arXiv subjects

Yinchuan Li

Publications and source records attributed to Yinchuan Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

Find, Fix, Reason: Context Repair for Video Reasoning

Reinforcement learning has advanced video reasoning in large multi-modal models, yet dominant pipelines either rely on on-policy self-exploration, which plateaus at the model's knowledge boundary, or hybrid replay that mixes policies and demands careful regularization. Dynamic context methods zoom into focused evidence but often require curated pretraining and two-stage tuning, and their context remains bounded by a small model's capability. In contrast, larger models excel at instruction following and multi-modal understanding, can supply richer context to smaller models, and rapidly zoom in on target regions via simple tools. Building on this capability, we introduce an observation-level intervention: a frozen, tool-integrated teacher identifies the missing spatiotemporal dependency and provides a minimal evidence patch (e.g., timestamps, regions etc.) from the original video while the question remains unchanged. The student answers again with the added context, and training updates with a chosen-rollout scheme integrated into Group Relative Policy Optimization (GRPO). We further propose a Robust Improvement Reward (RIR) that aligns optimization with two goals: outcome validity through correct answers and dependency alignment through rationales that reflect the cited evidence. Advantages are group-normalized across the batch, preserving on-policy exploration while directing it along causally meaningful directions with minimal changes to the training stack. Experiments on various related benchmarks show consistent accuracy gains and strong generalization. Code will be available at https://jethrojames.github.io/FFR/.

cs.CV↗

arXiv2026

STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization

Transforming complex actions into discrete skill abstractions has demonstrated strong potential for robotic manipulation. Existing approaches mainly leverage latent variable models, e.g., VQ-VAE, to learn skill abstractions through learned vectors (codebooks), while they suffer from codebook collapse and modeling the causal relationship between learned skills. To address these limitations, we present \textbf{S}kill \textbf{T}raining with \textbf{A}ugmented \textbf{R}otation (\textbf{STAR}), a framework that advances both skill learning and composition to complete complex behaviors. Specifically, to prevent codebook collapse, we devise rotation-augmented residual skill quantization (RaRSQ). It encodes relative angles between encoder outputs into the gradient flow by rotation-based gradient mechanism. Points within the same skill code are forced to be either pushed apart or pulled closer together depending on gradient directions. Further, to capture the causal relationship between skills, we present causal skill transformer (CST) which explicitly models dependencies between skill representations through an autoregressive mechanism for coherent action generation. Extensive experiments demonstrate the superiority of STAR on both LIBERO benchmark and realworld tasks, with around 12\% improvement over the baselines.

cs.RO↗

arXiv2026

Panoramic Affordance Prediction

Affordance prediction serves as a critical bridge between perception and action in embodied AI. However, existing research is confined to pinhole camera models, which suffer from narrow Fields of View (FoV) and fragmented observations, often missing critical holistic environmental context. In this paper, we present the first exploration into Panoramic Affordance Prediction, utilizing 360-degree imagery to capture global spatial relationships and holistic scene understanding. To facilitate this novel task, we first introduce PAP-12K, a large-scale benchmark dataset containing over 1,000 ultra-high-resolution (12k, 11904 x 5952) panoramic images with over 12k carefully annotated QA pairs and affordance masks. Furthermore, we propose PAP, a training-free, coarse-to-fine pipeline inspired by the human foveal visual system to tackle the ultra-high resolution and severe distortion inherent in panoramic images. PAP employs recursive visual routing via grid prompting to progressively locate targets, applies an adaptive gaze mechanism to rectify local geometric distortions, and utilizes a cascaded grounding pipeline to extract precise instance-level masks. Experimental results on PAP-12K reveal that existing affordance prediction methods designed for standard perspective images suffer severe performance degradation and fail due to the unique challenges of panoramic vision. In contrast, PAP framework effectively overcomes these obstacles, significantly outperforming state-of-the-art baselines and highlighting the immense potential of panoramic perception for robust embodied intelligence.

cs.CV↗

arXiv2026

DVD: Deterministic Video Depth Estimation with Generative Priors

Existing video depth estimation faces a fundamental trade-off: generative models suffer from stochastic geometric hallucinations and scale drift, while discriminative models demand massive labeled datasets to resolve semantic ambiguities. To break this impasse, we present DVD, the first framework to deterministically adapt pre-trained video diffusion models into single-pass depth regressors. Specifically, DVD features three core designs: (i) repurposing the diffusion timestep as a structural anchor to balance global stability with high-frequency details; (ii) latent manifold rectification (LMR) to mitigate regression-induced over-smoothing, enforcing differential constraints to restore sharp boundaries and coherent motion; and (iii) global affine coherence, an inherent property bounding inter-window divergence, which enables seamless long-video inference without requiring complex temporal alignment. Extensive experiments demonstrate that DVD achieves state-of-the-art zero-shot performance across benchmarks. Furthermore, DVD successfully unlocks the profound geometric priors implicit in video foundation models using 163x less task-specific data than leading baselines. Notably, we fully release our pipeline, providing the whole training suite for SOTA video depth estimation to benefit the open-source community.

cs.CV↗

arXiv2026

Boosting Cross-problem Generalization in Diffusion-Based Neural Combinatorial Solver via Inference Time Adaptation

Diffusion-based Neural Combinatorial Optimization (NCO) has demonstrated effectiveness in solving NP-complete (NPC) problems by learning discrete diffusion models for solution generation, eliminating hand-crafted domain knowledge. Despite their success, existing NCO methods face significant challenges in both cross-scale and cross-problem generalization, and high training costs compared to traditional solvers. While recent studies on diffusion models have introduced training-free guidance approaches that leverage pre-defined guidance functions for conditional generation, such methodologies have not been extensively explored in combinatorial optimization. To bridge this gap, we propose a training-free inference time adaptation framework (DIFU-Ada) that enables both the zero-shot cross-problem transfer and cross-scale generalization capabilities of diffusion-based NCO solvers without requiring additional training. We provide theoretical analysis that helps understanding the cross-problem transfer capability. Our experimental results demonstrate that a diffusion solver, trained exclusively on the Traveling Salesman Problem (TSP), can achieve competitive zero-shot transfer performance across different problem scales on TSP variants, such as Prize Collecting TSP (PCTSP) and the Orienteering Problem (OP), through inference time adaptation.

cs.LG↗

arXiv2026

Generative Models in Decision Making: A Survey

Generative models have fundamentally reshaped the landscape of decision-making, reframing the problem from pure scalar reward maximization to high-fidelity trajectory generation and distribution matching. This paradigm shift addresses intrinsic limitations in classical Reinforcement Learning (RL), particularly the limited expressivity of standard unimodal policy distributions in capturing complex, multi-modal behaviors embedded in diverse datasets. However, current literature often treats these models as isolated algorithmic improvements, rarely synthesizing them into a single comprehensive framework. This survey proposes a principled taxonomy grounding generative decision-making within the probabilistic framework of Control as Inference. By performing a variational factorization of the trajectory posterior, we conceptualize four distinct functional roles: Controllers for amortized policy inference, Modelers for dynamics priors, Optimizers for iterative trajectory refinement, and Evaluators for trajectory guidance and value assessment. Unlike existing architecture-centric reviews, this function-centric framework allows us to critically analyze representative generative families across distinct dimensions. Furthermore, we examine deployment in high-stakes domains, specifically Embodied AI, Autonomous Driving, and AI for Science, highlighting systemic risks such as dynamics hallucination in world models and proxy exploitation. Finally, we chart the path toward Generalist Physical Intelligence, identifying pivotal challenges in inference efficiency, trustworthiness, and the emergence of Physical Foundation Models.

cs.LG↗

arXiv2026

DeCo: Task Decomposition and Skill Composition for Zero-Shot Generalization in Long-Horizon 3D Manipulation

Generalizing language-conditioned multi-task imitation learning (IL) models to novel long-horizon 3D manipulation tasks is challenging. To address this, we propose DeCo (Task Decomposition and Skill Composition), a model-agnostic framework that enhances zero-shot generalization to compositional long-horizon manipulation tasks. DeCo decomposes IL demonstrations into modular atomic tasks based on gripper-object interactions, creating a dataset that enables models to learn reusable skills. At inference, DeCo uses a vision-language model (VLM) to parse high-level instructions, retrieve relevant skills, and dynamically schedule their execution. A spatially-aware skill-chaining module ensures smooth, collision-free transitions between skills. We introduce DeCoBench, a benchmark designed to evaluate compositional generalization in long-horizon manipulation tasks. DeCo improves the success rate of three IL models, RVT-2, 3DDA, and ARP, by 66.67%, 21.53%, and 57.92%, respectively, on 12 novel tasks. In real-world experiments, the DeCo-enhanced model, trained on only 6 atomic tasks, completes 9 novel tasks in zero-shot, with a 53.33% improvement over the baseline model. Project website: https://deco226.github.io.

cs.RO↗

arXiv2026

Personalized Federated Learning with Bidirectional Communication Compression via One-Bit Random Sketching

Federated Learning (FL) enables collaborative training across decentralized data, but faces key challenges of bidirectional communication overhead and client-side data heterogeneity. To address communication costs while embracing data heterogeneity, we propose pFed1BS, a novel personalized federated learning framework that achieves extreme communication compression through one-bit random sketching. In personalized FL, the goal shifts from training a single global model to creating tailored models for each client. In our framework, clients transmit highly compressed one-bit sketches, and the server aggregates and broadcasts a global one-bit consensus. To enable effective personalization, we introduce a sign-based regularizer that guides local models to align with the global consensus while preserving local data characteristics. To mitigate the computational burden of random sketching, we employ the Fast Hadamard Transform for efficient projection. Theoretical analysis guarantees that our algorithm converges to a stationary neighborhood of the global potential function. Numerical simulations demonstrate that pFed1BS substantially reduces communication costs while achieving competitive performance compared to advanced communication-efficient FL algorithms.

cs.LG↗

arXiv2025

Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO

Direct alignment methods typically train large language models (LLMs) by contrasting the likelihoods of preferred and dispreferred responses. While effective at capturing relative preferences, these methods are widely observed to suppress the absolute likelihoods of example responses. As a result, aligned models can deviate from expected patterns, exhibiting rewar-hacking effect even without an explicit reward model. This fundamental limitation of contrastive alignment, which we term likelihood underdetermination, motivates us to revisit direct preference optimization (DPO) -- the seminal direct alignment method. Interestingly, we show that the DPO loss admits a principled decomposition. The reformulated loss not only extends naturally to a broader range of feedback types, but also unveils the root cause of likelihood underdetermination. Specifically, we identify that standard DPO implicitly oversimplifies a regularizer in the reformulated loss; restoring this full term effectively resolves the underdetermination. Building on these insights, we introduce PRoximalized PReference Optimization (PRO), a unified alignment method that accommodates diverse feedback types while eliminating likelihood underdetermination through an efficient approximation of the full regularizer. Empirical evaluations demonstrate the consistent superiority of PRO over existing methods across pairwise, binary and scalar feedback.

cs.CL↗

arXiv2025

Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising

Diffusion models, such as diffusion policy, have achieved state-of-the-art results in robotic manipulation by imitating expert demonstrations. While diffusion models were originally developed for vision tasks like image and video generation, many of their inference strategies have been directly transferred to control domains without adaptation. In this work, we show that by tailoring the denoising process to the specific characteristics of embodied AI tasks -- particularly structured, low-dimensional nature of action distributions -- diffusion policies can operate effectively with as few as 5 neural function evaluations (NFE). Building on this insight, we propose a population-based sampling strategy, genetic denoising, which enhances both performance and stability by selecting denoising trajectories with low out-of-distribution risk. Our method solves challenging tasks with only 2 NFE while improving or matching performance. We evaluate our approach across 14 robotic manipulation tasks from D4RL and Robomimic, spanning multiple action horizons and inference budgets. In over 2 million evaluations, our method consistently outperforms standard diffusion-based policies, achieving up to 20\% performance gains with significantly fewer inference steps.

cs.RO↗

arXiv2025

PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs

The ability to use, understand, and create tools is a hallmark of human intelligence, enabling sophisticated interaction with the physical world. For any general-purpose intelligent agent to achieve true versatility, it must also master these fundamental skills. While modern Multimodal Large Language Models (MLLMs) leverage their extensive common knowledge for high-level planning in embodied AI and in downstream Vision-Language-Action (VLA) models, the extent of their true understanding of physical tools remains unquantified. To bridge this gap, we present PhysToolBench, the first benchmark dedicated to evaluating the comprehension of physical tools by MLLMs. Our benchmark is structured as a Visual Question Answering (VQA) dataset comprising over 1,000 image-text pairs. It assesses capabilities across three distinct difficulty levels: (1) Tool Recognition: Requiring the recognition of a tool's primary function. (2) Tool Understanding: Testing the ability to grasp the underlying principles of a tool's operation. (3) Tool Creation: Challenging the model to fashion a new tool from surrounding objects when conventional options are unavailable. Our comprehensive evaluation of 32 MLLMs-spanning proprietary, open-source, specialized embodied, and backbones in VLAs-reveals a significant deficiency in tool understanding. Furthermore, we provide an in-depth analysis and propose preliminary solutions. Code and dataset are publicly available.

cs.CV↗

arXiv2025

A Theory of Multi-Agent Generative Flow Networks

Generative flow networks utilize a flow-matching loss to learn a stochastic policy for generating objects from a sequence of actions, such that the probability of generating a pattern can be proportional to the corresponding given reward. However, a theoretical framework for multi-agent generative flow networks (MA-GFlowNets) has not yet been proposed. In this paper, we propose the theory framework of MA-GFlowNets, which can be applied to multiple agents to generate objects collaboratively through a series of joint actions. We further propose four algorithms: a centralized flow network for centralized training of MA-GFlowNets, an independent flow network for decentralized execution, a joint flow network for achieving centralized training with decentralized execution, and its updated conditional version. Joint Flow training is based on a local-global principle allowing to train a collection of (local) GFN as a unique (global) GFN. This principle provides a loss of reasonable complexity and allows to leverage usual results on GFN to provide theoretical guarantees that the independent policies generate samples with probability proportional to the reward function. Experimental results demonstrate the superiority of the proposed framework compared to reinforcement learning and MCMC-based methods.

cs.LG↗

arXiv2025

UltraVSR: Achieving Ultra-Realistic Video Super-Resolution with Efficient One-Step Diffusion Space

Diffusion models have shown great potential in generating realistic image detail. However, adapting these models to video super-resolution (VSR) remains challenging due to their inherent stochasticity and lack of temporal modeling. Previous methods have attempted to mitigate this issue by incorporating motion information and temporal layers. However, unreliable motion estimation from low-resolution videos and costly multiple sampling steps with deep temporal layers limit them to short sequences. In this paper, we propose UltraVSR, a novel framework that enables ultra-realistic and temporally-coherent VSR through an efficient one-step diffusion space. A central component of UltraVSR is the Degradation-aware Reconstruction Scheduling (DRS), which estimates a degradation factor from the low-resolution input and transforms the iterative denoising process into a single-step reconstruction from low-resolution to high-resolution videos. To ensure temporal consistency, we propose a lightweight Recurrent Temporal Shift (RTS) module, including an RTS-convolution unit and an RTS-attention unit. By partially shifting feature components along the temporal dimension, it enables effective propagation, fusion, and alignment across frames without explicit temporal layers. The RTS module is integrated into a pretrained text-to-image diffusion model and is further enhanced through Spatio-temporal Joint Distillation (SJD), which improves temporally coherence while preserving realistic details. Additionally, we introduce a Temporally Asynchronous Inference (TAI) strategy to capture long-range temporal dependencies under limited memory constraints. Extensive experiments show that UltraVSR achieves state-of-the-art performance, both qualitatively and quantitatively, in a single sampling step. Code is available at https://github.com/yongliuy/UltraVSR.

cs.CV↗

arXiv2025

RA-DP: Rapid Adaptive Diffusion Policy for Training-Free High-frequency Robotics Replanning

Diffusion models exhibit impressive scalability in robotic task learning, yet they struggle to adapt to novel, highly dynamic environments. This limitation primarily stems from their constrained replanning ability: they either operate at a low frequency due to a time-consuming iterative sampling process, or are unable to adapt to unforeseen feedback in case of rapid replanning. To address these challenges, we propose RA-DP, a novel diffusion policy framework with training-free high-frequency replanning ability that solves the above limitations in adapting to unforeseen dynamic environments. Specifically, our method integrates guidance signals which are often easily obtained in the new environment during the diffusion sampling process, and utilizes a novel action queue mechanism to generate replanned actions at every denoising step without retraining, thus forming a complete training-free framework for robot motion adaptation in unseen environments. Extensive evaluations have been conducted in both well-recognized simulation benchmarks and real robot tasks. Results show that RA-DP outperforms the state-of-the-art diffusion-based methods in terms of replanning frequency and success rate. Moreover, we show that our framework is theoretically compatible with any training-free guidance signal.

cs.RO↗

arXiv2025

Less is More: Empowering GUI Agent with Context-Aware Simplification

The research focus of GUI agents is shifting from text-dependent to pure-vision-based approaches, which, though promising, prioritize comprehensive pre-training data collection while neglecting contextual modeling challenges. We probe the characteristics of element and history contextual modeling in GUI agent and summarize: 1) the high-density and loose-relation of element context highlight the existence of many unrelated elements and their negative influence; 2) the high redundancy of history context reveals the inefficient history modeling in current GUI agents. In this work, we propose a context-aware simplification framework for building an efficient and effective GUI Agent, termed SimpAgent. To mitigate potential interference from numerous unrelated elements, we introduce a masking-based element pruning method that circumvents the intractable relation modeling through an efficient masking mechanism. To reduce the redundancy in historical information, we devise a consistency-guided history compression module, which enhances implicit LLM-based compression through innovative explicit guidance, achieving an optimal balance between performance and efficiency. With the above components, SimpAgent reduces 27% FLOPs and achieves superior GUI navigation performances. Comprehensive navigation experiments across diverse web and mobile environments demonstrate the effectiveness and potential of our agent.

cs.CV↗

arXiv2025

Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills

Recent efforts to leverage the Multi-modal Large Language Model (MLLM) as GUI agents have yielded promising outcomes. However, these agents still struggle with long-horizon tasks in online environments, primarily due to insufficient knowledge and the inherent gap between offline and online domains. In this paper, inspired by how humans generalize knowledge in open-ended environments, we propose a Hierarchical Multimodal Skills (HMS) module to tackle the issue of insufficient knowledge. It progressively abstracts trajectories into execution skills, core skills, and ultimately meta-skills, providing a hierarchical knowledge structure for long-horizon task planning. To bridge the domain gap, we propose the Skill-Augmented Monte Carlo Tree Search (SA-MCTS) algorithm, which efficiently leverages skills acquired in offline environments to reduce the action search space during online tree exploration. Building on HMS, we propose Mirage-1, a multimodal, cross-platform, plug-and-play GUI agent. To validate the performance of Mirage-1 in real-world long-horizon scenarios, we constructed a new benchmark, AndroidLH. Experimental results show that Mirage-1 outperforms previous agents by 32\%, 19\%, 15\%, and 79\% on AndroidWorld, MobileMiniWob++, Mind2Web-Live, and AndroidLH, respectively. Project page: https://cybertronagent.github.io/Mirage-1.github.io/

cs.AI↗

arXiv2025

DiMeR: Disentangled Mesh Reconstruction Model

We propose DiMeR, a novel geometry-texture disentangled feed-forward model with 3D supervision for sparse-view mesh reconstruction. Existing methods confront two persistent obstacles: (i) textures can conceal geometric errors, i.e., visually plausible images can be rendered even with wrong geometry, producing multiple ambiguous optimization objectives in geometry-texture mixed solution space for similar objects; and (ii) prevailing mesh extraction methods are redundant, unstable, and lack 3D supervision. To solve these challenges, we rethink the inductive bias for mesh reconstruction. First, we disentangle the unified geometry-texture solution space, where a single input admits multiple feasible solutions, into geometry and texture spaces individually. Specifically, given that normal maps are strictly consistent with geometry and accurately capture surface variations, the normal maps serve as the sole input for geometry prediction in DiMeR, while the texture is estimated from RGB images. Second, we streamline the algorithm of mesh extraction by eliminating modules with low performance/cost ratios and redesigning regularization losses with 3D supervision. Notably, DiMeR still accepts raw RGB images as input by leveraging foundation models for normal prediction. Extensive experiments demonstrate that DiMeR generalises across sparse-view-, single-image-, and text-to-3D tasks, consistently outperforming baselines. On the GSO and OmniObject3D datasets, DiMeR significantly reduces Chamfer Distance by more than 30%.

cs.CV↗

arXiv2025

GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent

GUI automation faces critical challenges in dynamic environments. MLLMs suffer from two key issues: misinterpreting UI components and outdated knowledge. Traditional fine-tuning methods are costly for app-specific knowledge updates. We propose GUI-explorer, a training-free GUI agent that incorporates two fundamental mechanisms: (1) Autonomous Exploration of Function-aware Trajectory. To comprehensively cover all application functionalities, we design a Function-aware Task Goal Generator that automatically constructs exploration goals by analyzing GUI structural information (e.g., screenshots and activity hierarchies). This enables systematic exploration to collect diverse trajectories. (2) Unsupervised Mining of Transition-aware Knowledge. To establish precise screen-operation logic, we develop a Transition-aware Knowledge Extractor that extracts effective screen-operation logic through unsupervised analysis the state transition of structured interaction triples (observation, action, outcome). This eliminates the need for human involvement in knowledge extraction. With a task success rate of 53.7% on SPA-Bench and 47.4% on AndroidWorld, GUI-explorer shows significant improvements over SOTA agents. It requires no parameter updates for new apps. GUI-explorer is open-sourced and publicly available at https://github.com/JiuTian-VL/GUI-explorer.

cs.AI↗