arXiv subjects

Zhaoxiang Zhang

Publications and source records attributed to Zhaoxiang Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Trace-WAM: Learning to Act via 3D Motion Prediction for World Action Models

World Action Models (WAMs) learn representations for robot control by coupling future visual prediction with action generation. Successful manipulation depends primarily on how the robot and task-relevant objects evolve, whereas future-video prediction must also reconstruct the appearance and background of the entire scene. We therefore propose Trace-WAM, which augments video-action learning with future 3D motion prediction as an auxiliary objective. This objective supervises temporal point correspondence together with image-plane displacement and depth change, directly describing the interaction dynamics and spatial changes involved in manipulation. To this end, we adopt a three-branch Mixture-of-Transformer (Tri-MoT) architecture to jointly learn video prediction, motion prediction, and action generation. The motion expert predicts future trajectories from current visual features, allowing motion supervision to shape the representations used for action generation. Because the action expert does not consume predicted trajectories, inference retains the current-observation policy path: a single visual forward pass followed by action denoising. Experiments on RoboCasa-GR1, LIBERO, and LIBERO-Plus demonstrate strong in-distribution performance and out-of-distribution generalization, with particularly clear gains over Fast-WAM under limited demonstrations and distribution shifts.

cs.RO↗

arXiv2026

WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform

World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason about environmental dynamics. However, existing embodied world model benchmarks are still largely confined to vision-only prediction, offline embodied applications, and simulator-based evaluation, making them insufficient for assessing increasingly comprehensive world models. In this work, we introduce WorldArena 2.0, an expanded benchmark that systematically broadens embodied world model evaluation along three dimensions: modality, functionality, and platform. Along the modality dimension, WorldArena 2.0 extends evaluation from vision-only to visuotactile modalities, enabling assessment of multimodal perception and prediction. Along the functionality dimension, it extends beyond policy evaluation and planning to assess world models as interactive RL environments for policy optimization. Along the platform dimension, it moves beyond simulator-only evaluation to a diverse suite of simulated and real-world robotic settings across multiple embodiments. Under a standardized protocol, WorldArena 2.0 comprehensively evaluates perceptual quality, interactive utility, and cross-platform performance, providing a comprehensive testbed for tracking progress toward embodied world models. The project page including codes and demos is available at: https://world-arena.ai/.

cs.RO↗

arXiv2026

Generalized CycleGRPO for Fine-Grained Multimodal Understanding and Grounding

Fine-grained multimodal intelligence requires models to both understand a designated region and localize it from language. Existing methods learn these directions with separate objectives and task-specific annotations. We present Generalized CycleGRPO, the first unified reinforcement learning framework coupling region understanding and localization across spatial, temporal, and spatio-temporal domains. Given a region, a multimodal large language model generates candidate descriptions and then localizes each description to reconstruct the input region. Reconstruction overlap provides a verifiable reward for captioning, while individual localization rewards improve the inverse mapping. A common region-space formulation extends this cycle from image masks and boxes to video intervals and timestamped spatial evidence, without reference captions or an external language-model judge during reinforcement learning. In videos, the cycle encourages descriptions that distinguish a target event from similar recurrences. We introduce DOVE (Distinctive Occurrence-level Video-caption Evaluation), a human-verified contrastive benchmark for this temporal distinctiveness. CycleGRPO improves SAMTok's overall gIoU from 57.5% to 68.2% on GroundingSuite and average gIoU from 71.2% to 78.7% on GRES. For temporal tasks, it achieves 51.9% tIoU on Charades and 33.3% Temporal Evidence Coverage on DOVE, compared with 45.6% and 14.8% for the Qwen3-VL initialization. These results establish region-text cycle consistency as a general self-evaluation principle for multimodal understanding and localization. Models, code, and DOVE are available at https://devinxzhang.github.io/Generalized-CycleGRPO-Page/.

cs.CV↗

arXiv2026

In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks

We study robotic in-context learning (ICL), an emerging paradigm that enables robots to infer and execute tasks from visual demonstrations. Despite its growing promise, the problem itself remains under-defined: a visual demonstration simultaneously conveys action trajectories, object semantics, manipulation affordances, spatial relations, and task goals, making it unclear what information the robot is actually expected to follow. In this work, we first provide a clear problem definition of robot ICL that explicitly defines its learning target and resolves this fundamental prompt ambiguity. Building on this definition, we develop a minimalist and reproducible ICL framework (SimpleICL) with a visual prompt encoder and a low-cost data collection protocol. Without massive pre-training or specialized data infrastructure, our framework achieves strong performance in both simulation and real-world environments. Extensive experiments further reveal several key properties of robot ICL, including semantic discrimination and task-relevant disentanglement. We will fully open-source our data and training pipeline to facilitate systematic and reproducible research on robot ICL. The project page can be found at https://simpleicl.github.io/simpleicl.

cs.RO↗

arXiv2026

PUGS: Physics-Guided Uncertainty Modeling for Underwater Dynamic 3D Gaussian Splatting

Dynamic 3D Gaussian Splatting (3DGS) provides an efficient framework for dynamic scene reconstruction. Most existing approaches model scene dynamics with deterministic deformation fields, assuming each Gaussian follows a distinct geometric trajectory over time. This assumption breaks down underwater, where light scattering, refraction, marine snow and low visibility create substantial physical ambiguity in captured images. We present PUGS, a physics-guided uncertainty model for underwater dynamic 3DGS. PUGS learns inherent uncertainty induced by underwater image formation and leverages it as a physical signal for dynamic scene modeling. Rather than estimating a single deterministic displacement, it parameterizes each Gaussian's motion as a probability distribution with expected deformation and physical uncertainty. We adopt stochastic deformation optimization to sample Gaussian trajectories via local reparameterization, exploring multiple physically plausible solutions during training. We further propose uncertainty stochastic annealing and a dual-path self-consistency distillation objective, converting stochastic exploration to deterministic reconstruction while preserving temporal coherence. Extensive experiments on underwater dynamic datasets and physics-aware benchmarks demonstrate superior rendering quality, temporal consistency and reconstruction robustness. Our method achieves 1.16 dB PSNR gain over the strongest baseline on UVEB and 3.99 dB on DRUVA.

cs.CV↗

arXiv2026

DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training

We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction. Training such a model on existing robot datasets faces two obstacles: imprecise calibration can impair action following, while limited coverage of unsuccessful interactions can bias predictions toward successful outcomes. To improve action following across embodiments, we render action trajectories into image-space conditions and introduce offline geometric calibration to align these conditions with the target videos. To broaden interaction coverage, we introduce counterfactual post-training, modifying recorded action trajectories and generating future videos under a wider range of actions and contact configurations. To provide feedback on these predictions without paired ground-truth futures, we construct a human-annotated video dataset covering robot, object, and interaction defects and use it to train an embodied video reward model. Its scores guide reinforcement-learning post-training toward more physically plausible interaction outcomes. On AgiBot, DreamTrue attains state-of-the-art action following, while reducing the human-assessed interaction defect rate from from 48.12% to 6.25%. Notably, our model ranks first in the world model track of the AgiBot World Challenge 2026. The project page can be found at https://brave-eai.github.io/DreamTrue.

cs.RO↗

arXiv2026

MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research

We present MobileGym, a browser-hosted, lightweight, fully controllable environment for everyday mobile use, targeting interaction fidelity without replicating proprietary backends. It enables two capabilities previously out of reach for everyday apps: verifiable outcome signals through deterministic state-based judging over structured JSON state, and scalable online RL through low-cost parallel rollouts. The full environment state is captured, configured, forked, and compared as structured JSON, and a single server can host hundreds of parallel instances, with about 400 MB memory per instance and about 3 s cold start. A layered state model and a declarative task-definition framework keep state programmability and task creation practical at scale, and a single programmatic judging mechanism delivers both deterministic evaluation verdicts and dense RL rewards. The accompanying MobileGym-Bench provides 416 parameterized task templates, including 256 test and 160 train templates, over 28 apps, with deterministic judges and a structured AnswerSheet protocol that avoids free-text matching failures. In a Sim-to-Real case study, GRPO on Qwen3-VL-4B-Instruct gains +12.8 percentage points on the 256-task test set, and on a 59-task real-device signal subset, real-device execution retains 95.1% of the simulation-side training gain. Project page: https://mobilegym.github.io.

cs.AI↗

arXiv2026

DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo

Achieving human-level manipulation requires dexterous robotic hands capable of complex object interactions. Advancing such capabilities further demands standardized benchmarks for systematic evaluation. However, prior work does not focus on task-oriented dexterous manipulation. Existing benchmarks also often lack high quality human demonstrations and an easy-to-use evaluation pipeline. In this paper, we present DexJoCo, a benchmark and toolkit for task-oriented dexterous manipulation, comprising 11 functionally grounded tasks that evaluate tool-use, bimanual coordination, long-horizon execution, and reasoning. We develop a low-cost data collection system and collect 1.1K trajectories across these tasks, with support for domain randomization to assess robustness. We benchmark modern models under diverse settings, including visual and dynamics randomization, multi-task training, and action-head adaptation. Through extensive empirical analysis, we identify several important insights and common limitations of current policies in dexterous manipulation, highlighting key challenges for future research in dexterous hand robot learning. Code is available at: https://dexjoco.github.io

cs.RO↗

arXiv2026

UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction

Fine-grained robotic manipulation depends on understanding parts, not only whole objects. Existing 3D foundation models tend to be either generalized but object-aware, or part-aware but limited to closed-set taxonomies, which weakens zero-shot transfer. We study text-conditioned 3D part segmentation, where a free-form phrase selects a functional part on point cloud. We introduce UniPart, a feed-forward cross-modal 3D Transformer that conditions CLIP text embedding. To scale supervision, we build LangPart-1M with 160K+ Objaverse assets and 8M text to part pairs using multi-view consistent part generation. We further manually label a high-quality subset, LangPart-4K, for fine-tuning and evaluation. UniPart achieves strong zero-shot results on open-vocabulary part benchmarks and transfers to language-conditioned part grasping in real world.

cs.CV↗

arXiv2026

CHOREO: Every Humanoid Skill as a Trajectory

Recent advances in humanoid robotics have produced diverse skills through reinforcement learning, motion imitation, and generative modeling. Yet these capabilities remain siloed because they are built around incompatible representations, interfaces, and controllers. We present CHOREO, a framework for training-free composition of heterogeneous humanoid skills. Our key observation is that, regardless of how a skill is learned, it can ultimately be expressed as an executable motion trajectory. Based on this observation, CHOREO converts each capability into SkillMotion, a unified representation that combines motion states, contacts, semantics, and boundary conditions. Skills are composed through direct continuation, cubic Hermite blending, or validated bridge motions, without retraining source models or updating models at test time. On Unitree G1 in MuJoCo, CHOREO organizes 2,950 admitted SkillMotion assets derived from heterogeneous sources and achieves 95.4\% sequence success across 130 multi-action tasks, including 93.8\% success on eight-action sequences. These results demonstrate that executable trajectories provide a scalable interface for accumulating and composing pretrained humanoid capabilities.

cs.RO↗

arXiv2026

MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

AI agents with advanced reasoning and tool-use capabilities have demonstrated impressive performance in web browsing for deep search. However, existing benchmarks such as BrowseComp primarily focus on textual content, overlooking the prevalence of multimodal content. To bridge this gap, we introduce MM-BrowseComp, a novel benchmark comprising 400 challenging, hand-crafted questions designed to evaluate multimodal retrieval and reasoning capabilities. Unlike prior work, MM-BrowseComp incorporates visual prompts and necessitates the extraction of key evidence from web images and videos to complete questions, rendering text-only approaches insufficient. Additionally, we provide a verified checklist for each question, enabling fine-grained analysis of multimodal dependencies and reasoning paths. Our comprehensive evaluation of 27 state-of-the-art models reveals that even leading models like GPT-5-High with tools achieve only 24.25\% accuracy, highlighting the suboptimal multimodal browsing capabilities, establishing MM-BrowseComp as a rigorous new standard for the field.

cs.CL↗

arXiv2026

CAPEval: A Decoupled Caption Evaluation across Understanding and Generation

Captions serve as a primary supervision signal for both multimodal understanding and text-to-image generation. However, previous evaluations treat the caption quality as a single scalar objective, which conflates two distinct properties: (1) how much visual information a caption covers and (2) how reliably the image supports its stated claims. To this end, we design a decoupled caption evaluation benchmark, CAPEval (Coverage And Precision Evaluation), with human-written ground-truth captions and human-verified atomic checklist items. Specifically, CAPEval decomposes caption quality into Coverage and Precision. The former quantifies how thoroughly a caption covers ground-truth factual content, while the latter reflects the factual correctness rate of all claims expressed in the caption. We select 10 captioners and further conduct controlled downstream end-to-end experiments with them from four model families, where the caption source is the only variable. Empirically, we find a consistent task-dependent dissociation: Coverage serves as the stronger correlate for understanding performance, whereas Precision acts as the dominant predictor for generation performance. This decoupled evaluation paradigm not only delivers a more fine-grained diagnosis of caption quality, but also offers actionable guidance for selecting and optimizing captioners tailored to different downstream tasks.

cs.CV↗

arXiv2026

WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity

Controllable video generation models are increasingly being developed as world models. Accordingly, evaluating them in this role extends beyond the apparent appearance of generated videos to the inherent reactivity of the worlds they depict: the ability to infer from the scene state how the world should react and to generate plausible consequences not explicitly described in the input. Yet existing benchmarks mainly assess visual quality or explicit instruction fulfillment by checking whether requested actions and interaction outcomes are realized, leaving inherent reactivity underexamined. We introduce WorldExam, a hierarchical diagnostic benchmark spanning four levels: Visual Quality, Control Adherence, Spatial Consistency, and World Reactivity. It comprises 1,474 cases across eight dedicated tasks and supports unified evaluation of camera-, action-, and language-driven model paradigms. The World Reactivity level evaluates scene-conditioned reactions and goal-directed behaviors beyond what is explicitly specified in the input. Evaluation of 20 representative models reveals a clear capability split. Camera-driven models excel at camera control, but their interfaces do not support dynamic interaction; action-driven models control subjects more precisely but often leave the world unresponsive; and language-driven models perform better on interaction but follow complex controls less faithfully. No model combines broad task coverage with consistently strong performance, showing that high visual quality and explicit instruction fulfillment do not guarantee inherent reactivity.

cs.CV↗

arXiv2026

PhiZero: A World Model Built Around Physical Language

We introduce PhiZero, a physical world model built around physical language, a compact discrete representation of world-state transitions. Existing physical world models typically predict future videos directly in pixel space, leaving the underlying world dynamics implicit within high-dimensional visual predictors. Motivated by humans' ability to abstract predictive structure from visual experience and organize it in natural language for explicit reasoning, we learn physical language from in-the-wild videos through self-supervision and use it to explicitly reason about how the physical world evolves. Accordingly, PhiZero adopts a reason-then-render paradigm: it first infers future world evolution as a physical-language sequence and then renders the inferred transitions into videos. Extensive experiments across generation and understanding benchmarks validate the ability of PhiZero to model physically coherent world evolution. We further show its potential for realistic and interactive world modeling, fine-grained action-conditioned simulation, and zero-shot motion transfer.

cs.CV↗

arXiv2026

Improving Large Vision-Language Models' Understanding for Flow Field Data

Large Vision-Language Models (LVLMs) have shown impressive capabilities across a range of tasks that integrate visual and textual understanding, such as image captioning and visual question answering. These models are trained on large-scale image and video datasets paired with text, enabling them to bridge visual perception and natural language processing. However, their application to scientific domains, especially in interpreting complex field data commonly used in the natural sciences, remains underexplored. In this work, we introduce FieldLVLM, a novel framework designed to improve large vision-language models' understanding of field data. FieldLVLM consists of two main components: a field-aware language generation strategy and a data-compressed multimodal model tuning. The field-aware language generation strategy leverages a special-purpose machine learning pipeline to extract key physical features from field data, such as flow classification, Reynolds number, and vortex patterns. This information is then converted into structured textual descriptions that serve as a dataset. The data-compressed multimodal model tuning focuses on LVLMs with these generated datasets, using a data compression strategy to reduce the complexity of field inputs and retain only the most informative values. This ensures compatibility with the models language decoder and guides its learning more effectively. Experimental results on newly proposed benchmark datasets demonstrate that FieldLVLM significantly outperforms existing methods in tasks involving scientific field data. Our findings suggest that this approach opens up new possibilities for applying large vision-language models to scientific research, helping bridge the gap between large models and domain-specific discovery.

cs.CV↗

arXiv2026

ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory

Recent VLM and VLA systems have improved robotic perception and action prediction, yet long-horizon embodied agents still require a general runtime layer for reasoning, memory, tool use, verification, and cross-embodiment execution. We present ABot-AgentOS, a general robotic Agent Operating System that sits above low-level controllers and provides a deliberative agent layer for scene-conditioned planning, context-isolated skill execution, multi-stage verification, multi-modal memory, and edge-cloud collaboration. To evaluate such systems, we introduce EmbodiedWorldBench, an executable benchmark with 16 indoor, outdoor, and hybrid scenes, four difficulty levels, and over 200 tasks involving navigation, object search, NPC dialogue, dynamic events, and trace-grounded scoring. ABot-AgentOS further introduces Universal Multi-modal Graph Memory, a persistent source-grounded substrate that converts dialogue, visual observations, spatial context, temporal relations, and task traces into typed nodes and edges. A failure-driven self-evolution loop converts diagnosed memory failures into gated runtime evo-assets that are promoted only to later evaluation splits, preventing current-split ground-truth leakage while enabling continual improvement. On an initial EmbodiedWorldBench subset, ABot-AgentOS improves over a single-controller baseline in both task success and goal completion. Across memory benchmarks, ABot-AgentOS Static achieves 87.5 on LoCoMo, 59.9 on OpenEQA EM-EQA, 88.6 on Mem-Gallery, and 76.5 Acc@All on NExT-QA; self-evolution further improves LoCoMo to 88.7, OpenEQA to 60.4, and Mem-Gallery to 89.0. These results suggest that a general Agent OS layer can improve long-horizon embodied execution while providing persistent, auditable memory for continual interaction.

cs.AI↗

arXiv2026

AVSCap: Orchestrating Audio-Visual Synergy for Omni-modal Video Captioning

Omni-modal video captioning is not merely combining visual captioning with audio transcription: a useful caption must describe how visual actions, speech, music, and sound effects co-evolve. Existing large multimodal models often fail at this relational step, treating audio and visual streams as loosely coupled observations, relying on automatic speech recognition, and under-specifying non-speech sounds and their links to visual events. We present AVSCap, a framework for audio-visual captioning centered on explicit cross-modal event binding. First, we construct AVSCap-130K, a tri-modal training corpus generated by a decoupled-then-fused pipeline that anchors visual and acoustic evidence before composing grounded omni-modal captions. Second, we train AVSCap-7B, a 7B captioner with a two-stage strategy: supervised fine-tuning establishes baseline capabilities, while sample-efficient reinforcement learning uses hybrid rewards to optimize acoustic completeness and audio-visual synergy. Our scaling analysis shows that reinforcement learning brings larger gains than increasing SFT data. Third, we introduce AVSCapBench, a benchmark that decomposes captions into visual, audio, and synergy events and evaluates them with fine-grained event recall. Experiments on AVSCapBench and external benchmarks show that AVSCap-7B improves non-speech audio coverage and cross-modal binding, delivering the best overall performance among evaluated open-source models.

cs.CV↗

arXiv2026

MotionAtlas: Detailed Region Captioning for Motion-Centric Videos

We propose MotionAtlas, a system for detailed captioning of motion-centric videos, comprising (1) a dedicated human-annotated benchmark, (2) a scalable, high-quality pipeline to construct training samples, and (3) a family of powerful Video-MLLMs. Unlike conventional global motion captioning datasets, we focus on region-aware motion captioning: given a video and a spatiotemporal mask, the model generates precise descriptions of motion within the target region, thereby alleviating visual clutter and motion entanglement and enabling reliable, quantifiable evaluation. Concretely, we first build MotionAtlas-Bench, a comprehensive benchmark comprising 2,073 multiple-choice questions, meticulously annotated for a curated set of high-quality, motion-centric videos, to evaluate fine-grained motion understanding of the objects in question. Second, we design a rigorous and scalable data pipeline that leverages self-bootstrap refinement to suppress fine-grained hallucinations, yielding 159k high-quality motion captioning data. Third, we design a tailored training data composition strategy, which achieves consistent and substantial performance gains across diverse baseline Video-MLLMs, including Molmo2 and Qwen3-VL. For instance, MotionAtlas-4B surpasses Qwen3-VL-4B by an average of 5.2 percentage points across general motion benchmarks. The benchmark, dataset, and code have been released.

cs.CV↗