Searcharxiv⌕ Search

arXiv subjects

Xilin Chen

Publications and source records attributed to Xilin Chen.

At least 37 records · Page 2Linked to original sources
arXiv2026

What Makes VLMs Robust? Towards Reconciling Robustness and Accuracy in Vision-Language Models

Achieving adversarial robustness in Vision-Language Models (VLMs) inevitably compromises accuracy on clean data, presenting a long-standing and challenging trade-off. In this work, we revisit this trade-off by investigating a fundamental question: What makes VLMs robust? Through a detailed analysis of adversarially fine-tuned models, we examine how robustness mechanisms function internally and how they interact with clean accuracy. Our analysis reveals that adversarial robustness is not uniformly distributed across network depth. Instead, unexpectedly, it is primarily localized within the shallow layers, driven by a low-frequency spectral bias and input-insensitive attention patterns. Meanwhile, updates to the deep layers tend to undermine both clean accuracy and robust generalization. Motivated by these insights, we propose Adversarial Robustness Adaptation (R-Adapt), a simple yet effective framework that freezes all pre-trained weights and introduces minimal, insight-driven adaptations only in the initial layers. This design achieves an exceptional balance between adversarial robustness and clean accuracy. R-Adapt further supports training-free, model-guided, and data-driven paradigms, offering flexible pathways to seamlessly equip standard models with robustness. Extensive evaluations on 18 datasets and diverse tasks demonstrate our state-of-the-art performance under various attacks. Notably, R-Adapt generalizes efficiently to large vision-language models (e.g., LLaVA and Qwen-VL) to enhance their robustness. Our project page is available at https://summu77.github.io/R-Adapt.

cs.CV↗
arXiv2026

Component-Based Out-of-Distribution Detection

Out-of-Distribution (OOD) detection requires sensitivity to subtle shifts without overreacting to natural In-Distribution (ID) diversity. However, from the viewpoint of detection granularity, global representation inevitably suppress local OOD cues, while patch-based methods are unstable due to entangled spurious-correlation and noise. And neither them is effective in detecting compositional OODs composed of valid ID components. Inspired by recognition-by-components theory, we present a training-free Component-Based OOD Detection (CoOD) framework that addresses the existing limitations by decomposing inputs into functional components. To instantiate CoOD, we derive Component Shift Score (CSS) to detect local appearance shifts, and Compositional Consistency Score (CCS) to identify cross-component compositional inconsistencies. Empirically, CoOD achieves consistent improvements on both coarse- and fine-grained OOD detection.

cs.CV↗
arXiv2026

EgoMotion: Hierarchical Reasoning and Diffusion for Egocentric Vision-Language Motion Generation

Faithfully modeling human behavior in dynamic environments is a foundational challenge for embodied intelligence. While conditional motion synthesis has achieved significant advances, egocentric motion generation remains largely underexplored due to the inherent complexity of first-person perception. In this work, we investigate Egocentric Vision-Language (Ego-VL) motion generation. This task requires synthesizing 3D human motion conditioned jointly on first-person visual observations and natural language instructions. We identify a critical \textit{reasoning-generation entanglement} challenge: the simultaneous optimization of semantic reasoning and kinematic modeling introduces gradient conflicts. These conflicts systematically degrade the fidelity of multimodal grounding and motion quality. To address this challenge, we propose a hierarchical generative framework \textbf{EgoMotion}. Inspired by the biological decoupling of cognitive reasoning and motor control, EgoMotion operates in two stages. In the Cognitive Reasoning stage, A vision-language model (VLM) projects multimodal inputs into a structured space of discrete motion primitives. This forces the VLM to acquire goal-consistent representations, effectively bridging the semantic gap between high-level perceptual understanding and low-level action execution. In the Motion Generation stage, these learned representations serve as expressive conditioning signals for a diffusion-based motion generator. By performing iterative denoising within a continuous latent space, the generator synthesizes physically plausible and temporally coherent trajectories. Extensive evaluations demonstrate that EgoMotion achieves state-of-the-art performance, and produces motion sequences that are both semantically grounded and kinematically superior to existing approaches.

cs.CV↗
arXiv2026

GEAR: GEometry-motion Alternating Refinement for Articulated Object Modeling with Gaussian Splatting

High-fidelity interactive digital assets are essential for embodied intelligence and robotic interaction, yet articulated objects remain challenging to reconstruct due to their complex structures and coupled geometry-motion relationships. Existing methods suffer from instability in geometry-motion joint optimization, while their generalization remains limited on complex multi-joint or out-of-distribution objects. To address these challenges, we propose GEAR, an EM-style alternating optimization framework that jointly models geometry and motion as interdependent components within a Gaussian Splatting representation. GEAR treats part segmentation as a latent variable and joint motion parameters as explicit variables, alternately refining them for improved convergence and geometric-motion consistency. To enhance part segmentation quality without sacrificing generalization, we leverage a vanilla 2D segmentation model to provide multi-view part priors, and employ a weakly supervised constraint to regularize the latent variable. Experiments on multiple benchmarks and our newly constructed dataset GEAR-Multi demonstrate that GEAR achieves state-of-the-art results in geometric reconstruction and motion parameters estimation, particularly on complex articulated objects with multiple movable parts.

cs.CV↗
arXiv2026

MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models

The rapid integration of Large Vision-Language Models (LVLMs) into critical domains necessitates comprehensive moral evaluation to ensure their alignment with human values. While extensive research has addressed moral evaluation in LLMs, text-centric assessments cannot adequately capture the complex contextual nuances and ambiguities introduced by visual modalities. To bridge this gap, we introduce MM-MoralBench, a multimodal moral evaluation benchmark grounded in Moral Foundations Theory. We construct unique multimodal scenarios by combining synthesized visual contexts with character dialogues to simulate real-world dilemmas where visual and linguistic information interact dynamically. Our benchmark assesses models across six moral foundations through moral judgment, classification, and response tasks. Extensive evaluations of over 20 LVLMs reveal that models exhibit pronounced moral alignment bias, diverging significantly from human consensus. Furthermore, our analysis indicates that general scaling or structural improvements yield diminishing returns in moral alignment, and thinking paradigm may trigger overthinking-induced failures in moral contexts, highlighting the necessity for targeted moral alignment strategies. Our benchmark is publicly available.

cs.CV↗
arXiv2026

VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model

The emergence of Large Vision-Language Models (LVLMs) marks significant strides towards achieving general artificial intelligence. However, these advancements are accompanied by concerns about biased outputs, a challenge that has yet to be thoroughly explored. Existing benchmarks are not sufficiently comprehensive in evaluating biases due to their limited data scale, single questioning format and narrow sources of bias. To address this problem, we introduce VLBiasBench, a comprehensive benchmark designed to evaluate biases in LVLMs. VLBiasBench, features a dataset that covers nine distinct categories of social biases, including age, disability status, gender, nationality, physical appearance, race, religion, profession, social economic status, as well as two intersectional bias categories: race x gender and race x social economic status. To build a large-scale dataset, we use Stable Diffusion XL model to generate 46,848 high-quality images, which are combined with various questions to creat 128,342 samples. These questions are divided into open-ended and close-ended types, ensuring thorough consideration of bias sources and a comprehensive evaluation of LVLM biases from multiple perspectives. We conduct extensive evaluations on 15 open-source models as well as two advanced closed-source models, yielding new insights into the biases present in these models. Our benchmark is available at https://github.com/Xiangkui-Cao/VLBiasBench.

cs.CV↗
arXiv2026

ACT Now: Preempting LVLM Hallucinations via Adaptive Context Integration

Large Vision-Language Models (LVLMs) frequently suffer from severe hallucination issues. Existing mitigation strategies predominantly rely on isolated, single-step states to enhance visual focus or suppress strong linguistic priors. However, these static approaches neglect dynamic context changes across the generation process and struggles to correct inherited information loss. To address this limitation, we propose Adaptive Context inTegration (ACT), a training-free inference intervention method that mitigates hallucination through the adaptive integration of contextual information. Specifically, we first propose visual context exploration, which leverages spatio-temporal profiling to adaptively amplify attention heads responsible for visual exploration. To further facilitate vision-language alignment, we propose semantic context aggregation that marginalizes potential semantic queries to effectively aggregate visual evidence, thereby resolving the information loss caused by the discrete nature of token prediction. Extensive experiments across diverse LVLMs demonstrate that ACT significantly reduces hallucinations and achieves competitive results on both discriminative and generative benchmarks, acting as a robust and highly adaptable solution without compromising fundamental generation capabilities.

cs.CV↗
arXiv2026

INFACT: A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video-LLMs

Despite rapid progress, Video Large Language Models (Video-LLMs) remain unreliable due to hallucinations, which are outputs that contradict either video evidence (faithfulness) or verifiable world knowledge (factuality). Existing benchmarks provide limited coverage of factuality hallucinations and predominantly evaluate models only in clean settings. We introduce \textsc{INFACT}, a diagnostic benchmark comprising 9{,}800 QA instances with fine-grained taxonomies for faithfulness and factuality, spanning real and synthetic videos. \textsc{INFACT} evaluates models in four modes: Base (clean), Visual Degradation, Evidence Corruption, and Temporal Intervention for order-sensitive items. Reliability under induced modes is quantified using Resist Rate (RR) and Temporal Sensitivity Score (TSS). Experiments on 14 representative Video-LLMs reveal that higher Base-mode accuracy does not reliably translate to higher reliability in the induced modes, with evidence corruption reducing stability and temporal intervention yielding the largest degradation. Notably, many open-source baselines exhibit near-zero TSS on factuality, indicating pronounced temporal inertia on order-sensitive questions.

cs.CV↗
arXiv2026

A Survey on Interpretability in Visual Recognition

Visual recognition models have achieved unprecedented success in various tasks. While researchers aim to understand the underlying mechanisms of these models, the growing demand for deployment in safety-critical areas like autonomous driving and medical diagnostics has accelerated the development of eXplainable AI (XAI). Distinct from generic XAI, visual recognition XAI is positioned at the intersection of vision and language, which represent the two most fundamental human modalities and form the cornerstones of multimodal intelligence. This paper provides a systematic survey of XAI in visual recognition by establishing a multi-dimensional taxonomy from a human-centered perspective based on intent, object, presentation, and methodology. Beyond categorization, we summarize critical evaluation desiderata and metrics, conducting an extensive qualitative assessment across different categories and demonstrating quantitative benchmarks within specific dimensions. Furthermore, we explore the interpretability of Multimodal Large Language Models and practical applications, identifying emerging trends and opportunities. By synthesizing these diverse perspectives, this survey provides an insightful roadmap to inspire future research on the interpretability of visual recognition models.

cs.CV↗
arXiv2026

V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs

Adversarial attacks have evolved from simply disrupting predictions on conventional task-specific models to the more complex goal of manipulating image semantics on Large Vision-Language Models (LVLMs). However, existing methods struggle with controllability and fail to precisely manipulate the semantics of specific concepts in the image. We attribute this limitation to semantic entanglement in the patch-token representations on which adversarial attacks typically operate: global context aggregated by self-attention in the vision encoder dominates individual patch features, making them unreliable handles for precise local semantic manipulation. Our systematic investigation reveals a key insight: value features (V) computed within the transformer attention block serve as much more precise handles for manipulation. We show that V suppresses global-context channels, allowing it to retain high-entropy, disentangled local semantic information. Building on this discovery, we propose V-Attack, a novel method designed for precise local semantic attacks. V-Attack targets the value features and introduces two core components: (1) a Self-Value Enhancement module to refine V's intrinsic semantic richness, and (2) a Text-Guided Value Manipulation module that leverages text prompts to locate source concept and optimize it toward a target concept. By bypassing the entangled patch features, V-Attack achieves highly effective semantic control. Extensive experiments across diverse LVLMs, including LLaVA, InternVL, DeepseekVL and GPT-4o, show that V-Attack improves the attack success rate by an average of 36% over state-of-the-art methods, exposing critical vulnerabilities in modern visual-language understanding. Our code and data are available https://github.com/Summu77/V-Attack.

cs.CV↗
arXiv2026

From Semantics to Pixels: Coarse-to-Fine Masked Autoencoders for Hierarchical Visual Understanding

Self-supervised visual pre-training methods face an inherent tension: contrastive learning (CL) captures global semantics but loses fine-grained detail, while masked image modeling (MIM) preserves local textures but suffers from "attention drift" due to semantically-agnostic random masking. We propose C2FMAE, a coarse-to-fine masked autoencoder that resolves this tension by explicitly learning hierarchical visual representations across three data granularities: semantic masks (scene-level), instance masks (object-level), and RGB images (pixel-level). Two synergistic innovations enforce a strict top-down learning principle. First, a cascaded decoder sequentially reconstructs from scene semantics to object instances to pixel details, establishing explicit cross-granularity dependencies that parallel decoders cannot capture. Second, a progressive masking curriculum dynamically shifts the training focus from semantic-guided to instance-guided and finally to random masking, creating a structured learning path from global context to local features. To support this framework, we construct a large-scale multi-granular dataset with high-quality pseudo-labels for all 1.28M ImageNet-1K images. Extensive experiments show that C2FMAE achieves significant performance gains on image classification, object detection, and semantic segmentation, validating the effectiveness of our hierarchical design in learning more robust and generalizable representations.

cs.CV↗
arXiv2026

RoboPCA: Pose-centered Affordance Learning from Human Demonstrations for Robot Manipulation

Understanding spatial affordances -- comprising the contact regions of object interaction and the corresponding contact poses -- is essential for robots to effectively manipulate objects and accomplish diverse tasks. However, existing spatial affordance prediction methods mainly focus on locating the contact regions while delegating the pose to independent pose estimation approaches, which can lead to task failures due to inconsistencies between predicted contact regions and candidate poses. In this work, we propose RoboPCA, a pose-centered affordance prediction framework that jointly predicts task-appropriate contact regions and poses conditioned on instructions. To enable scalable data collection for pose-centered affordance learning, we devise Human2Afford, a data curation pipeline that automatically recovers scene-level 3D information and infers pose-centered affordance annotations from human demonstrations. With Human2Afford, scene depth and the interaction object's mask are extracted to provide 3D context and object localization, while pose-centered affordance annotations are obtained by tracking object points within the contact region and analyzing hand-object interaction patterns to establish a mapping from the 3D hand mesh to the robot end-effector orientation. By integrating geometry-appearance cues through an RGB-D encoder and incorporating mask-enhanced features to emphasize task-relevant object regions into the diffusion-based framework, RoboPCA outperforms baseline methods on image datasets, simulation, and real robots, and exhibits strong generalization across tasks and categories.

cs.RO↗
arXiv2026

Uni-Skill: Building Self-Evolving Skill Repository for Generalizable Robotic Manipulation

While skill-centric approaches leverage foundation models to enhance generalization in compositional tasks, they often rely on fixed skill libraries, limiting adaptability to new tasks without manual intervention. To address this, we propose Uni-Skill, a Unified Skill-centric framework that supports skill-aware planning and facilitates automatic skill evolution. Unlike prior methods that restrict planning to predefined skills, Uni-Skill requests for new skill implementations when existing ones are insufficient, ensuring adaptable planning with self-augmented skill library. To support automatic implementation of diverse skills requested by the planning module, we construct SkillFolder, a VerbNet-inspired repository derived from large-scale unstructured robotic videos. SkillFolder introduces a hierarchical skill taxonomy that captures diverse skill descriptions at multiple levels of abstraction. By populating this taxonomy with large-scale, automatically annotated demonstrations, Uni-Skill shifts the paradigm of skill acquisition from inefficient manual annotation to efficient offline structural retrieval. Retrieved examples provide semantic supervision over behavior patterns and fine-grained references for spatial trajectories, enabling few-shot skill inference without deployment-time demonstrations. Comprehensive experiments in both simulation and real-world settings verify the state-of-the-art performance of Uni-Skill over existing VLM-based skill-centric approaches, highlighting its advanced reasoning capabilities and strong zero-shot generalization across a wide range of novel tasks.

cs.RO↗
arXiv2026

Multi-PA: A Multi-perspective Benchmark on Privacy Assessment for Large Vision-Language Models

Large Vision-Language Models (LVLMs) exhibit impressive potential across various tasks but also face significant privacy risks, limiting their practical applications. Current researches on privacy assessment for LVLMs is limited in scope, with gaps in both assessment dimensions and privacy categories. To bridge this gap, we propose Multi-PA, a comprehensive benchmark for evaluating the privacy preservation capabilities of LVLMs in terms of privacy awareness and leakage. Privacy awareness measures the model's ability to recognize the privacy sensitivity of input data, while privacy leakage assesses the risk of the model unintentionally disclosing privacy information in its output. We design a range of sub-tasks to thoroughly evaluate the model's privacy protection offered by LVLMs. Multi-PA covers 26 categories of personal privacy, 15 categories of trade secrets, and 18 categories of state secrets, totaling 31,962 samples. Based on Multi-PA, we evaluate the privacy preservation capabilities of 21 open-source and 2 closed-source LVLMs. Our results reveal that current LVLMs generally pose a high risk of facilitating privacy breaches, with vulnerabilities varying across personal privacy, trade secret, and state secret.

cs.CR↗
arXiv2026

Towards Transferable Defense Against Malicious Image Edits

Recent approaches employing imperceptible perturbations in input images have demonstrated promising potential to counter malicious manipulations in diffusion-based image editing systems. However, existing methods suffer from limited transferability in cross-model evaluations. To address this, we propose Transferable Defense Against Malicious Image Edits (TDAE), a novel bimodal framework that enhances image immunity against malicious edits through coordinated image-text optimization. Specifically, at the visual defense level, we introduce FlatGrad Defense Mechanism (FDM), which incorporates gradient regularization into the adversarial objective. By explicitly steering the perturbations toward flat minima, FDM amplifies immune robustness against unseen editing models. For textual enhancement protection, we propose an adversarial optimization paradigm named Dynamic Prompt Defense (DPD), which periodically refines text embeddings to align the editing outcomes of immunized images with those of the original images, then updates the images under optimized embeddings. Through iterative adversarial updates to diverse embeddings, DPD enforces the generation of immunized images that seek a broader set of immunity-enhancing features, thereby achieving cross-model transferability. Extensive experimental results demonstrate that our TDAE achieves state-of-the-art performance in mitigating malicious edits under both intra- and cross-model evaluations.

cs.CV↗
arXiv2026

BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation

Deploying powerful Vision-Language-Action (VLA) models on edge devices is limited by their massive size. In this paper, we take a deployment-oriented view of VLA training: we target efficiency through model design and optimization, rather than relying solely on post-hoc compression. Thus, we propose BitVLA, a fully native 1-bit VLA model for robotic manipulation, where every parameters is ternary, i.e., {-1,0,1}. BitVLA is built on the publicly available 1-bit LLM BitNet b1.58 2B4T, and is trained as a vision-language-action policy that inherits the compactness of 1-bit pretraining while retaining strong task performance. To further reduce the memory footprint of the vision backbone, we introduce Quantize-then-Distill, a post-training quantization-aware training strategy that compresses a full-precision vision encoder to 1.58-bit weights, while a full-precision teacher guides representation alignment during training. Across simulation benchmarks and real-world tasks, BitVLA matches the performance of the full-precision OpenVLA-OFT baseline, while reducing model memory by 11.0x and end-to-end latency by 4.4x. These results suggest a practical path toward training-time efficiency-accuracy co-design for embodied policies, enabling competitive manipulation capability on memory-constrained edge robotic platforms. We release the code in https://github.com/ustcwhy/BitVLA, model weights in https://huggingface.co/lxsy/bitvla-bf16.

cs.RO↗
arXiv2026

Measuring the Measurers: Quality Evaluation of Hallucination Benchmarks for Large Vision-Language Models

Despite the outstanding performance in multimodal tasks, Large Vision-Language Models (LVLMs) have been plagued by the issue of hallucination, i.e., generating content that is inconsistent with the corresponding visual inputs. While previous works have proposed various benchmarks to evaluate this issue, the quality of these evaluations remains unverified. We observe that some of these benchmarks may produce inconsistent evaluation results across repeated tests or fail to align with human evaluation. To address this, we propose a Hallucination benchmark Quality Measurement framework (HQM), which leverages specific indicators to assess both reliability and validity. Our empirical analysis using HQM reveals and pinpoints potential evaluation issues in existing benchmarks, exposing a critical gap in current hallucination evaluation. To bridge this gap, we propose HQH, a High-Quality Hallucination benchmark, which demonstrates superior reliability and validity under HQM, serving as a credible evaluation tool. Our large-scale evaluation of popular LVLMs on HQH reveals severe hallucination problems, which occur not only in the models' main answer to a question but also in additional analysis. This highlights the necessity for future model improvements to effectively mitigate hallucinations and reduce the associated security risks in real-world applications. Our benchmark is publicly available at https://github.com/HQHBench/HQHBench.

cs.CV↗
arXiv2026

MATS: An Audio Language Model under Text-only Supervision

Large audio-language models (LALMs), built upon powerful Large Language Models (LLMs), have exhibited remarkable audio comprehension and reasoning capabilities. However, the training of LALMs demands a large corpus of audio-language pairs, which requires substantial costs in both data collection and training resources. In this paper, we propose \textbf{MATS}, an audio-language multimodal LLM designed to handle \textbf{M}ultiple \textbf{A}udio task using solely \textbf{T}ext-only \textbf{S}upervision. By leveraging pre-trained audio-language alignment models such as CLAP, we develop a text-only training strategy that projects the shared audio-language latent space into LLM latent space, endowing the LLM with audio comprehension capabilities without relying on audio data during training. To further bridge the modality gap between audio and language embeddings within CLAP, we propose the \textbf{S}trongly-rel\textbf{a}ted \textbf{n}oisy \textbf{t}ext with \textbf{a}udio (\textbf{Santa}) mechanism. Santa maps audio embeddings into CLAP language embedding space while preserving essential information from the audio input. Extensive experiments demonstrate that MATS, despite being trained exclusively on text data, achieves competitive performance compared to recent LALMs trained on large-scale audio-language pairs. The code is publicly available in \href{https://github.com/wangwen-banban/MATS}{https://github.com/wangwen-banban/MATS}.

cs.SD↗