arXiv subjects

Jianyu Chen

Publications and source records attributed to Jianyu Chen.

At least 19 recordsLinked to original sources

arXiv2026

HITCH: Teaching a Vision-Language Model to Operate a Humanoid through a Whole-Body Harness

Enabling vision-language models (VLMs) to control humanoid robots requires both reliable whole-body interfaces and knowledge of how to use the body that carries over across tasks. We present HITCH (Harness Interfaces To Command Humanoids), a harness in which perception returns the 3D position of any point the VLM selects in its image, and execution turns commands for the pelvis, torso, hands, walking, and gaze into whole-body motion with a learned tracker. We find that both measuring the scene and executing commands accurately raise task success. We then fine-tune a VLM on trajectories in which teacher policies solve five base tasks through HITCH, so that it learns how to operate the humanoid. Without task-specific trajectories, the fine-tuned model completes 51% of SIMPLE episodes and 42.5% of HumanoidArena episodes, and adding five trajectories per SIMPLE task raises its SIMPLE success to 95%. On a real G1, it carries a box and walks to a goal without real training data.

cs.RO↗

arXiv2026

HiLo-WAM: Decoupling Long-Horizon Task Evolution and Local Dynamics in World Action Models

World Action Models (WAMs) improve robotic manipulation by jointly modeling visual dynamics and robot actions. However, most existing WAMs model dense short-horizon visual dynamics, capturing local interactions but providing limited long-range task context. Extending prediction horizons increases uncertainty and computation while entangling task-level evolution with fine-grained local dynamics, obscuring their dependencies and distinct roles in action generation. We propose HiLo-WAM, which decouples long-horizon task evolution from local visual dynamics while jointly modeling their interaction with robot actions. A sparse long-horizon visual stream captures historical task context and future evolution, while a dense local dynamics visual stream models short-horizon robot-object interactions. The two streams operate at different temporal scales within a unified dual-DiT architecture and guide actions through structured cross-stream attention. Progressive inference further reduces unnecessary computation through stream-wise partial denoising, joint denoising, and dynamic skipping. Experiments demonstrate strong long-horizon manipulation performance: HiLo-WAM achieves a 93.70% average success rate on RoboTwin 2.0 and a 17.43 progress score on RoboDojo long-horizon tasks, with robust in-domain and OOD performance on the Fourier GR-3 robot. Ablations confirm the complementary contributions of long-horizon task evolution and local interaction dynamics, while temporal-scale analyses highlight the importance of balancing temporal coverage and resolution. Progressive inference further achieves a 2.93x speedup while improving performance.

cs.RO↗

arXiv2026

Video Prediction Policy 2: Predict Better, Act Better

World action models (WAMs) have emerged as an important class of generalist robot policies, aiming to transfer video prediction priors to action learning. However, we find that existing WAMs frequently produce incorrect motion predictions in open-ended environment, leading to erroneous actions. We attribute this limitation to two factors: (1) base video models are not optimized for manipulation, and (2) naively incorporating action components into video models can substantially degrade their generalization capabilities. We introduce Video Prediction Policy 2 (VPP2), a WAM that enables strong zero-shot generalization in both video prediction and action generation. First, we curate a large-scale, diverse dataset of manipulation videos to continue pretraining the base video foundation model. We annotate video clips with detailed captions and perform \textit{event-level} video pretraining to promote generalization across open-ended manipulation tasks. Second, we post-train and distill the video model into a single-step visual planner with fixed prediction horizon. Finally, we introduce action module via a mixture-of-transformers (MoT) architecture to learn implicit inverse dynamics model. Experiments demonstrate three key results: (1) VPP2-14B outperforms Cosmos3-64B by 11.0\% points in video prediction instruction-following success rate on open-ended tasks; (2) VPP2 surpasses the strongest baseline by 18.5\% points in success rate on real-world zero-shot ALOHA manipulation tasks; and (3) following benchmark-specific post-training, VPP2 achieves the highest success rates among evaluated methods on the challenging LIBERO-Pro, LIBERO-OOD, and RoboDojo benchmarks.

cs.CV↗

arXiv2026

RoboDuo: Attempt, Check and Atomic Recovery through Code for Vision-Language-Action Models

Vision-Language-Action (VLA) models map a language instruction and the current observation directly to actions, without checking whether the instruction has been completed. For long-horizon tasks, a single failed step therefore goes unnoticed and leaves the whole task unfinished. Such failed episodes, however, often end with the task partially complete. Moreover, the unfinished steps are reusable atomic skills that recur across demonstrations. A failed attempt can thus be recovered by composing with atomic skills. We propose RoboDuo, a closed-loop dual-system framework that uses code as the interface between a coding agent and two VLAs. The agent writes a program that lets a full-task VLA attempt the whole task and checks whether it is complete; on failure, an atomic VLA finishes the remaining steps. Since the agent emits no actions and only decides which VLA for execution, RoboDuo wraps an existing full-task VLA without updating its weights. To train the atomic VLA and the coding agent with the completion-checking ability, we build LIBERO-Atomic, LIBERO-Code, and LIBERO-Judge from a single set of LIBERO demonstrations. RoboDuo consistently improves X-VLA and $π_{0.5}$ on LIBERO and LIBERO-PRO, with the largest gains on long-horizon tasks, and recovers failed rollouts of a frozen full-task VLA on a real robot.

cs.RO↗

arXiv2026

EXE: Egocentric Cross-Embodiment Pretraining via Factorized Latent Actions for VLA Models

Vision-Language-Action (VLA) models are bottlenecked by the scarcity of robot data. Egocentric human manipulation videos offer an abundant, diverse, and semantically-rich alternative that inherently captures manipulation intent. However, the embodiment gap makes it difficult to extract action-relevant representations from these videos. From the perspective of action execution, human hands and robots share analogous manipulation primitives---reaching, grasping, placing---yet exhibit distinct kinematics tied to their embodiments. This might motivate our key approach: egocentric video pretraining can yield shared action representations capturing transferable manipulation skills, while human-specific motion patterns should be disentangled to avoid interfering with robot policy learning. To this end, we propose EXE, an Egocentric Cross(X)-Embodiment pretraining framework that learns a factorized latent action representation from egocentric human videos, separating shared manipulation priors from embodiment-specific signals. By leveraging the shared action space, the robot policy acquires generalizable manipulation semantics from diverse human demonstrations without being biased by human-specific kinematics. This shared knowledge transfers across embodiments with different kinematic structures, enabling the same pretraining to benefit both parallel grippers and dexterous hands. EXE yields consistent gains over baseline without pretraining on RoboTwin 2.0, RoboCasa GR1, and real-world manipulation tasks.

cs.RO↗

arXiv2026

HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model

Learning generalizable vision-language-action (VLA) models from large-scale human videos is promising but challenging due to cross-embodiment discrepancies in both visual observations and executable actions. While latent action models reduce the action execution gap by learning action abstractions, they still rely on visual features. Thus, misaligned human and robot visual representations can lead to inconsistencies in policy inputs and induce domain-dependent latent actions, hindering effective co-training with human videos.To address this, we propose HARP, a human-robot aligned representation learning framework for more effective VLA pretraining from human videos. Specifically, HARP uses paired human-robot demonstrations as cross-embodiment bridges and abundant unpaired human and robot videos as a scalable dynamics supervision data source. It trains a robot-adapted visual encoder and a latent action model with manipulation-centric auxiliary cues and a source-relative pair-discriminative alignment loss, which adapts robot representations toward human semantics while preserving pair-level discrimination. The learned aligned vision encoder and latent action model provide a unified vision and action representation for VLA-style policy learning, where human and robot videos provide vision-language-to-latent-action supervision and a lightweight robot action head grounds latent actions into executable commands. Experiments on feature visualization, simulation, and real-world manipulation show improved human-robot alignment and downstream policy performance, achieving 4.481 average length on CALVIN ABC$\rightarrow$D and a 7.1 percentage-point improvement in real-world success rate over the strongest evaluated baseline. Code, videos, and demos are available at https://puzhenyuan.github.io/HARP-VLA-website/.

cs.RO↗

arXiv2026

GALA: Geometry-Aware Latent Action Modeling for Vision-Language-Action Model Pretraining across Embodiments

Learning large-scale vision-language-action (VLA) models from multi-embodiment datasets remains challenging due to heterogeneous action spaces across end effectors. Although latent action models (LAMs) can learn embodiment-agnostic action representations from diverse video data, existing image-based LAMs often fail to capture fine-grained end-effector articulation, particularly finger-level geometric changes in human and dexterous robot hands. To address this limitation, we propose GALA, a Geometry-Aware Latent-Action modeling framework that augments image-based latent actions with 3D end-effector geometric motion. However, naively incorporating point clouds yields fine-grained action representations with limited shared semantics, hindering cross-embodiment pretraining. To address this issue, we introduce the Unified End-effector Motion Representation (UEMR), which preserves fine-grained motion information while improving the cross-embodiment generalizability of latent actions. Building upon UEMR, GALA combines visual latent actions that capture scene-level dynamics with geometric latent actions that capture shared fine-grained end-effector articulation, providing effective supervision for VLA pretraining from multi-embodiment data, including action-free ego-centric human videos. Experiments on fine-grained motion probing, cross-embodiment retrieval, and downstream VLA evaluation demonstrate GALA's effectiveness in modeling generalizable fine-grained motions across embodiments, achieving 68.3% RoboCasa-GR1 success rate and 75.5% real-world success rate. Code, appendix, and demos are available at https://puzhenyuan.github.io/GALA-website/.

cs.RO↗

arXiv2026

Veo-Act: Enhancing VLA Policies with Frontier Video Models

Video generation models can produce coherent vi- sual sequences depicting object motion and interactions. We in- vestigate how frontier video generation models can complement vision-language-action policies to enhance generalizable robotic manipulation. VLA policies have become a dominant paradigm for robot learning, but their action-oriented adaptation of pretrained VLMs can weaken semantic generalization, limiting robustness in ambiguous or out-of-distribution manipulation scenarios. We use video models as visual planners, motivated by their potential to generalize across complex scenes and their priors over hand motion. However, manipulation methods based on video models often lack the precision and temporal responsiveness needed for low-level dexterous interaction. To address this gap, we present Veo-Act, a hierarchical framework with Veo-3.1 as a high-level motion planner and a VLA policy as the low-level executor. A multi-head inverse dynamics model converts generated frame pairs into actions and learns an interaction gate to trigger the handoff to reactive VLA control. Experiments in simulation and on a real robot show improved instruction following and overall task success over the baseline VLA in novel and semantically complex manipulation settings, supporting the complementary roles of video planning and reactive interaction.

cs.RO↗

arXiv2026

Wrench-Based Bayesian Pose Estimation via Matrix--Fisher Gaussian Inference

In this paper, a residual-safeguarded local Matrix Fisher--Gaussian (MFG) inference method is developed for wrench-based pose estimation on $\mathrm{SO}(3)\times\mathbb{R}^3$. The force/torque measurements are modeled by a quasi-static contact system in which the predicted wrench depends on the unknown object pose through an implicit equilibrium state. Since the resulting nonlinear likelihood is not globally conjugate to the coupled MFG family, a local Bayesian update is constructed by linearizing the reduced wrench residual and matching the induced Gauss--Newton posterior model to a coupled MFG distribution. It is shown that the reduced residual Jacobian has a Schur-complement form, and that the local quadratic posterior admits a closed-form MFG approximation matching the prescribed local first- and second-order posterior coefficients. The same sensitivity model yields a compensated rotational information score, which characterizes the weakest locally informative attitude direction after translational compensation. A residual-safeguarded recentering algorithm is further introduced to update the linearization point only through candidates that decrease the recomputed whitened wrench residual. In the tested sparse prior-mismatch regimes, the resulting estimator reduces residual merit and pose error relative to single-pass and local baseline variants, and controlled robot experiments provide a proof of concept under calibrated quasi-static conditions.

cs.RO↗

arXiv2026

HEFT: Heavy-Payload Full-size Humanoid Teleoperation with Privileged Motion Guidance and Windowed Payload Curriculum

General motion tracking and teleoperation offer a promising path to scalable humanoid skill acquisition, yet most existing frameworks are validated on compact platforms or without real payload interaction, leaving full-size humanoids with real payloads largely unexplored. Scaling to full-size humanoids introduces two compounding challenges: their larger inertia and tighter balance margins make tracking highly sensitive to noise, drift, and retargeting errors from commodity VR trackers, while their payload potential remains largely underutilized. We present HEFT, a heavy-payload full-size humanoid teleoperation framework that addresses both challenges. HEFT learns from deployable noisy VR references with physically plausible reconstructed references through Privileged Motion Guidance (PMG), and uses a Windowed Payload Curriculum (WPC) with expert-guided payload caps to acquire robust heavy-payload tracking. We deploy HEFT on L7, a 175cm, 65kg humanoid. The robot tracks motions including turns, forward/backward locomotion, and squats under payloads up to 24kg.

cs.RO↗

arXiv2026

VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models

Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLM) into their policy backbone, are gaining significant attention for their promising generalization capabilities. This paper revisits a fundamental yet seldom systematically studied question: how VLM choice and competence translate to downstream VLA policies performance? We introduce VLM4VLA, a minimal adaptation pipeline that converts general-purpose VLMs into VLA policies using only a small set of new learnable parameters for fair and efficient comparison. Despite its simplicity, VLM4VLA proves surprisingly competitive with more sophisticated network designs. Through extensive empirical studies on various downstream tasks across three benchmarks, we find that while VLM initialization offers a consistent benefit over training from scratch, a VLM's general capabilities are poor predictors of its downstream task performance. This challenges common assumptions, indicating that standard VLM competence is necessary but insufficient for effective embodied control. We further investigate the impact of specific embodied capabilities by fine-tuning VLMs on seven auxiliary embodied tasks (e.g., embodied QA, visual pointing, depth estimation). Contrary to intuition, improving a VLM's performance on specific embodied skills does not guarantee better downstream control performance. Finally, modality-level ablations identify the visual module in VLM, rather than the language component, as the primary performance bottleneck. We demonstrate that injecting control-relevant supervision into the vision encoder of the VLM yields consistent gains, even when the encoder remains frozen during downstream fine-tuning. This isolates a persistent domain gap between current VLM pretraining objectives and the requirements of embodied action-planning.

cs.CV↗

arXiv2026

Learning Generalizable Robot Policy with Human Demonstration Video as a Prompt

Recent robot learning methods commonly rely on imitation learning from massive robotic dataset collected with teleoperation. When facing a new task, such methods generally require collecting a set of new teleoperation data and finetuning the policy. Furthermore, the teleoperation data collection pipeline is also tedious and expensive. Instead, human is able to efficiently learn new tasks by just watching others do. In this paper, we introduce a novel two-stage framework that utilizes human demonstrations to learn a generalizable robot policy. Such policy can directly take human demonstration video as a prompt and perform new tasks without any new teleoperation data and model finetuning at all. In the first stage, we train video generation model that captures a joint representation for both the human and robot demonstration video data using cross-prediction. In the second stage, we fuse the learned representation with a shared action space between human and robot using a novel prototypical contrastive loss. Empirical evaluations on real-world dexterous manipulation tasks show the effectiveness and generalization capabilities of our proposed method.

cs.RO↗

arXiv2026

Critical Transitions in Interacting Particle Systems: An Onsager-Machlup Action Functional Framework

This paper establishes an indirect approximation theorem for the most probable transition pathway of a stochastic interacting particle system in the mean-field framework. This paper studied the problem of indirect approximation of the most probable transition pathway of an interacting particle system (i.e., a high-dimensional stochastic dynamical system) and its mean field limit equation (McKean-Vlasov stochastic differential equation). This study is based on the Onsager-Machlup action functional, reformulated the problem as an optimal control problem. This paper completes the derivation using the stochastic Pontryagin's Maximum Principle. This paper proves the existence and uniqueness theorem for the solution to the mean-field optimal control problem of McKean-Vlasov stochastic differential equations and establishes a system of equations that determine the control parameters $θ^{*}$ and $θ^{N}$ respectively. There are few studies on the most probable transition pathways of stochastic interacting particle systems, it is still a great challenge to solve the most probable transition pathways directly or to approximate it with the mean field limit system. Therefore, this paper first gave the proof of correspondence between the core equation of Pontryagin's Maximum Principle, that is, Hamiltonian extreme condition equation. In other words, this relationship indirectly illustrates the correspondence between the most probable transition pathways of stochastic interacting particle systems and those of mean-field systems.

math.DS↗

arXiv2026

UAM: A Dual-Stream Perspective on Forgetting in VLA Training

Vision--language--action (VLA) models are typically built by fine-tuning a pretrained vision--language model (VLM) on action data. However, we show that this standard recipe systematically erodes the VLM's multimodal competence, a side effect we call the embodiment tax. But do VLAs have to forget? Inspired by the two-stream organization of biological vision, we trace this degradation to a structural bottleneck: current VLAs ask a single encoder to support both language-grounded semantics and control-relevant visual features, whereas biological vision separates recognition and visuomotor control into distinct pathways. Building on this view, we propose the Unified Action Model (UAM), which adds a parallel Dorsal Expert, an analog of the brain's dorsal pathway. To make the Dorsal Expert an effective second pathway and reduce the control-learning burden on the VLM, we initialize it from a pretrained generative model and train it with a mid-level reasoning objective that predicts visual dynamics. This design allows us to train the whole VLA end-to-end on action data alone: with no parameter freezing, no gradient stopping, and no auxiliary VL co-training, UAM retains over $95\%$ of the underlying VLM's multimodal capability and at the same time achieves the highest average success rate among baselines on a variety of manipulation tasks that probe out-of-distribution generalization, including unseen objects, novel object--target compositions, and instruction variation. Together, these results suggest that semantic preservation in VLAs can emerge from architectural separation itself, rather than being enforced by frozen weights or auxiliary data replay, and that this preserved semantic capability can naturally transfer from VLMs to semantic generalization in actions.

cs.CV↗

arXiv2026

Dexora: Open-source VLA for High-DoF Bimanual Dexterity

Vision-Language-Action (VLA) models have recently become a central direction in embodied AI, but current systems are restricted to either dual-gripper control or single-arm dexterous hand manipulation. While low-dimensional gripper control can often be handled with simpler methods, high-dimensional dexterous hand control benefits greatly from full end-to-end VLA learning. In this work, we introduce Dexora, the first open-source VLA system that natively targets dual-arm, dual-hand high-DoF manipulation. We design a hybrid teleoperation pipeline that decouples gross arm kinematics (captured with a custom exoskeleton backpack) from fine finger motion (markerless hand tracking via Apple Vision Pro), and that drives both a physical dual-arm dual-hand platform and an identical MuJoCo digital twin. Using that interface, we assemble a large training corpus: an embodiment-matched synthetic corpus (100K simulated trajectories, 6.5M frames) and a real-world dataset of 10K teleoperated episodes (2.92M frames). To mitigate noisy teleoperation demonstrations, we propose a data-quality-aware training recipe: an offline discriminator provides clip-level weights for diffusion-transformer policy training, down-weighting low-quality demonstrations. Empirically, Dexora outperforms competitive VLA baselines on both basic and dexterous benchmarks (e.g., average dexterous success 66.7% vs. 51.7%), attains 90% success on basic tasks, and shows robust out-of-distribution and cross-embodiment generalization. Ablations confirm the importance of real data and the discriminator for dexterity.

cs.RO↗

arXiv2026

UniJEPA: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning

Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage knowledge from large-scale pretraining, prior work (VLA) has typically built generalist policies either on top of vision-language understanding models (VLMs) or generative models. However, both semantic understanding from vision-language pretraining and visual dynamics modeling from visual-generation pretraining are crucial for embodied robots. Recent unified models of generation and understanding have demonstrated strong capabilities in both comprehension and generation through large-scale pretraining. We posit that robotic policy learning can likewise benefit from the combined strengths of understanding, planning, and continuous future representation learning. Building on this insight, we introduce UniJEPA, which acquires the ability to dynamically model high-dimensional visual features through pretraining on over 1M internet-scale instructional manipulation videos. Subsequently, UniJEPA is fine-tuned on data collected from the robot embodiment, enabling the learning of mappings from predictive representations to action tokens. Extensive experiments show our approach consistently outperforms baseline methods in terms of 9\% and 12\% across simulation environments and real-world out-of-distribution tasks.

cs.RO↗

arXiv2026

Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training

Post-training is essential for turning pretrained generalist robot policies into reliable task-specific controllers, but existing human-in-the-loop pipelines remain tied to physical execution: each correction requires robot time, scene setup, resets, and operator supervision in the real world. Meanwhile, action-conditioned world models have been studied mainly for imagination, synthetic data generation, and policy evaluation. We propose \textbf{Human-in-the-World-Model (Hi-WM)}, a post-training framework that uses a learned world model as a reusable corrective substrate for failure-targeted policy improvement. A policy is first rolled out in closed loop inside the world model; when the rollout becomes incorrect or failure-prone, a human intervenes directly in the model to provide short corrective actions. Hi-WM caches intermediate states and supports rollback and branching, allowing a single failure state to be reused for multiple corrective continuations and yielding dense supervision around behaviors that the base policy handles poorly. The resulting corrective trajectories are then added back to the training set for post-training. We evaluate Hi-WM on three real-world manipulation tasks spanning both rigid and deformable object interaction, and on two policy backbones. Hi-WM improves real-world success by 37.9 points on average over the base policy and by 19.0 points over a world-model closed-loop baseline, while world-model evaluation correlates strongly with real-world performance (r = 0.953). These results suggest that world models can serve not only as generators or evaluators, but also as effective corrective substrates for scalable robot post-training.

cs.RO↗

arXiv2026

Learning Additively Compositional Latent Actions for Embodied AI

Latent action learning infers pseudo-action labels from visual transitions, providing an approach to leverage internet-scale video for embodied AI. However, most methods learn latent actions without structural priors that encode the additive, compositional structure of physical motion. As a result, latents often entangle irrelevant scene details or information about future observations with true state changes and miscalibrate motion magnitude. We introduce Additively Compositional Latent Action Model (AC-LAM), which enforces scene-wise additive composition structure over short horizons on the latent action space. These AC constraints encourage simple algebraic structure in the latent action space~(identity, inverse, cycle consistency) and suppress information that does not compose additively. Empirically, AC-LAM learns more structured, motion-specific, and displacement-calibrated latent actions and provides stronger supervision for downstream policy learning, outperforming state-of-the-art LAMs across simulated and real-world tabletop tasks.

cs.CV↗