arXiv subjects

Xiaojian Ma

Publications and source records attributed to Xiaojian Ma.

At least 19 recordsLinked to original sources

arXiv2026

SEED-UMI: Sharing the Exoskeleton between human and robot for onE-to-one Dexterous demonstration

Imitation learning for dexterous hands is bottlenecked by the difficulty of collecting contact-rich demonstrations that transfer faithfully to the robot. Prior wearable-exoskeleton systems record only on the human side and retarget via open-loop mappings calibrated in free space, which degrade under contact. We present SEED-UMI, a framework in which both the human and the robot wear the same exoskeleton: joint encoders become a physically shared measurement, and wrist cameras mounted to the exoskeleton observe the same outer mechanism during both human data collection and robot policy rollouts. This turns retargeting into paired cross-embodiment supervision and lets policies train directly on raw exoskeleton-centric wrist images, without segmentation or inpainting. On five contact-rich tasks, SEED-UMI achieves 3.0x greater data collection efficiency than exoskeleton-based teleoperation and a 70.0% average rollout success rate.

cs.RO↗

arXiv2026

DualGR: Generative Retrieval with Long and Short-Term Interests Modeling

In large-scale industrial recommendation systems, retrieval must produce high-quality candidates from massive corpora under strict latency. Recently, Generative Retrieval (GR) has emerged as a viable alternative to Embedding-Based Retrieval (EBR), which quantizes items into a finite token space and decodes candidates autoregressively, providing a scalable path that explicitly models target-history interactions via cross-attention. However, deploying GR in short-video feeds remains challenged by long-short interest interference, context-induced noise in hierarchical SID generation, and the lack of explicit learning from exposed-but-unclicked feedback. To address these challenges, we propose DualGR, which combines (i) a Dual-Branch Long/Short-Term Router (DBR) with selective activation, (ii) Search-based SID Decoding (S2D) that constrains fine-level decoding within the current coarse bucket for efficiency and noise control, and (iii) an Exposure-aware Next-Token Prediction Loss (ENTP-Loss) that treats unclicked exposures as coarse-level hard negatives to promote timely interest fade-out. On the large-scale Kuaishou short-video recommendation system, DualGR has achieved outstanding performance. Online A/B testing shows +0.527% video views and +0.432% watch time lifts, validating DualGR as a practical and effective paradigm for industrial generative retrieval.

cs.IR↗

arXiv2026

Learning Panorama-Aware VLA for Mobile Manipulation with Whole-Body Teleoperation

Mobile manipulation is a key capability for embodied intelligence, enabling robots to accomplish complex multi-stage tasks in open-world environments. However, mobile manipulation poses two key challenges for vision-language-action (VLA) policies: At the data level, the efficient collection of high-quality whole-body demonstrations demands the coordinated control of both the mobile base and the robotic arms; at the model level, existing VLA models predominantly rely on local camera observations, whose limited field of view hinders global spatial understanding. To address these challenges, we develop a whole-body teleoperation system and a panoramic-aware VLA policy. The system enables coordinated control of a wheeled bimanual robot through a single VR interface and supports the acquisition of a real-world mobile manipulation dataset comprising 5.5 hours of multimodal demonstrations. Building upon this dataset, we propose PanoVLA, a panorama-aware vision-language-action policy for mobile bimanual manipulation. Built upon a Mixture-of-Transformers architecture, PanoVLA introduces global spatial context through dedicated panorama encoding and fusion modules, enabling effective integration of panoramic observations with language instructions and robot states for action generation. Evaluation on four real-world mobile manipulation tasks demonstrates that PanoVLA achieves an average stage completion rate of 91.3\% and an end-to-end success rate of 73.4\%, substantially outperforming local-view baselines. These results demonstrate that incorporating panoramic spatial context improves spatial understanding and closed-loop manipulation performance in mobile robots.

cs.RO↗

arXiv2026

AdaReP:Adaptive Re-Planning under Model Mismatch for Neural World-Model Predictive Control

Neural world models coupled with model predictive control (MPC) replan at every environment step to bound accumulated prediction error, but this incurs substantial computational overhead. Reusing a cached plan reduces this overhead, yet its effectiveness depends on how prediction mismatch propagates through the local dynamics. We analyze this trade-off with a perturbation-based dynamic-regret framework and show that stale-plan penalties scale with the reuse tolerance, the accumulated mismatch since the last replanning step, and the local dynamics sensitivity. Based on this structure, we propose AdaReP, a training-free wrapper that adapts the replanning tolerance online using the current deviation from the cached rollout and a local sensitivity estimate, without modifying the learned world model or planner. Across image-space planning, latent-space control, and real-world robotic manipulation, AdaReP substantially reduces planner-side computation while maintaining comparable task performance, including over 80% fewer queries on a 50-trial physical robot study.

cs.RO↗

arXiv2026

Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning

Multimodal agents, which integrate a controller e.g., a vision language model) with external tools, have demonstrated remarkable capabilities in tackling complex multimodal tasks. Existing approaches for training these agents, both supervised fine-tuning and reinforcement learning, depend on extensive human-annotated task-answer pairs and tool trajectories. However, for complex multimodal tasks, such annotations are prohibitively expensive or impractical to obtain. In this paper, we propose an iterative tool usage exploration method for multimodal agents without any pre-collected data, namely SPORT, via step-wise preference optimization to refine the trajectories of tool usage. Our method enables multimodal agents to autonomously discover effective tool usage strategies through self-exploration and optimization, eliminating the bottleneck of human annotation. SPORT has four iterative components: task synthesis, step sampling, step verification, and preference tuning. We first synthesize multimodal tasks using language models. Then, we introduce a novel trajectory exploration scheme, where step sampling and step verification are executed alternately to solve synthesized tasks. In step sampling, the agent tries different tools and obtains corresponding results. In step verification, we employ a verifier to provide AI feedback to construct step-wise preference data. The data is subsequently used to update the controller for tool usage through preference tuning, producing a SPORT agent. By interacting with real environments, the SPORT agent gradually evolves into a more refined and capable system. Evaluation in the GTA and GAIA benchmarks shows that the SPORT agent achieves 6.41% and 3.64% improvements, underscoring the generalization and effectiveness introduced by our method. The project page is https://SPORT-Agents.github.io.

cs.CV↗

arXiv2026

"Noisier" Noise Contrastive Eestimation is (Almost) Maximum Likelihood

Noise Contrastive Estimation (NCE) has fueled major breakthroughs in representation learning and generative modeling. Yet a long-standing challenge remains: accurately estimating ratios between distributions that differ substantially, which significantly limits the applicability of NCE on modern high-dimensional and multimodal datasets. We revisit this problem from a less explored perspective: the magnitude of the noise distribution. Specifically, we show that with a virtually scaled (\ie, artificially increased) noise magnitude, the gradient of the NCE objective can closely align with that of Maximum Likelihood, enabling a trajectory-wise approximation from NCE to MLE, and faster convergence both theoretically and empirically. Building on this insight, we introduce ``Noisier'' NCE, a simple drop-in modification to vanilla NCE that incurs little to no extra computational cost, while effectively handling density-ratio estimation in challenging regimes where traditional MLE and NCE struggle. Beyond improving classical density-ratio learning, ``Noisier'' NCE proves broadly applicable: it achieves strong results across image modeling, anomaly detection, and offline black-box optimization. On CIFAR-10 and ImageNet64x64 datasets, it yields 10-step and even 1-step samplers that match or surpass state-of-the-art methods, while cutting training iterations by up to half.

cs.LG↗

arXiv2026

Probing Visual Planning in Image Editing Models

Visual planning represents a crucial facet of human intelligence, especially in tasks that require complex spatial reasoning and navigation. Yet, in machine learning, this inherently visual problem is often tackled through a verbal-centric lens. While recent research demonstrates the promise of fully visual approaches, they suffer from significant computational inefficiency due to the step-by-step planning-by-generation paradigm. In this work, we present EAR, an editing-as-reasoning paradigm that reformulates visual planning as a single-step image transformation. To isolate intrinsic reasoning from visual recognition, we employ abstract puzzles as probing tasks and introduce AMAZE, a procedurally generated dataset that features the classical Maze and Queen problems, covering distinct, complementary forms of visual planning. The abstract nature of AMAZE also facilitates automatic evaluation of autoregressive and diffusion-based models in terms of both pixel-wise fidelity and logical validity. We assess leading proprietary and open-source editing models. The results show that they all struggle in the zero-shot setting, finetuning on basic scales enables remarkable generalization to larger in-domain scales and out-of-domain scales and geometries. However, our best model that runs on high-end hardware fails to match the zero-shot efficiency of human solvers, highlighting a persistent gap in neural visual reasoning.

cs.CV↗

arXiv2026

Chain Of Interaction Benchmark (COIN): When Reasoning meets Embodied Interaction

Generalist embodied agents must perform interactive, causally-dependent reasoning, continually interacting with the environment, acquiring information, and updating plans to solve long-horizon tasks before they could be adopted in real-life scenarios. For instance, retrieving an apple from a cabinet may require opening multiple doors and drawers before the apple becomes visible and reachable, demanding sequential interaction under partial observability. However, existing benchmarks fail to systematically evaluate this essential capability. We introduce COIN, a benchmark designed to assess interactive reasoning in realistic robotic manipulation through three key contributions. First, we construct COIN-50: 50 interactive tasks in daily scenarios, and create COIN-Primitive required by causally-dependent tasks, and COIN-Composition with mid-term complexity for skill learning and generalization evaluation. Second, we develop a low-cost mobile AR teleoperation system and collect the COIN-Primitive Dataset with 50 demonstrations per primitive task (1,000 in total). Third, we develop systematic evaluation metrics about execution stability and generalization robustness to evaluate CodeAsPolicy, VLA, and language-conditioned H-VLA approaches. Our comprehensive evaluation reveals critical limitations in current methods: models struggle with interactive reasoning tasks due to significant gaps between visual understanding and motor execution. We provide fine-grained analysis of these limitations.

cs.RO↗

arXiv2026

LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning

Developing vision-language models (VLMs) capable of understanding 3D scenes has been a longstanding research goal. Despite recent progress, 3D VLMs still struggle with spatial reasoning and robustness. We identify three key obstacles hindering their progress: (1) scene representation is constrained by a capacity-efficiency trade-off, which impedes scalable learning; (2) training data lacks a comprehensive scheme, with limited diversity across tasks and scene domains; and (3) models exhibit robustness deficiencies and lack effective post-training. To address these challenges, we first propose condensed feature grid (CFG), an efficient scene representation that significantly reduces token overhead while preserving strong perceptual capacity. Building on CFG, we introduce LEO-VL, a 3D VLM trained on over 700k 3D vision-language (3D-VL) data spanning four real-world indoor domains and five tasks such as captioning and dialogue. To further improve robustness, we propose SceneDPO, a novel post-training objective that incorporates contrastive signals across both answers and scenes. LEO-VL achieves state-of-the-art performance on various 3D-VL benchmarks, such as SQA3D, Beacon3D, and Scan2Cap. Extensive analyses highlight the efficiency of CFG and provide key insights such as the importance of task and scene diversity, the priority of data quality for effective scaling, and the advantages of SceneDPO.

cs.CV↗

arXiv2026

MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning

Reasoning-augmented machine learning systems have shown improved performance in various domains, including image generation. However, existing reasoning-based methods for image generation either restrict reasoning to a single modality (image or text) or rely on high-quality reasoning data for fine-tuning. To tackle these limitations, we propose MILR, a test-time method that jointly reasons over image and text in a unified latent vector space. Reasoning in MILR is performed by searching through vector representations of discrete image and text tokens. Practically, this is implemented via the policy gradient method, guided by an image quality critic. We instantiate MILR within the unified multimodal understanding and generation (MUG) framework that natively supports language reasoning before image synthesis and thus facilitates cross-modal reasoning. The intermediate model outputs, which are to be optimized, serve as the unified latent space, enabling MILR to operate entirely at test time. We evaluate MILR on GenEval, T2I-CompBench, and WISE, achieving state-of-the-art results on all benchmarks. Notably, on knowledge-intensive WISE, MILR attains an overall score of 0.63, improving over the baseline by 80%. Our further analysis indicates that joint reasoning in the unified latent space is the key to its strong performance. Moreover, our qualitative studies reveal MILR's non-trivial ability in temporal and cultural reasoning, highlighting the efficacy of our reasoning method.

cs.CV↗

arXiv2025

TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents

Building Graphical User Interface (GUI) agents is a promising research direction, which simulates human interaction with computers or mobile phones to perform diverse GUI tasks. However, a major challenge in developing generalized GUI agents is the lack of sufficient trajectory data across various operating systems and applications, mainly due to the high cost of manual annotations. In this paper, we propose the TongUI framework that builds generalized GUI agents by learning from rich multimodal web tutorials. Concretely, we crawl and process online GUI tutorials (such as videos and articles) into GUI agent trajectory data, through which we produce the GUI-Net dataset containing 143K trajectory data across five operating systems and more than 200 applications. We develop the TongUI agent by fine-tuning Qwen2.5-VL-3B/7B models on GUI-Net, which show remarkable performance improvements on commonly used grounding and navigation benchmarks, outperforming baseline agents about 10\% on multiple benchmarks, showing the effectiveness of the GUI-Net dataset and underscoring the significance of our TongUI framework. We will fully open-source the code, the GUI-Net dataset, and the trained models soon.

cs.CV↗

arXiv2025

From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes

3D visual grounding has made notable progress in localizing objects within complex 3D scenes. However, grounding referring expressions beyond objects in 3D scenes remains unexplored. In this paper, we introduce Anywhere3D-Bench, a holistic 3D visual grounding benchmark consisting of 2,886 referring expression-3D bounding box pairs spanning four different grounding levels: human-activity areas, unoccupied space beyond objects, individual objects in the scene, and fine-grained object parts. We assess a range of state-of-the-art 3D visual grounding methods alongside large language models (LLMs) and multimodal LLMs (MLLMs) on Anywhere3D-Bench. Experimental results reveal that space-level and part-level visual grounding pose the greatest challenges: space-level tasks require a more comprehensive spatial reasoning ability, for example, modeling distances and spatial relations within 3D space, while part-level tasks demand fine-grained perception of object composition. Even the best-performing models, Google Gemini-2.5-Pro and OpenAI o3, achieve just around 30% accuracy on space-level tasks and around 40% on part-level tasks, significantly lower than its performance on area-level and object-level tasks. These findings underscore a critical gap in current models' capacity to understand and reason about 3D scenes beyond object-level semantics.

cs.CV↗

arXiv2025

NEP: Autoregressive Image Editing via Next Editing Token Prediction

Text-guided image editing involves modifying a source image based on a language instruction and, typically, requires changes to only small local regions. However, existing approaches generate the entire target image rather than selectively regenerate only the intended editing areas. This results in (1) unnecessary computational costs and (2) a bias toward reconstructing non-editing regions, which compromises the quality of the intended edits. To resolve these limitations, we propose to formulate image editing as Next Editing-token Prediction (NEP) based on autoregressive image generation, where only regions that need to be edited are regenerated, thus avoiding unintended modification to the non-editing areas. To enable any-region editing, we propose to pre-train an any-order autoregressive text-to-image (T2I) model. Once trained, it is capable of zero-shot image editing and can be easily adapted to NEP for image editing, which achieves a new state-of-the-art on widely used image editing benchmarks. Moreover, our model naturally supports test-time scaling (TTS) through iteratively refining its generation in a zero-shot manner. The project page is: https://nep-bigai.github.io/

cs.CV↗

arXiv2025

JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse

Recently, action-based decision-making in open-world environments has gained significant attention. Visual Language Action (VLA) models, pretrained on large-scale web datasets, have shown promise in decision-making tasks. However, previous work has primarily focused on action post-training, often neglecting enhancements to the foundational model itself. In response, we introduce a novel approach, Act from Visual Language Post-Training, which refines Visual Language Models (VLMs) through visual and linguistic guidance in a self-supervised manner. This enhancement improves the models' capabilities in world knowledge, visual recognition, and spatial grounding in open-world environments. Following the above post-training paradigms, we obtain the first VLA models in Minecraft that can follow human instructions on over 1k different atomic tasks, including crafting, smelting, cooking, mining, and killing. Our experiments demonstrate that post-training on non-trajectory tasks leads to a significant 40% improvement over the best agent baseline on a diverse set of atomic tasks. Furthermore, we demonstrate that our approach surpasses traditional imitation learning-based policies in Minecraft, achieving state-of-the-art performance. We have open-sourced the code, models, and datasets to foster further research. The project page can be found in https://craftjarvis.github.io/JarvisVLA.

cs.CV↗

arXiv2025

Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation

Embodied scene understanding requires not only comprehending visual-spatial information that has been observed but also determining where to explore next in the 3D physical world. Existing 3D Vision-Language (3D-VL) models primarily focus on grounding objects in static observations from 3D reconstruction, such as meshes and point clouds, but lack the ability to actively perceive and explore their environment. To address this limitation, we introduce \underline{\textbf{M}}ove \underline{\textbf{t}}o \underline{\textbf{U}}nderstand (\textbf{\model}), a unified framework that integrates active perception with \underline{\textbf{3D}} vision-language learning, enabling embodied agents to effectively explore and understand their environment. This is achieved by three key innovations: 1) Online query-based representation learning, enabling direct spatial memory construction from RGB-D frames, eliminating the need for explicit 3D reconstruction. 2) A unified objective for grounding and exploring, which represents unexplored locations as frontier queries and jointly optimizes object grounding and frontier selection. 3) End-to-end trajectory learning that combines \textbf{V}ision-\textbf{L}anguage-\textbf{E}xploration pre-training over a million diverse trajectories collected from both simulated and real-world RGB-D sequences. Extensive evaluations across various embodied navigation and question-answering benchmarks show that MTU3D outperforms state-of-the-art reinforcement learning and modular navigation approaches by 14\%, 23\%, 9\%, and 2\% in success rate on HM3D-OVON, GOAT-Bench, SG3D, and A-EQA, respectively. \model's versatility enables navigation using diverse input modalities, including categories, language descriptions, and reference images. These findings highlight the importance of bridging visual grounding and exploration for embodied intelligence.

cs.CV↗

arXiv2025

Falcon: Fast Visuomotor Policies via Partial Denoising

Diffusion policies are widely adopted in complex visuomotor tasks for their ability to capture multimodal action distributions. However, the multiple sampling steps required for action generation significantly harm real-time inference efficiency, which limits their applicability in real-time decision-making scenarios. Existing acceleration techniques either require retraining or degrade performance under low sampling steps. Here we propose Falcon, which mitigates this speed-performance trade-off and achieves further acceleration. The core insight is that visuomotor tasks exhibit sequential dependencies between actions. Falcon leverages this by reusing partially denoised actions from historical information rather than sampling from Gaussian noise at each step. By integrating current observations, Falcon reduces sampling steps while preserving performance. Importantly, Falcon is a training-free algorithm that can be applied as a plug-in to further improve decision efficiency on top of existing acceleration techniques. We validated Falcon in 48 simulated environments and 2 real-world robot experiments. demonstrating a 2-7x speedup with negligible performance degradation, offering a promising direction for efficient visuomotor policy design.

cs.RO↗

arXiv2025

FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation

This paper investigates training better visual world models for robot manipulation, i.e., models that can predict future visual observations by conditioning on past frames and robot actions. Specifically, we consider world models that operate on RGB-D frames (RGB-D world models). As opposed to canonical approaches that handle dynamics prediction mostly implicitly and reconcile it with visual rendering in a single model, we introduce FlowDreamer, which adopts 3D scene flow as explicit motion representations. FlowDreamer first predicts 3D scene flow from past frame and action conditions with a U-Net, and then a diffusion model will predict the future frame utilizing the scene flow. FlowDreamer is trained end-to-end despite its modularized nature. We conduct experiments on 4 different benchmarks, covering both video prediction and visual planning tasks. The results demonstrate that FlowDreamer achieves better performance compared to other baseline RGB-D world models by 7% on semantic similarity, 11% on pixel quality, and 6% on success rate in various robot manipulation domains.

cs.RO↗

arXiv2025

Building LLM Agents by Incorporating Insights from Computer Systems

LLM-driven autonomous agents have emerged as a promising direction in recent years. However, many of these LLM agents are designed empirically or based on intuition, often lacking systematic design principles, which results in diverse agent structures with limited generality and scalability. In this paper, we advocate for building LLM agents by incorporating insights from computer systems. Inspired by the von Neumann architecture, we propose a structured framework for LLM agentic systems, emphasizing modular design and universal principles. Specifically, this paper first provides a comprehensive review of LLM agents from the computer system perspective, then identifies key challenges and future directions inspired by computer system design, and finally explores the learning mechanisms for LLM agents beyond the computer system. The insights gained from this comparative analysis offer a foundation for systematic LLM agent design and advancement.

cs.CV↗