arXiv subjects

Yinda Chen

Publications and source records attributed to Yinda Chen.

At least 19 recordsLinked to original sources

arXiv2026

VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing

Understanding how Vision-Language-Action (VLA) models transform multimodal knowledge into embodied control remains an open challenge. We present VLA-Trace, a progressive diagnostic framework that analyzes VLA models through a unified evidence chain from representation dynamics to causal control attribution and behavioral manifestation. It specifically combines cross-modal and checkpoint-drift centered kernel alignment (CKA) to trace representation evolution, attention knockout interventions to identify modality-specific control pathways, and rollout-level behavioral probes to examine grounding, shortcut dependence, and semantic following. Experiments on $π_{0.5}$ and OpenVLA reveal three key findings. First, the two models exhibit distinct modality-specific adaptation dynamics during VLA finetuning. Second, they rely on different multimodal routing strategies and layer-wise dependencies during action decoding. Third, although VLA policies excel at visually grounded trajectory generation, they remain limited in fine-grained semantic following. These findings highlight future directions for representation-preserving adaptation, causal VLA circuits, and compositional semantic control.

cs.AI↗

arXiv2026

What Should a Skill Remember? Quality--Cost Trade-offs in Cost-Aware Skill Rewriting for Language Model Agents

Large language model agents increasingly rely on skills: reusable procedural documents encoding workflows, tool use, implementation patterns, validation checks, and domain rules. Skill rewriting is often treated as prompt compression, but shorter skills can make agents more expensive by removing sparse operational anchors that prevent exploration, debugging, and recovery. We study skill rewriting through this economic lens. Our controlled framework profiles skill structure, rewrites skills using information-preservation strategies, and evaluates the rewrites under fixed task instructions, environments, and verifiers. Experiments on SkillsBench reveal distinct quality--cost trade-offs across strategies: API/code anchoring, workflow guarding, and rule/formula anchoring benefit different task families, with no universally dominant template. In the main held-out evaluation, the learned policy reduces total cost by 7.0% and downstream agent-token cost by 6.0%; in frozen cross-model transfer, the corresponding reductions average 14.7% and 13.7%, while verifier quality is preserved. These results position skill design as cost-aware operational knowledge engineering rather than prompt compression. Resources: https://github.com/1Reminding/Skill_EE.

cs.CL↗

arXiv2026

Pelican-VLA 0.5: Attending Before Acting Benefits Generalization

In this report, we present Pelican-VLA 0.5, a unified VLA model that integrates vision-language understanding, future-frame generation, and action prediction within a single architecture. Pelican-VLA 0.5 achieves attention-level generalization: without object annotations, segmentation masks, attention supervision, or task-specific fine-tuning, its action pathway already focuses on the manipulation-relevant object and contact region. This behavior persists across unseen scenes and unseen robot embodiments, and is substantially stronger than in other open-source VLA baselines. We verify that this ability originates from the learnable Bottleneck Token inserted between perception and action: by routing task-relevant visual information through a compact bottleneck, the tokens interface induces manipulation-centric attention during pre-training and remains effective across different policy structures, including a MoT-style architecture.

cs.RO↗

arXiv2026

Holo-World: Unified Camera, Object and Weather Control for Video World Model

Video world models are moving toward preserving an observed world under controllable camera and object motion while allowing its environmental state to change. Yet these controls remain isolated, and weather generation typically relies on a source video or reconstructed scene that already specifies future structure. We study a first-frame-anchored source-to-state setting, where the model starts from a single image and follows explicit camera and object controls and an optional weather instruction, then generates a video that either preserves the source world or transfers it to a target weather state. To address these challenges, we first build HoloStateData, a state video dataset that turns diverse videos into unified control samples for camera, object, and weather supervision. Second, we introduce Holo-World, a unified controllable video world model that jointly controls the scene from a single image. Its Unified Scene Adapter factorizes world preservation and weather transfer into distinct parameter subspaces, using rendered background, geometry buffers, and object controls to maintain controlled scene structure while modeling weather-dependent appearance and particle effects. Additionally, Scene-Weather Decomposed CFG guides scene and weather residuals separately, strengthening target weather effects without over-amplifying the full condition. Quantitative and qualitative experiments demonstrate that Holo-World maintains precise camera and object controls with consistent scene structure while transferring scenes into diverse target weather states, outperforming video-to-video weather editing baselines on weather-state generation. Our project page is available at https://xiangchenyin.github.io/Holo-World/

cs.CV↗

arXiv2026

Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation

Lightweight 3D medical image segmentation remains constrained by a fundamental \textit{``efficiency / robustness conflict''}, particularly when processing complex anatomical structures and heterogeneous modalities. In this paper, we study how to redesign the framework based on the characteristics of high-dimensional 3D images, and explore data synergy to overcome the fragile representation of lightweight methods. Our approach, VeloxSeg, begins with a deployable and extensible dual-stream CNN-Transformer architecture composed of Paired Window Attention (PWA) and Johnson-Lindenstrauss lemma-guided convolution (JLC). For each 3D image, we invoke a ``glance-and-focus'' principle, where PWA rapidly retrieves multi-scale information, and JLC ensures robust local feature extraction with minimal parameters, significantly enhancing the model's ability to operate with low computational budget. Followed by an extension of the dual-stream architecture that incorporates modal interaction into the multi-scale image-retrieval process, VeloxSeg efficiently models heterogeneous modalities. Finally, Spatially Decoupled Knowledge Transfer (SDKT) via Gram matrices injects the texture prior extracted by a self-supervised network into the segmentation network, yielding stronger representations than baselines at no extra inference cost. Experimental results on multimodal benchmarks show that VeloxSeg achieves a 26\% Dice improvement, alongside increasing GPU throughput by 11$\times$, CPU by 48$\times$, and reducing training peak GPU memory usage by $1/20$, inference by $1/24$. Code is available at https://github.com/JinPLu/VeloxSeg.

cs.CV↗

arXiv2026

Current World Models Lack a Persistent State Core

World models are increasingly regarded as a decisive step toward artificial general intelligence, yet modeling the physical world demands more than rendering convincing frames on demand: it requires an internal world state that keeps evolving over time, decoupled from observation, so that objects endure and events run to their conclusions whether or not a camera is watching, much as the moon holds to its orbit when no one is looking. This requirement is a blind spot of existing benchmarks, which reward surface properties such as fidelity, motion, and camera controllability while never asking whether a generated world keeps evolving once it is unobserved. We introduce \textbf{WRBench}, the first systematic diagnostic benchmark that treats camera motion as an intervention on observability and resolves evaluation into a human-calibrated chain that asks whether the camera executes the requested interaction, whether the scene stays continuous and identifiable while in view, and whether a returning target remains consistent with the event that was set in motion. Across 9{,}600 videos from 23 models spanning four control paradigms, one finding proves stubborn: current systems maintain the observed world as a tracking shot, resuming a returning target in the state at which it was abandoned rather than advancing the event while it went unseen. Because this failure recurs across control paradigms, model families, and increments of scale, robust world-state evolution does not follow from cleaner imagery, tighter control, richer geometric priors, or sheer parameter count We therefore argue that the stability of the physical state kernel and the consistency of worldlines under viewpoint intervention should become first-class objectives of world-model design, so that a world model captures how the world will unfold rather than how the next frame appears.

cs.CV↗

arXiv2026

Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models

While Diffusion Large Language Models (dLLMs) offer structural advantages for global planning, efficiently verifying that they arrive at correct answers via valid reasoning traces remains a critical challenge. In this work, we propose a geometric perspective: Reasoning on the Manifold. We hypothesize that valid generation trajectories reside as stable attractors on the high-density manifold of the learned distribution, whereas invalid paths exhibit off-manifold drift. To operationalize this, we introduce Bidirectional Manifold Consistency (BMC), a training-free, unsupervised metric that quantifies the stability of the generated sequence through a forward-masking and backward-reconstruction cycle. Empirically, we demonstrate BMC's versatility across the full reasoning lifecycle: (1) in Diagnosis, it serves as a robust discriminator of solution validity without ground truth answer; (2) in Inference, it enables rejection resampling to effectively concentrate computational resources on complex reasoning tasks; and (3) in Alignment, it functions as a dense geometric reward that transforms sparse outcome supervision into fine-grained guidance, empowering models to self-evolve beyond standard baselines. Our results establish intrinsic geometric stability as a robust indicator of correctness for dLLMs.

cs.LG↗

arXiv2026

Pelican-Unify 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action

We present Pelican-Unify 1.0, the first embodied foundation model trained according to the principle of unification. Pelican-Unify 1.0 uses a single VLM as a unified understanding module, mapping scenes, instructions, visual contexts, and action histories into a shared semantic space. The same VLM also serves as a unified reasoning module, autoregressively producing task-, action-, and future-oriented chains of thought in a single forward pass and projecting the final hidden state into a dense latent variable. A Unified Future Generator (UFG) then conditions on this latent variable and jointly generates future videos and future actions through two modality-specific output heads within the same denoising process. The language, video, and action losses are all backpropagated into the shared representation, enabling the model to jointly optimize understanding, reasoning, imagination, and action during training, rather than training three isolated expert systems. Experiments demonstrate that unification does not imply compromise. With a single checkpoint, Pelican-Unify 1.0 achieves strong performance across all three capabilities: 64.7 on eight VLM benchmarks, the best among comparable-scale models; 66.03 on WorldArena, ranking first; and 93.5 on RoboTwin, the second-best average among compared action methods. These results show that the unified paradigm succeeds in preserving specialist strength while bringing understanding, reasoning, imagination, and action into one model.

cs.RO↗

arXiv2026

DVP-MVS++: Synergize Depth-Normal-Edge and Harmonized Visibility Prior for Multi-View Stereo

Recently, patch deformation-based methods have demonstrated significant effectiveness in multi-view stereo due to their incorporation of deformable and expandable perception for reconstructing textureless areas. However, these methods generally focus on identifying reliable pixel correlations to mitigate matching ambiguity of patch deformation, while neglecting the deformation instability caused by edge-skipping and visibility occlusions, which may cause potential estimation deviations. To address these issues, we propose DVP-MVS++, an innovative approach that synergizes both depth-normal-edge aligned and harmonized cross-view priors for robust and visibility-aware patch deformation. Specifically, to avoid edge-skipping, we first apply DepthPro, Metric3Dv2 and Roberts operator to generate coarse depth maps, normal maps and edge maps, respectively. These maps are then aligned via an erosion-dilation strategy to produce fine-grained homogeneous boundaries for facilitating robust patch deformation. Moreover, we reformulate view selection weights as visibility maps, and then implement both an enhanced cross-view depth reprojection and an area-maximization strategy to help reliably restore visible areas and effectively balance deformed patch, thus acquiring harmonized cross-view priors for visibility-aware patch deformation. Additionally, we obtain geometry consistency by adopting both aggregated normals via view selection and projection depth differences via epipolar lines, and then employ SHIQ for highlight correction to enable geometry consistency with highlight-aware perception, thus improving reconstruction quality during propagation and refinement stage. Evaluation results on ETH3D, Tanks & Temples and Strecha datasets exhibit the state-of-the-art performance and robust generalization capability of our proposed method.

cs.CV↗

arXiv2026

MAIN-VLA: Modeling Abstraction of Intention and eNvironment for Vision-Language-Action Models

Despite significant progress in Visual-Language-Action (VLA), in highly complex and dynamic environments that involve real-time unpredictable interactions (such as 3D open worlds and large-scale PvP games), existing approaches remain inefficient at extracting action-critical signals from redundant sensor streams. To tackle this, we introduce MAIN-VLA, a framework that explicitly Models the Abstraction of Intention and eNvironment to ground decision-making in deep semantic alignment rather than superficial pattern matching. Specifically, our Intention Abstraction (IA) extracts verbose linguistic instructions and their associated reasoning into compact, explicit semantic primitives, while the Environment Semantics Abstraction (ESA) projects overwhelming visual streams into a structured, topological affordance representation. Furthermore, aligning these two abstract modalities induces an emergent attention-concentration effect, enabling a parameter-free token-pruning strategy that filters out perceptual redundancy without degrading performance. Extensive experiments in open-world Minecraft and large-scale PvP environments (Game for Peace and Valorant) demonstrate that MAIN-VLA sets a new state-of-the-art, which achieves superior decision quality, stronger generalization, and cutting-edge inference efficiency.

cs.CV↗

arXiv2026

Does DINOv3 Set a New Medical Vision Standard? Benchmarking 2D and 3D Classification, Segmentation, and Registration

The advent of large-scale vision foundation models, pre-trained on diverse natural images, has marked a paradigm shift in computer vision. However, how the frontier vision foundation models' efficacies transfer to specialised domains such as medical imaging remains an open question. This report investigates whether DINOv3, a state-of-the-art self-supervised vision transformer (ViT) pre-trained on natural images, can directly serve as a powerful, unified encoder for medical vision tasks without domain-specific fine-tuning. To answer this, we benchmark DINOv3 across common medical vision tasks, including 2D and 3D classification, segmentation, and registration on a wide range of medical imaging modalities. We systematically analyse its scalability by varying model sizes and input image resolutions. Our findings reveal that DINOv3 shows impressive performance and establishes a formidable new baseline. Remarkably, it can even outperform medical-specific foundation models like BiomedCLIP and CT-Net on several tasks, despite being trained solely on natural images. However, we identify clear limitations: The model's features degrade in scenarios requiring deep domain specialisation, such as in whole-slide images (WSIs), electron microscopy (EM), and positron emission tomography (PET). Furthermore, we observe that DINOv3 does not consistently follow the scaling law in the medical domain. Its performance does not reliably increase with larger models or finer feature resolutions, showing diverse scaling behaviours across tasks. Overall, our work establishes DINOv3 as a strong baseline, whose powerful visual features can serve as a robust prior for multiple medical tasks. This opens promising future directions, such as leveraging its features to enforce multiview consistency in 3D reconstruction.

cs.CV↗

arXiv2025

Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving

Vision-Language-Action (VLA) models have recently shown strong decision-making capabilities in autonomous driving. However, existing VLAs often struggle with achieving efficient inference and generalizing to novel autonomous vehicle configurations and driving scenarios. In this paper, we propose Reasoning-VLA, a general and fast action-generation VLA framework. The proposed model employs a set of learnable action queries, initialized via Gaussian sampling from ground-truth trajectories within the training corpus. These learnable queries interact with reasoning-enhanced vision-language features to generate continuous action trajectories in parallel. To promote robust generalization, we consolidate eight publicly available autonomous driving datasets into a standardized, Chain-of-Thought reasoning-based, and easy-to-use data format for model training. Leveraging both supervised learning and reinforcement learning fine-tuning, extensive empirical evaluations across multiple benchmarks demonstrate that Reasoning-VLA achieves state-of-the-art performance, superior generalization capability, and the excellent inference speed reported to date.

cs.CV↗

arXiv2025

CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model

Autonomous driving represents a prominent application of artificial intelligence. Recent approaches have shifted from focusing solely on common scenarios to addressing complex, long-tail situations such as subtle human behaviors, traffic accidents, and non-compliant driving patterns. Given the demonstrated capabilities of large language models (LLMs) in understanding visual and natural language inputs and following instructions, recent methods have integrated LLMs into autonomous driving systems to enhance reasoning, interpretability, and performance across diverse scenarios. However, existing methods typically rely either on real-world data, which is suitable for industrial deployment, or on simulation data tailored to rare or hard case scenarios. Few approaches effectively integrate the complementary advantages of both data sources. To address this limitation, we propose a novel VLM-guided, end-to-end adversarial transfer framework for autonomous driving that transfers long-tail handling capabilities from simulation to real-world deployment, named CoC-VLA. The framework comprises a teacher VLM model, a student VLM model, and a discriminator. Both the teacher and student VLM models utilize a shared base architecture, termed the Chain-of-Causality Visual-Language Model (CoC VLM), which integrates temporal information via an end-to-end text adapter. This architecture supports chain-of-thought reasoning to infer complex driving logic. The teacher and student VLM models are pre-trained separately on simulated and real-world datasets. The discriminator is trained adversarially to facilitate the transfer of long-tail handling capabilities from simulated to real-world environments by the student VLM model, using a novel backpropagation strategy.

cs.RO↗

arXiv2025

FURINA: Free from Unmergeable Router via LINear Aggregation of mixed experts

The Mixture of Experts (MoE) paradigm has been successfully integrated into Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning (PEFT), delivering performance gains with minimal parameter overhead. However, a key limitation of existing MoE-LoRA methods is their reliance on a discrete router, which prevents the integration of the MoE components into the backbone model. To overcome this, we propose FURINA, a novel Free from Unmergeable Router framework based on the LINear Aggregation of experts. FURINA eliminates the router by introducing a Self-Routing mechanism. This is achieved through three core innovations: (1) decoupled learning of the direction and magnitude for LoRA adapters, (2) a shared learnable magnitude vector for consistent activation scaling, and (3) expert selection loss that encourages divergent expert activation. The proposed mechanism leverages the angular similarity between the input and each adapter's directional component to activate experts, which are then scaled by the shared magnitude vector. This design allows the output norm to naturally reflect the importance of each expert, thereby enabling dynamic, router-free routing. The expert selection loss further sharpens this behavior by encouraging sparsity and aligning it with standard MoE activation patterns. We also introduce a shared expert within the MoE-LoRA block that provides stable, foundational knowledge. To the best of our knowledge, FURINA is the first router-free, MoE-enhanced LoRA method that can be fully merged into the backbone model, introducing zero additional inference-time cost or complexity. Extensive experiments demonstrate that FURINA not only significantly outperforms standard LoRA but also matches or surpasses the performance of existing MoE-LoRA methods, while eliminating the extra inference-time overhead of MoE.

cs.CL↗

arXiv2025

TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation

Neuron segmentation from electron microscopy (EM) volumes is crucial for understanding brain circuits, yet the complex neuronal structures in high-resolution EM images present significant challenges. EM data exhibits unique characteristics including high noise levels, anisotropic voxel dimensions, and ultra-long spatial dependencies that make traditional vision models inadequate. Inspired by autoregressive pretraining in language models, we propose TokenUnify, a hierarchical predictive coding framework that captures multi-scale dependencies through three complementary learning objectives. TokenUnify integrates random token prediction, next-token prediction, and next-all token prediction to create a comprehensive representational space with emergent properties. From an information-theoretic perspective, these three tasks are complementary and provide optimal coverage of visual data structure, with our approach reducing autoregressive error accumulation from O(K) to O(sqrt(K)) for sequences of length K. We also introduce a large-scale EM dataset with 1.2 billion annotated voxels, offering ideal long-sequence visual data with spatial continuity. Leveraging the Mamba architecture's linear-time sequence modeling capabilities, TokenUnify achieves a 44% performance improvement on downstream neuron segmentation and outperforms MAE by 25%. Our approach demonstrates superior scaling properties as model size increases, effectively bridging the gap between pretraining strategies for language and vision models.

cs.CV↗

arXiv2025

EMPOWER: Evolutionary Medical Prompt Optimization With Reinforcement Learning

Prompt engineering significantly influences the reliability and clinical utility of Large Language Models (LLMs) in medical applications. Current optimization approaches inadequately address domain-specific medical knowledge and safety requirements. This paper introduces EMPOWER, a novel evolutionary framework that enhances medical prompt quality through specialized representation learning, multi-dimensional evaluation, and structure-preserving algorithms. Our methodology incorporates: (1) a medical terminology attention mechanism, (2) a comprehensive assessment architecture evaluating clarity, specificity, clinical relevance, and factual accuracy, (3) a component-level evolutionary algorithm preserving clinical reasoning integrity, and (4) a semantic verification module ensuring adherence to medical knowledge. Evaluation across diagnostic, therapeutic, and educational tasks demonstrates significant improvements: 24.7% reduction in factually incorrect content, 19.6% enhancement in domain specificity, and 15.3% higher clinician preference in blinded evaluations. The framework addresses critical challenges in developing clinically appropriate prompts, facilitating more responsible integration of LLMs into healthcare settings.

cs.CL↗

arXiv2025

Low-Cost Test-Time Adaptation for Robust Video Editing

Video editing is a critical component of content creation that transforms raw footage into coherent works aligned with specific visual and narrative objectives. Existing approaches face two major challenges: temporal inconsistencies due to failure in capturing complex motion patterns, and overfitting to simple prompts arising from limitations in UNet backbone architectures. While learning-based methods can enhance editing quality, they typically demand substantial computational resources and are constrained by the scarcity of high-quality annotated data. In this paper, we present Vid-TTA, a lightweight test-time adaptation framework that personalizes optimization for each test video during inference through self-supervised auxiliary tasks. Our approach incorporates a motion-aware frame reconstruction mechanism that identifies and preserves crucial movement regions, alongside a prompt perturbation and reconstruction strategy that strengthens model robustness to diverse textual descriptions. These innovations are orchestrated by a meta-learning driven dynamic loss balancing mechanism that adaptively adjusts the optimization process based on video characteristics. Extensive experiments demonstrate that Vid-TTA significantly improves video temporal consistency and mitigates prompt overfitting while maintaining low computational overhead, offering a plug-and-play performance boost for existing video editing models.

cs.CV↗

arXiv2025

Dual form Complementary Masking for Domain-Adaptive Image Segmentation

Recent works have correlated Masked Image Modeling (MIM) with consistency regularization in Unsupervised Domain Adaptation (UDA). However, they merely treat masking as a special form of deformation on the input images and neglect the theoretical analysis, which leads to a superficial understanding of masked reconstruction and insufficient exploitation of its potential in enhancing feature extraction and representation learning. In this paper, we reframe masked reconstruction as a sparse signal reconstruction problem and theoretically prove that the dual form of complementary masks possesses superior capabilities in extracting domain-agnostic image features. Based on this compelling insight, we propose MaskTwins, a simple yet effective UDA framework that integrates masked reconstruction directly into the main training pipeline. MaskTwins uncovers intrinsic structural patterns that persist across disparate domains by enforcing consistency between predictions of images masked in complementary ways, enabling domain generalization in an end-to-end manner. Extensive experiments verify the superiority of MaskTwins over baseline methods in natural and biological image segmentation. These results demonstrate the significant advantages of MaskTwins in extracting domain-invariant features without the need for separate pre-training, offering a new paradigm for domain-adaptive segmentation.

cs.CV↗