic systems.

cs.AI↗
arXiv2025

CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation

Emotional Image Content Generation (EICG) aims to generate semantically clear and emotionally faithful images based on given emotion categories, with broad application prospects. While recent text-to-image diffusion models excel at generating concrete concepts, they struggle with the complexity of abstract emotions. There have also emerged methods specifically designed for EICG, but they excessively rely on word-level attribute labels for guidance, which suffer from semantic incoherence, ambiguity, and limited scalability. To address these challenges, we propose CoEmoGen, a novel pipeline notable for its semantic coherence and high scalability. Specifically, leveraging multimodal large language models (MLLMs), we construct high-quality captions focused on emotion-triggering content for context-rich semantic guidance. Furthermore, inspired by psychological insights, we design a Hierarchical Low-Rank Adaptation (HiLoRA) module to cohesively model both polarity-shared low-level features and emotion-specific high-level semantics. Extensive experiments demonstrate CoEmoGen's superiority in emotional faithfulness and semantic coherence from quantitative, qualitative, and user study perspectives. To intuitively showcase scalability, we curate EmoArt, a large-scale dataset of emotionally evocative artistic images, providing endless inspiration for emotion-driven artistic creation. The dataset and code are available at https://github.com/yuankaishen2001/CoEmoGen.

cs.CV↗