arXiv subjects

Xiaohan Zhang

Publications and source records attributed to Xiaohan Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

RefCaptioner: Multi-Reference Image-Grounded Video Captioning

Existing video captioning models generate natural descriptions of video content but cannot explicitly ground local visual elements to multiple reference images. We introduce multi-reference image-grounded video captioning, a new task requiring factual video descriptions with phrase-level reference grounding, and propose RefCaptioner, a two-stage post-training framework for this task. RefCaptioner combines mixed-data SFT with Hierarchical Coverage-Discounted GRPO to jointly improve reference selection, phrase-level binding, distractor rejection, and cross-reference consistency while preserving general video-captioning ability. To support training, we construct a corpus containing $20,000$ videos and 171,354 reference images. We further introduce MRVBench, a benchmark for evaluating caption factuality and multi-reference grounding on both real-world and AI-generated videos. Experiments show that RefCaptioner achieves the best overall performance among the open-source models while remaining competitive on standard video captioning benchmarks. Human evaluation further confirms that its captions are preferred by annotators and enable more source-faithful video reconstruction with both open-source and proprietary video generators.

cs.CV↗

arXiv2026

CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-Centric 3D Scene Generation

Challenges remain in ego-centric 3D scene generation due to limited view overlap and the dominant influence of individual perspectives on scene interpretation. These factors hinder the creation of viewpoint-consistent and semantically aligned visual content, as well as the construction of accurate geometric structures. In this paper, we propose CGGS, a text-to-3D framework aiming to enhance 3D-content-awareness and address geometric distortions in ego-centric scene generation. Firstly, the Ego-centric Generator is proposed by fine-tuning a Multi-View Latent Diffusion Model with consistency-augmented loss to generate consistent, high-fidelity 2D content aligned with textual descriptions. Then, Layout Decorator leverages optical flow and point-track correspondence to estimate depth, therefore producing dense point clouds as coarse layouts from the ego-centric 2D priors. Building on this initialization, Geometric Refiner is proposed to enhance 3D Gaussian reconstruction via an entropy-based Mutual Information Depth Loss (MID) combined with a hierarchical optimization scheme for improving visual quality and geometric structure. Comprehensive experiments demonstrate that CGGS outperforms previous methods in generating coherent and accurate text-driven 3D scenes.

cs.GR↗

arXiv2026

MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation

Multi-reference-to-audio-video (MR2AV) generation aims to generate coherent audio-video content conditioned on multiple references and textual instructions. Existing benchmarks mainly focus on text-driven generation, single-reference subject preservation, or isolated audio-video alignment, leaving the emerging MR2AV setting largely unexplored. Compared with these settings, MR2AV requires models to jointly reason over multiple references while generating synchronized visual and audio content. Models must not only preserve each reference faithfully but also correctly bind and compose multiple referenced entities into coherent audio-visual events. To address this gap, we introduce MultiRef-Compass, a unified benchmark for MR2AV generation. It comprises $350$ carefully curated samples constructed through a scalable and controllable asset-composition pipeline, covering multi-view subject preservation, multi-entity binding, and human-object-scene composition. To provide interpretable assessment, MultiRef-Compass defines an evaluation protocol with four dimensions: Basic Quality, Reference Consistency, Audio-Visual Consistency, and Instruction Following, using 14 sub-metrics. MultiRef-Compass integrates automatic metrics with a rejudging-enhanced MLLM-as-a-Judge framework, enabling scalable and auditable evaluation of both perceptual fidelity and reference-conditioned composition. Extensive experiments on eight representative MR2AV systems reveal substantial room for improvement across multiple evaluation dimensions, underscoring the need for a comprehensive benchmark and positioning MultiRef-Compass as a foundation for future MR2AV research.

cs.CV↗

arXiv2026

KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation

Video generation increasingly relies on keyframe-based workflows, where creators specify a sequence of reference images to guide generation. Although recent models support multi-keyframe conditioning, it remains unclear whether they can faithfully reproduce the prescribed keyframes while maintaining overall video quality. We present KeyFrame-Compass, the first comprehensive benchmark for evaluating keyframe-conditioned video generation. The benchmark contains 386 carefully curated samples spanning three application domains, two video structures, two prompt granularities, two conditioning formats, and four keyframe densities, enabling controlled analysis under diverse generation settings. We further introduce an automated evaluation framework that jointly measures keyframe execution and overall video quality. Specifically, we decompose keyframe execution into six complementary metrics covering presence, fidelity, temporal ordering, localization, persistence, and uniqueness, while assessing overall video quality through evidence-grounded MLLM judgments augmented with specialized perception models. Experiments on nine representative video generation systems reveal several fundamental limitations. Current models exhibit a clear trade-off between faithful keyframe execution and natural video synthesis. Their performance further degrades as keyframe constraints become denser and most open-source models also fail to interpret storyboard-grid inputs as temporally ordered keyframe sequences.

cs.CV↗

arXiv2026

MoLingo: Motion-Language Alignment for Text-to-Human Motion Generation

We introduce MoLingo, a text-to-motion (T2M) model that generates realistic, lifelike human motion by denoising in a continuous latent space. Recent works perform latent space diffusion, either on the whole latent at once or auto-regressively over multiple latents. In this paper, we study how to make diffusion on continuous motion latents work best. We focus on two questions: (1) how to build a semantically aligned latent space so diffusion becomes more effective, and (2) how to best inject text conditioning so the motion follows the description closely. We propose a semantic-aligned motion encoder trained with frame-level text labels so that latents with similar text meaning stay close, which makes the latent space more diffusion-friendly. We also compare single-token conditioning with a multi-token cross-attention scheme and find that cross-attention gives better motion realism and text-motion alignment. With semantically aligned latents, auto-regressive generation, and cross-attention text conditioning, our model sets a new state of the art in human motion generation on standard metrics and in a user study. We will release our code and models for further research and downstream usage.

cs.CV↗

arXiv2026

GIRAF: Towards Generalizable Human Interactions with Articulated Objects

Synthesizing realistic full-body human interactions with articulated objects is a fundamental challenge for embodied AI and graphics, with applications in robotics training and virtual agents. Existing models remain limited: some focus on simple activities with static objects, while others restrict attention to hand-only manipulation. This leaves open the problem of generating coordinated full-body motion that approaches, manipulates, and moves articulated objects in a realistic and generalizable way. The key difficulty lies in reasoning jointly about locomotion, fine-grained contact, and object articulation. Models must capture subtle hand-object correspondences that transfer across object geometries, while also producing seamless transitions from navigation to manipulation. At the same time, the scarcity of large-scale paired motion-scene data makes it difficult to generalize across diverse object positions and shapes. We introduce a text-conditioned diffusion model that addresses these challenges through three core ideas: an object-centric representation that unifies hand-object contact with object surfaces, a mixed-domain training strategy that balances locomotion and interaction, and a contact-based augmentation scheme that expands training diversity. Through experiments, our method demonstrated strong generalization to unseen object configurations, surpassing current state-of-the-art methods.

cs.CV↗

arXiv2026

FairFlow: Demystifying and Mitigating Stereotype Bias in Text-to-Image Diffusion Transformers

Multimodal diffusion transformers (MM-DiTs) have emerged as the prevalent backbone for modern text-to-image generation systems. However, they exhibit critical alignment vulnerabilities, systematically manifesting severe stereotype biases even under benign prompts. This poses a significant risk of algorithmic discrimination in deployed systems. Since most existing mitigation strategies were tailored for legacy U-Net architectures, the precise remediation of these vulnerabilities in MM-DiTs remains a critical open challenge. In this work, we first investigate the root cause of this vulnerability via mechanistic analysis. We reveal that bias representations in MM-DiTs are not uniformly distributed across depth, but are mediated by a sparse set of layers functioning as internal semantic binding hubs. These hubs exhibit a stage-wise propagation driving bias manifestation: early hubs establish the structural templates susceptible to bias, middle hubs actively extract core stereotypical concepts from textual conditioning, and late hubs globally solidify these biases through visual self-attention. Leveraging these architectural insights, we propose FairFlow, an intrinsic, mechanism-guided mitigation framework. FairFlow acts as an internal regulator by employing sparse steering: it learns attribute-specific fair directions and injects them exclusively at the identified semantic hubs within a constrained inference window. Evaluations on FLUX.1-dev and Stable Diffusion~3 demonstrate that FairFlow effectively neutralizes these stereotypical vulnerabilities across gender, race, and intersectional settings, achieving an optimal fairness-fidelity balance. With near-zero inference overhead and robustness to complex prompts, FairFlow provides a lightweight and practical bias mitigation for large-scale deployed MM-DiT systems. Code and datasets will be publicly released upon acceptance.

cs.CV↗

arXiv2026

Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors

Bridging the sim-to-real gap is a core challenge in deploying learned manipulation policies. Sim-to-real learning is attractive because it can replace expensive real robot demonstrations with scalable synthetic data, yet world-action models have not previously been shown to transfer from simulation to real robotic manipulation. We study whether a world-action model can be trained from synthetic priors and deployed zero-shot in the real world. To this end, we build upon Cosmos Policy, a video diffusion model adapted for visuomotor control. We construct simulation environments with extensive domain randomization and generate demonstrations using the AnyTask motion planning pipeline. We evaluate our approach across object lifting, drawer opening, and pick-and-place tasks using ${\sim}800$ synthetic demonstrations per task and no real demonstrations. When deployed zero-shot on a Franka Robot, our policy attains a 35\% average success rate. To our knowledge, this represents the first successful sim-to-real transfer of a world-action model for robotic manipulation.

cs.RO↗

arXiv2026

Scaling Short-Term Memory of Visuomotor Policies for Long-Horizon Tasks

Many robotic tasks require short-term memory, whether it's retrieving an object that's no longer visible or turning off an appliance after a set period. Yet, most visuomotor policies trained via imitation learning rely only on immediate sensory input without using past experiences to guide decisions. We present PRISM, a transformer-based architecture for visuomotor policies to effectively use short-term memory via two key components: (i) gated attention, which filters retrieved information to suppress irrelevant details, improving performance by reducing the spurious correlations between the history and current action prediction, (ii) a hierarchical architecture that first compresses local information into compact tokens and then integrates them to capture temporally extended dependencies, improving its compute and memory footprint. Together, these mechanisms enable us to scale short-term memory in visuomotor policies for up to two minutes. To systematically evaluate memory in visuomotor control, we introduce ReMemBench -- a benchmark of eight diverse household manipulation tasks spanning four categories of short-term memory -- designed to foster general memory mechanisms rather than siloed, task-specific solutions. PRISM consistently outperforms prior works, including recurrent architectures, transformers, and their variants -- achieving an absolute improvement of 5%--12% over the strongest baseline. On the RoboCasa and LIBERO benchmarks, it achieves absolute improvements of 11%--15% over its no-memory variant and fine-tuned Vision-Language-Action baselines such as GR00T-N1-3B and OpenVLA, despite not leveraging any large-scale pretraining. Together, PRISM and ReMemBench establish a foundation for developing and evaluating short-term memory-augmented visuomotor policies that scale to long-horizon tasks. Additional materials are available at https://shahrutav.github.io/short-term-memory

cs.RO↗

arXiv2026

Agentic Discovery of Non-Canonical Antimicrobial Peptides with AMPGAN v3

Antimicrobial resistance causes to over a million deaths annually. Antimicrobial peptides (AMPs) are a promising solution, but generative AMP models are not yet ready to design peptides with non-natural amino acids and/or chemical modifications, which are essential for real-world peptide drugs. We present AMPGAN v3, a multi-objective conditional GAN that expands the generative vocabulary to D-amino acids and N/C-terminus modifications such as amidation. By separating adversarial and activity-aware supervision across two specialized discriminators, AMPGAN v3 substantially improves training stability and outperforms prior generative AMP models on external classifiers. We validated five candidates spanning three structural classes in vitro; two showed activity against Gram-positive strains, with the best candidate reaching MIC 8 μg/mL against B. subtilis. To support downstream curation, we further present PepCraft, a multi-agent framework for end-to-end AMP discovery in which a Planning Agent orchestrates specialized executors for generation, filtering, and verification. Its prioritization recommendations align with our in vitro outcomes. Together, these contributions let us examine, on a small but real scale, how generative and agentic AI compose in therapeutic peptide discovery. Code: https://github.com/marszzibros/AMPGANv3

q-bio.QM↗

arXiv2026

State-dependent broadband X-ray Timing Reconfiguration in the Changing-look AGN NGC 1566

NGC 1566 has shown dramatic X-ray spectral changes during its recent changing-look outburst, but the evolution of its broadband X-ray timing properties remains poorly constrained. We combine long-term Swift/XRT monitoring with high-time-resolution XMM-Newton observations to construct one pre-outburst Dim broadband PSD and two outburst broadband reconstructions associated with the O1 peak and O2 decay observations. In the outburst reconstructions, the same Swift/XRT up-state monitoring segment provides the low-frequency constraint, while the O1 and O2 XMM-Newton observations provide phase-specific high-frequency constraints. Using PSRESP forward modelling with the observed sampling windows, we test bending-power-law PSD models in the soft (0.3-2 keV) and hard (2-10 keV) bands. The Dim and O2-associated reconstructions are acceptably described by bending-power-law solutions, whereas the O1 peak observation does not yield a robust bend-frequency measurement. For the accepted Dim and O2-associated solutions, the preferred bend frequency shifts from about 2.0 x 10^-5 to about 2.7 x 10^-7 Hz in the soft band, and from about 2.1 x 10^-5 to about 2.7 x 10^-7 Hz in the hard band, implying a substantially longer characteristic variability timescale in the O2-associated reconstruction. This consistent shift in both energy bands suggests that the timing evolution is not confined to the soft-excess component alone, but reflects a broader change in the X-ray variability structure. Together with previous spectral studies, these results point to a transient reconfiguration of the disc-corona variability timescale during the changing-look transition in NGC 1566.

astro-ph.HE↗

arXiv2026

Description-Code Inconsistency in Real-world MCP Servers: Measurement, Detection, and Security Implications

The Model Context Protocol (MCP) has emerged as a critical standard empowering Large Language Models (LLMs) to utilize external tools. In this ecosystem, LLMs rely on natural language descriptions provided by MCP servers to select and execute functions. This interaction implicitly assumes that tool descriptions faithfully reflect their underlying implementations, while this assumption is not mandatorily verified in practice. As a result, MCP deployments may suffer from a problem named Description-Code Inconsistency (DCI), where a tool's description of its capabilities and security boundaries is not consistent with what the code actually does. In this paper, we present a comprehensive study of DCI in real-world MCP servers. We formally define the problem and propose a comprehensive taxonomy spanning functionality inconsistencies and undeclared side effects. Guided by this taxonomy, we develop DCIChecker, an automated framework that combines structure-aware static analysis with the Direct-Reverse-Arbitration prompting method to cross-validate tool descriptions against actual code implementations. We apply this framework to a large-scale dataset comprising 19,200 description-code pairs extracted from 2,214 real-world MCP servers. Our measurement reveals that DCI is widespread, with 9.93% of these pairs exhibiting inconsistencies. We further demonstrate that DCI creates a critical defense blind spot, facilitating varied risks from operational failures to stealthy malicious behaviors. Finally, we propose mitigation strategies to enforce semantic consistency and enhance the reliability of the emerging agentic ecosystem.

cs.CR↗

arXiv2026

Can LLM Agents Sustain Long-Horizon Organizational Dynamics?

Large language agents are increasingly used for social simulation, yet it remains unclear whether they can sustain coherent behavior in structured organizations, where goals must propagate through hierarchy, tasks depend on prior execution, and artifacts accumulate over long horizons. We formulate long-horizon organizational simulation as a memory-centered coordination problem and introduce TaskWeave, a hierarchical agentic framework that maintains planning states through a Formulate-Partition-Diagnose-Align cycle and grounds execution through dependency-aware trace memory. We evaluate TaskWeave in a year-long IT company simulation and compare it with other multi-agent frameworks on organizational coherence, execution grounding, and downstream enterprise NLP utility. Experiments show that TaskWeave supports coherent and long-horizon organizational dynamics while producing grounded artifacts and adapting to external environments. These findings suggest that structured simulation memory is a key mechanism for building reliable LLM-based organizational simulators.

cs.AI↗

arXiv2026

LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV

Audio-visual generation is rapidly advancing from short clips to minute-long content, while existing evaluation protocols remain largely confined to short-form settings. Existing benchmarks primarily focus on 5--10 second text-conditioned generation and rarely support unified evaluation across text, image, and video conditioning modalities. Moreover, they provide limited insight into how identity consistency, narrative coherence, and audio-visual alignment degrade over extended temporal horizons. To bridge this gap, we introduce LongAV-Compass, a systematic benchmark for minute-long audio-visual generation. LongAV-Compass contains 284 curated test cases spanning text-to-audio-video (T2AV), image-to-audio-video (I2AV), and video-to-audio-video (V2AV), organized by application scenario and generation complexity. The benchmark combines taxonomy-guided benchmark construction with a unified evaluation framework that integrates MLLM-assisted assessment with complementary perceptual and multimodal metrics, including DINO-v2, ArcFace, CLIP, and ImageBind. The framework evaluates more than 20 fine-grained dimensions covering within-segment quality, cross-segment consistency, global narrative coherence, semantic alignment, and audio-visual synchronization. Through experiments on 11 representative models together with human-alignment validation, LongAV-Compass provides a diagnostic testbed for analyzing the limitations of current systems in sustaining coherent, semantically aligned, and temporally consistent minute-scale audio-visual generation across diverse input modalities.

cs.CV↗

arXiv2026

A First Measurement Study on Authentication Security in Real-World Remote MCP Servers

The Model Context Protocol (MCP) is emerging as a common interface connecting large language models (LLMs) with external services. Remote deployments are becoming increasingly important as agents connect to user-linked online services, such as social, productivity, and financial services. In such deployments, the authentication boundary between MCP clients and remote servers becomes security-critical, yet remains underexplored. We present the first measurement study of authentication security in real-world remote MCP servers. We identify 7,973 live remote MCP servers, finding that 40.55% expose tools without authentication. Among authenticated servers, OAuth is the dominant authorization mechanism for reaching remote services, and OAuth deployments in the MCP ecosystem commonly exhibit three characteristics: open client environments, dynamic client registration, and delegated authorization. These characteristics distinguish MCP deployments from traditional OAuth and introduce new attack surfaces. Guided by this observation, we derive a taxonomy of authentication flaws comprising three MCP-specific categories and conventional OAuth misconfigurations, for a total of four categories and nine concrete flaw types. To evaluate these flaws at scale, we implement a semi-automated detection framework that combines passive traffic inspection with active dynamic probing. Applying it to 119 testable real-world OAuth-enabled MCP servers, we find that each server exhibits at least one flaw, with a total of 325 flaws identified, among which dynamic client registration flaws affect 96.6% of tested servers. Many of these flaws can lead to sensitive information leakage and account takeover. Through responsible disclosure, we obtained 9 CVE IDs. Our findings expose pervasive authentication weaknesses in the MCP ecosystem and underscore the urgent need for hardened OAuth-based remote deployments.

cs.CR↗

arXiv2026

Robot Planning and Situation Handling with Active Perception

Current robots are capable of computing plans to accomplish complex tasks. However, real-world environments are inherently open and dynamic, and unforeseen situations frequently arise during plan execution, such as jamming doors and fallen objects on the floor. These situations may result from the robot's own action failures or from external disturbances, such as human activities. Detecting and handling such execution - time situations remains a significant challenge, limiting those robots' ability to achieve long-term autonomy. In this paper, we develop a planning and situation-handling framework, called VAP-TAMP, that enables robots to actively perceive and address unforeseen situations during plan execution. VAP-TAMP leverages action knowledge to strategically prompt vision-language models for active view selection and situation assessment, while constructing and reasoning over scene graphs for integrated task and motion planning. We evaluated VAP-TAMP using service tasks in simulation and on a mobile manipulation platform.

cs.RO↗

arXiv2026

AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards

Large language models (LLMs) have demonstrated strong potential in agentic tasks, particularly in slide generation. However, slide generation poses a fundamental challenge: the generation process is text-centric, whereas its quality is governed by visual aesthetics. This modality gap leads current models to frequently produce slides with aesthetically suboptimal layouts. Existing solutions typically rely either on heavy visual reflection, which incurs high inference cost yet yields limited gains; or on fine-tuning with large-scale datasets, which still provides weak and indirect aesthetic supervision. In contrast, the explicit use of aesthetic principles as supervision remains unexplored. In this work, we present AeSlides, a reinforcement learning framework with verifiable rewards for Aesthetic layout supervision in Slide generation. We introduce a suite of meticulously designed verifiable metrics to quantify slide layout quality, capturing key layout issues in an accurate, efficient, and low-cost manner. Leveraging these verifiable metrics, we develop a GRPO-based reinforcement learning method that directly optimizes slide generation models for aesthetically coherent layouts. With only 5K training prompts on GLM-4.7-Flash, AeSlides improves aspect ratio compliance from 36% to 85%, while reducing whitespace by 44%, element collisions by 43%, and visual imbalance by 28%. Human evaluation further shows a substantial improvement in overall quality, increasing scores from 3.31 to 3.56 (+7.6%), outperforming both model-based reward optimization and reflection-based agentic approaches, and even edging out Claude-Sonnet-4.5. These results demonstrate that such a verifiable aesthetic paradigm provides an efficient and scalable approach to aligning slide generation with human aesthetic preferences. Our repository is available at https://github.com/ympan0508/aeslides.

cs.CV↗

arXiv2026

DeepFWI: Identifying Bug-Sensitive Warnings with Multi-Modal Code-Warning Semantics

Static analysis tools have evolved over time to assist in detecting bugs. However, the excessive false warnings can impede developers' productivity and confidence in the tools. Previous research efforts have explored learning-based approaches to identify bug warnings. Nevertheless, their coarse granularity, focusing on either long-term warnings or function-level alerts, is insensitive to individual bugs. Also, they rely on manually crafted features or solely on source code semantics, which is inadequate for effective learning. In this paper, we propose DeepFWI, a learning-based approach that identifies bug-sensitive warnings at a fine-grained granularity. Specifically, we design a novel LSTM-based model that captures multi-modal semantics of source code and warnings from automated static analysis tools (ASATs) and highlights their correlations with cross-attention. To tackle the data scarcity of training and evaluation, we collected a large-scale dataset of 280,273 warnings. We conducted extensive experiments on the dataset to evaluate DeepFWI. The experimental results demonstrate the effectiveness of our approach, with an F1-score 67.06% for confirming true warnings in a finer-grained manner, significantly outperforming all baselines. Additionally, to validate the practicality of DeepFWI from the perspective of developers, we applied DeepFWI to four popular open-source projects. Our approach filtered out the vast majority of warnings, while still successfully surfacing 25 true bug-related warnings that were confirmed through manual analysis.

cs.SE↗