arXiv subjects

Cong Huang

Publications and source records attributed to Cong Huang.

At least 19 recordsLinked to original sources

arXiv2026

FBFM: A Training-Free Asynchronous Feedback Mechanism for Flow-Matching in World-Action Models Execution

Although world-action models (WAMs) enhance long-horizon robot control by predicting visual evolution before acting, long-horizon reliability demands repeated re-grounding in real observations--not recursive rollout. Existing WAMs address this by refreshing history or KV cache with ground-truth data between chunks. However, such chunk-wise feedback operates at a coarse temporal granularity and thus fails to correct prediction errors at the individual time-step level. To address this, we propose Feedback Flow Matching (FBFM), a training-free inference mechanism that pushes re-grounding inside the actively generated chunk. During flow matching, FBFM applies a masked pseudoinverse correction to the conditional velocity field: it leverages the preceding action chunk to guide generation of the next action chunk, and uses the image observed after executing that preceding chunk to guide the next frame prediction. This cross-chunk pairing--where feedback from one chunk arrives in time to shape the next--creates an asynchronous loop that corrects errors without waiting for chunk boundaries. Being training-free, the mechanism improves responsiveness to unexpected events and suppresses drift in long-horizon tasks. We evaluate FBFM on both a joint-generation WAM (DreamZero) and a stage-wise WAM (LingBot-VA). On selected LIBERO and RoboTwin2.0 tasks, it improves success rates by over 5% in favorable settings, and real-world robot observation-prediction diagnostics show notably better tracking. We argue that FBFM offers a new paradigm for fine-grained online correction, bridging open-loop flow generation with closed-loop real-world dynamics.

cs.RO↗

arXiv2026

Closing the Loop in Humanoid VLA: Persistent 3D Object Tokens for Verifiable Loco-Manipulation

Vision-language-action policies are a promising foundation for general robot control, but long-horizon humanoid loco-manipulation requires the robot to treat task objects as persistent physical entities across movement, contact, occlusion, and recovery. We study this problem as object-state divergence: the object state used to condition a whole-body action can differ from the state used to decide whether the action achieved the intended physical relation. We propose \emph{Persistent Object Tokenization} (POT), which maintains role-indexed 3D object records from RGB-D observations and converts them into object tokens for a whole-body action expert. Instantiated as \emph{POT-VLA}, the same object records condition action generation and support geometric predicate checks, yielding a closed-loop execution system in which object state is both actionable and verifiable. On a Unitree G1, POT-VLA improves a matched direct GR00T-N1.7 baseline from 39/80 to 71/80 successes over eight real-world task families. In an external Being-0-aligned reference, POT-VLA achieves 44/50 successes on aligned service tasks, compared with the 37/50 success reported by the Being-0 paper. The largest gains occur on tasks requiring maintained 3D relations, suggesting that persistent object-centered state is a useful abstraction for verifiable humanoid VLA execution.

cs.RO↗

arXiv2026

SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models

Vision-Language-Action (VLA) models are typically trained by imitation learning on large-scale robot demonstration datasets, but more data does not necessarily yield better policies due to redundancy, noise, and uneven coverage. Existing data selection methods often assess demonstrations at either the trajectory or state-action level, missing the reusable structures that compose long-horizon behaviors. In this paper, we propose SIEVE, a structure-aware data selection method for VLA imitation learning. SIEVE views demonstrations as compositions of reusable primitives and transition interfaces. It first discovers visuo-motor primitives from segmented trajectories, then allocates selection budgets to composition patterns by maximizing reuse-aware structural exposure under diminishing returns. Finally, it selects medoid trajectories within each composition-pattern bucket to retain central, stable, and imitation-friendly demonstrations. Experiments across multiple datasets, benchmarks, and VLA models show that SIEVE consistently outperforms competitive data selection baselines. Notably, SIEVE can surpass full-data training while using only 50% of demonstrations and 50% of training steps, suggesting that reusable structure, captured through primitives and transitions, is an important signal for efficient VLA imitation learning.

cs.RO↗

arXiv2026

Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models

Recent 3D generative models can synthesize high-quality geometry but often struggle to reproduce intricate textures from reference images, largely due to the scarcity of large-scale 3D training data with rich surface appearance. In contrast, visual generative models are trained on datasets several orders of magnitude larger and excel at modeling complex visual patterns. Motivated by this gap, we introduce Ink3D, a framework that bridges 3D generation with large-scale video generative models to synthesize extremely complex textures. Ink3D first reconstructs a white-mesh geometry using an off-the-shelf 3D generation model. It then employs OrbitPainter, a conditional video generative model, to produce dense orbit-scan videos capturing object appearance across viewpoints. To convert these views into coherent textures, we introduce TextureOptimizer, a neural baking module that integrates dense multi-view observations while mitigating geometry inconsistencies arising from video generation. By decoupling geometry and texture synthesis and leveraging large-scale pretrained video priors, Ink3D enables significantly richer and more faithful texture generation than prior approaches.

cs.CV↗

arXiv2026

Human-as-Humanoid: Enabling Zero-Shot Humanoid Learning from Ego-Exo Human Videos with Human-Aligned Embodiments

Vision-language-action (VLA) models across robot embodiments require high-quality observation--action supervision to learn deployable action distributions, yet scaling such robot data remains difficult, especially for high-DoF humanoids. Teleoperation provides controller-aligned supervision, while human egocentric videos capture diverse bimanual manipulation but do not directly provide executable robot actions. We introduce Human-as-Humanoid, a human-to-humanoid supervision framework that enables near-real-time human-centric action generation, making human demonstrations usable for high-DoF humanoid VLA training by jointly aligning the robot embodiment, the sensing setup, and the action-label interface. Built on PrimeU, a human-aligned 60-DoF upper-body humanoid, Human-as-Humanoid uses synchronized ego-exo videos to pair deployment-aligned egocentric observations with exocentric motion recovery, retargets the recovered human motion through staged Inverse Kinematics (IK) into controller-aligned 60-DoF action chunks, and trains the VLA model with Forward Kinematics (FK)-aware supervision to preserve wrist and fingertip task-space geometry. This converts large-scale human demonstrations from visual observations into executable observation--action supervision for the target humanoid. Experiments validate the conversion chain at the motion-recovery, robot-action-space, and real-robot deployment levels. Human-as-Humanoid yields a 4.8--7.2x raw demonstration-throughput gain over humanoid teleoperation in our data-collection analysis, and on several downstream tasks, policies post-trained only with the converted human labels generalize to real-robot deployment without target-task robot demonstrations. The official project website is available at https://zgc-embodyai.github.io/Human-as-Humanoid.

cs.RO↗

arXiv2026

EgoPriMo: Egocentric Motion Generation for Interactive Humanoid Control

Humanoid robots require whole-body motions that adapt to scene context, task requirements, and user intent. Motion tracking reproduces specified trajectories, and humanoid vision-language-action systems provide semantic interfaces, but neither offers a scalable and interactive prior for broad full-body behavior. We introduce EgoPriMo (Egocentric Motion Prior for Humanoid Robots), a unified framework that learns such priors from egocentric human demonstrations. Given egocentric observations and a text prompt, EgoPriMo reconstructs, generates, and forecasts SMPL-based full-body motion. Language is used as a high-level control signal rather than a complete motion specification. At the core of EgoPriMo is a Triple-stream DiT that jointly models body dynamics, egocentric visual context, and text; task-conditioning masks route different tasks and missing-modality data through the same checkpoint. Experiments on Nymeria and EgoExo4D show that one checkpoint improves egocentric motion generation over UniEgoMotion while supporting reconstruction and forecasting; the generated SMPL motions can also be executed by a Unitree humanoid controller. These results indicate a practical path from scalable egocentric observations to generalizable and interactive humanoid motion priors.

cs.RO↗

arXiv2026

RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models

Vision-language-action (VLA) models are built on the premise that semantic understanding from pretrained language or vision-language backbones should guide robot action prediction. Yet robot fine-tuning is optimized as imitation over task-specific action distributions, and many evaluations can be solved through visual or instruction-action shortcuts. We introduce RoboSemanticBench (RSB), an embodied benchmark for diagnosing semantic grounding in action prediction: whether post-trained VLA models can use complex instruction semantics to select and manipulate the correct physical target. In each episode, a robot receives a multiple-choice math or general-knowledge question, observes candidate answer blocks, and must grasp the block corresponding to the correct answer. RSB covers controlled arithmetic, grade-school mathematical understanding, and commonsense or factual understanding under four-choice and ten-choice suites. Across representative VLA models, we find that many policies learn to grasp candidate blocks but select the semantically correct block at near-random or below-random rates after controlling for grasp success, revealing a persistent gap between backbone-level semantic competence and action prediction.

cs.RO↗

arXiv2026

IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation

Robot imitation data are often multimodal: similar visual-language observations may be followed by different action chunks because human demonstrators act with different short-horizon intents, task phases, or recent context. Existing frame-conditioned VLA policies infer each chunk from the current observation and instruction alone, so under partial observability they may resample different intents across adjacent replanning steps, leading to inter-chunk conflict and unstable execution. We introduce IntentVLA, a history-conditioned VLA framework that encodes recent visual observations into a compact short-horizon intent representation and uses it to condition chunk generation. We further introduce AliasBench, a 12-task ambiguity-aware benchmark on RoboTwin2 with matched training data and evaluation environments that isolate short-horizon observation aliasing. Across AliasBench, SimplerEnv, LIBERO, and RoboCasa, IntentVLA improves rollout stability and outperforms strong VLA baselines

cs.RO↗

arXiv2026

PhysBrain 1.0 Technical Report

Vision-language-action models have advanced rapidly, but robot trajectories alone provide limited coverage for learning broad physical understanding. PhysBrain 1.0 studies a complementary route: converting large-scale human egocentric video into structured physical commonsense supervision before robot adaptation. Our data engine extracts scene elements, spatial dynamics, action execution, and depth-aware relations, then turns them into question-answer supervision for training PhysBrain VLMs. The resulting physical priors are further transferred to VLA policies through a capability-preserving and language-sensitive adaptation design. Across multimodal QA benchmarks and embodied control benchmarks, including ERQA, PhysBench, SimplerEnv-WidowX, LIBERO, and RoboCasa, PhysBrain 1.0 achieves SOTA results and shows especially strong out-of-domain performance on SimplerEnv. These results suggest that scaling physical commonsense from human interaction video can provide an effective bridge from multimodal understanding to robot action.

cs.RO↗

arXiv2026

FrameSkip: Learning from Fewer but More Informative Frames in VLA Training

Vision-Language-Action (VLA) policies are commonly trained from dense robot demonstration trajectories, often collected through teleoperation, by sampling every recorded frame as if it provided equally useful supervision. We argue that this convention creates a temporal supervision imbalance: long low-change segments dominate the training stream, while manipulation-critical transitions such as alignment, contact, grasping, and release appear only sparsely. We introduce FrameSkip, a data-layer frame selection framework that scores trajectory frames using action variation, visual-action coherence, task-progress priors, and gripper-transition preservation, then remaps training samples toward high-importance frames under a target retention ratio. Because FrameSkip operates only in the dataloader, it leaves the VLA architecture, action head, training objective, and inference procedure unchanged. Across RoboCasa-GR1, SimplerEnv, and LIBERO, FrameSkip improves the success-retention trade-off over full-frame training and simpler frame selection variants, achieving a macro-average success rate of 76.15% across the three benchmarks compared with 66.50% for full-frame training while using a compressed trajectory view that retains 20% of unique frames in the main setting.

cs.RO↗

arXiv2026

EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields

Pretrained video diffusion models provide powerful spatiotemporal generative priors, making them a natural foundation for robotic world models. While recent world-action models jointly optimize future videos and actions, they predominantly treat video generation as an auxiliary representation for policy learning. Consequently, they insufficiently explore the inverse problem: leveraging action signals to guide video synthesis, thereby often failing to preserve precise robot spatial geometry and fine-grained robot-object interaction dynamics in the generated rollouts. To bridge this gap, we present EA-WM, an Event-Aware Generative World Model that effectively closes the loop between kinematic control and visual perception. Rather than injecting joint or end-effector actions as abstract, low-dimensional tokens, EA-WM projects actions and kinematic states directly into the target camera view as Structured Kinematic-to-Visual Action Fields. To fully exploit this geometrically grounded representation, we introduce event-aware bidirectional fusion blocks that modulate cross-branch attention, capturing object state changes and interaction dynamics. Evaluated on the comprehensive WorldArena benchmark, EA-WM achieves state-of-the-art performance, outperforming existing baselines by a significant margin.

cs.CV↗

arXiv2026

STARRY: Spatial-Temporal Action-Centric World Modeling for Robotic Manipulation

Robotic manipulation requires reasoning about future spatial-temporal interactions and geometric constraints, yet existing Vision-Language-Action (VLA) policies often leave predictive representation weakly coupled with action execution, causing failures in tasks requiring precise spatial-temporal coordination. We propose STARRY, a world-model-enhanced action-generation policy that aligns spatial-temporal prediction and action generation by jointly denoising future spatial-temporal latents and actions through a unified diffusion process. To bridge 2D visual tokens and 3D metric control, STARRY introduces Geometry-Aware Selective Attention Modulation (GASAM), which converts predicted depth and end-effector geometry into token-aligned weights for selective action-attention modulation. On RoboTwin 2.0, STARRY achieves 93.82% / 93.30% average success under Clean and Randomized settings across 50 bimanual tasks. Real-world experiments show that STARRY improves average success from 42.5% to 70.8% compared with $\pi_{0.5}$. These results demonstrate the effectiveness of action-centric spatial-temporal world modeling for spatially and temporally demanding robotic manipulation.

cs.RO↗

arXiv2026

DanceCrafter: Fine-Grained Text-Driven Controllable Dance Generation via Choreographic Syntax

Text-driven controllable dance generation remains under-explored, primarily due to the severe scarcity of high-quality datasets and the inherent difficulty of articulating complex choreographies. Characterizing dance is particularly challenging owing to its intricate spatial dynamics, strong directionality, and the highly decoupled movements of distinct body parts. To overcome these bottlenecks, we bridge principles from dance studies, human anatomy, and biomechanics to propose \textit{Choreographic Syntax}, a novel theoretical framework with a tailored annotation system. Grounded in this syntax, we combine professional dance archives with high-fidelity motion capture data to construct \textbf{DanceFlow}, the most fine-grained dance dataset to date. It encompasses 41 hours of high-quality motions paired with 6.34 million words of detailed descriptions. At the model level, we introduce \textbf{DanceCrafter}, a tailored motion transformer built upon the Momentum Human Rig. To circumvent optimization instabilities, we construct a continuous manifold motion representation paired with a hybrid normalization strategy. Furthermore, we design an anatomy-aware loss to explicitly regulate the decoupled nature of body parts. Together, these adaptations empower DanceCrafter to achieve the high-fidelity and stable generation of complex dance sequences. Extensive evaluations and user studies demonstrate our state-of-the-art performance in motion quality, fine-grained controllability, and generation naturalness.

cs.CV↗

arXiv2026

3D-Mix for VLA: A Plug-and-Play Module for Integrating VGGT-based 3D Information into Vision-Language-Action Models

Vision-Language-Action (VLA) models leverage Multimodal Large Language Models (MLLMs) for robotic control, but recent studies reveal that MLLMs exhibit limited spatial intelligence due to training predominantly on 2D data, resulting in inadequate 3D perception for manipulation tasks. While recent approaches incorporate specialized 3D vision models such as VGGT to enhance spatial understanding, they employ diverse integration mechanisms without systematic investigation, leaving the optimal fusion strategy unclear. We conduct a comprehensive pilot study comparing nine VGGT integration schemes on standardized benchmarks and find that semantic-conditioned gated fusion, which adaptively balances 2D semantic and 3D geometric features based on task context, achieved the strongest performance among all nine evaluated fusion schemes in our pilot study. We present 3D-Mix, a plug-and-play module that integrates into diverse VLA architectures (GR00T-style and $\pi$-style) without modifying existing MLLM or action expert components. Experiments across six MLLM series (nine model variants, 2B--8B parameters) on SIMPLER and LIBERO show that 3D-Mix delivers consistent performance gains, averaging +7.0% on the out-of-domain (OOD) SIMPLER benchmark across all nine GR00T-style variants, establishing a principled approach for enhancing spatial intelligence in VLA systems.

cs.RO↗

arXiv2026

CyboRacket: A Perception-to-Action Framework for Humanoid Racket Sports

Dynamic ball-interaction tasks remain challenging for robots because they require tight perception-action coupling under limited reaction time. This challenge is especially pronounced in humanoid racket sports, where successful interception depends on accurate visual tracking, trajectory prediction, coordinated stepping, and stable whole-body striking. Existing robotic racket-sport systems often rely on external motion capture for state estimation or on task-specific low-level controllers that must be retrained across tasks and platforms. We present CyboRacket, a hierarchical perception-to-action framework for humanoid racket sports that integrates onboard visual perception, physics-based trajectory prediction, and large-scale pre-trained whole-body control. The framework uses onboard cameras to track the incoming object, predicts its future trajectory, and converts the estimated interception state into target end-effector and base-motion commands for whole-body execution by SONIC on the Unitree G1 humanoid robot. We evaluate the proposed framework in a vision-based humanoid tennis-hitting task. Experimental results demonstrate real-time visual tracking, trajectory prediction, and successful striking using purely onboard sensing.

cs.RO↗

arXiv2026

Cybo-Waiter: A Physical Agentic Framework for Humanoid Whole-Body Locomotion-Manipulation

Robots are increasingly expected to execute open ended natural language requests in human environments, which demands reliable long horizon execution under partial observability. This is especially challenging for humanoids because locomotion and manipulation are tightly coupled through stance, reachability, and balance. We present a humanoid agent framework that turns VLM plans into verifiable task programs and closes the loop with multi object 3D geometric supervision. A VLM planner compiles each instruction into a typed JSON sequence of subtasks with explicit predicate based preconditions and success conditions. Using SAM3 and RGB-D, we ground all task relevant entities in 3D, estimate object centroids and extents, and evaluate predicates over stable frames to obtain condition level diagnostics. The supervisor uses these diagnostics to verify subtask completion and to provide condition-level feedback for progression and replanning. We execute each subtask by coordinating humanoid locomotion and whole-body manipulation, selecting feasible motion primitives under reachability and balance constraints. Experiments on tabletop manipulation and long horizon humanoid loco manipulation tasks show improved robustness from multi object grounding, temporal stability, and recovery driven replanning.

cs.RO↗

arXiv2026

ScalSelect: Scalable Training-Free Multimodal Data Selection for Efficient Visual Instruction Tuning

Large-scale Visual Instruction Tuning (VIT) has become a key paradigm for advancing the performance of vision-language models (VLMs) across various multimodal tasks. However, training on the large-scale datasets is computationally expensive and inefficient due to redundancy in the data, which motivates the need for multimodal data selection to improve training efficiency. Existing data selection methods for VIT either require costly training or gradient computation. Training-free alternatives often depend on proxy models or datasets, instruction-agnostic representations, and pairwise similarity with quadratic complexity, limiting scalability and representation fidelity. In this work, we propose ScalSelect, a scalable training-free multimodal data selection method with linear-time complexity with respect to the number of samples, eliminating the need for external models or auxiliary datasets. ScalSelect first constructs sample representations by extracting visual features most attended by instruction tokens in the target VLM, capturing instruction-relevant information. It then identifies samples whose representations best approximate the dominant subspace of the full dataset representations, enabling scalable importance scoring without pairwise comparisons. Extensive experiments across multiple VLMs, datasets, and selection budgets demonstrate that ScalSelect achieves over 97.5% of the performance of training on the full dataset using only 16% of the data, and even outperforms full-data training in some settings. The code is available at \href{https://github.com/ChangtiWu/ScalSelect}{ScalSelect}.

cs.CV↗

arXiv2026

A$^2$-LLM: An End-to-end Conversational Audio Avatar Large Language Model

Developing expressive and responsive conversational digital humans is a cornerstone of next-generation human-computer interaction. While large language models (LLMs) have significantly enhanced dialogue capabilities, most current systems still rely on cascaded architectures that connect independent modules. These pipelines are often plagued by accumulated errors, high latency, and poor real-time performance. Lacking access to the underlying conversational context, these pipelines inherently prioritize rigid lip-sync over emotional depth. To address these challenges, we propose A$^2$-LLM, an end-to-end conversational audio avatar large language model that jointly reasons about language, audio prosody, and 3D facial motion within a unified framework. To facilitate training, we introduce FLAME-QA, a high-quality multimodal dataset designed to align semantic intent with expressive facial dynamics within a QA format. By leveraging deep semantic understanding, A$^2$-LLM generates emotionally rich facial movements beyond simple lip-synchronization. Experimental results demonstrate that our system achieves superior emotional expressiveness while maintaining real-time efficiency (500 ms latency, 0.7 RTF).

cs.LG↗