Searcharxiv⌕ Search

arXiv subjects

Chuheng Zhang

Publications and source records attributed to Chuheng Zhang.

At least 19 recordsLinked to original sources
arXiv2026

UniSteer: Unified Noise Steering for Efficient Human-Guided VLA Adaptation

Diffusion-based vision-language-action (VLA) models have emerged as strong priors for robotic manipulation, yet adapting them to real-world distributions remains challenging. In particular, on-robot reinforcement learning (RL) is expensive and time-consuming, so effective adaptation depends on efficient policy improvement within a limited budget of real-world interactions. Noise-space RL lowers the cost by keeping the pretrained VLA fixed as a denoising generator while updating only a lightweight actor that predicts the noise. However, its performance is still limited due to inefficient autonomous exploration. Human corrective interventions can reduce this exploration burden, but they are naturally provided in action space, whereas noise-space finetuning requires supervision over noise variables. To address these challenges, we propose UniSteer, a Unified Noise Steering framework that combines human corrective guidance with noise-space RL through approximate action-to-noise inversion. Given a human corrective action, UniSteer inverts the frozen flow-matching decoder to recover a noise target, which provides supervised guidance for the same noise actor that is simultaneously optimized via reinforcement learning. Real-world experiments on diverse manipulation tasks show that UniSteer adapts more efficiently than strong noise-space RL and action-space human-in-the-loop baselines, improving the success rate from 20% to 90% in 66 minutes on average across four real-world adaptation tasks.

cs.RO↗
arXiv2026

Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot Imitation

Human demonstrations for robot imitation learning often contain mistakes and corrective behaviors, such as imprecise grasps, object misalignment, unstable contact, and repeated attempts. While these segments are commonly treated as noisy or suboptimal data, they provide valuable evidence about when execution deviates from a desirable path and how task feasibility can be restored. However, existing reward and value models often rely on monotonic progress assumptions, which capture coarse task advancement but may overlook local execution errors and corrective behaviors in imperfect demonstrations. In this work, we propose ReTVL (ReTry-Supervised Value Learning), a framework for learning mistake-sensitive value functions from mixed-quality robot demonstrations by leveraging retry events as sparse supervision. ReTVL captures the local degradation-and-recovery structure around mistakes by combining global progress calibration with local pairwise preference learning induced by sparsely annotated retry keypoints. The learned value model is then used to reweight demonstration chunks for downstream behavior cloning, reducing the influence of harmful execution errors while preserving useful corrective behaviors. Experiments on real-robot manipulation tasks show that ReTVL produces more fine-grained value estimates than progress-based baselines and improves imitation learning from imperfect demonstrations.

cs.RO↗
arXiv2026

ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training

We study how to improve large foundation vision-language-action (VLA) systems through human-in-the-loop reinforcement learning (RL) in real-world environments. A key challenge is learning reliable value functions from heterogeneous real-world experience, as value estimation provides the primary learning signal for VLA training. In practice, replay buffers contain trajectories collected from historical policies, online rollouts, demonstrations, and intermittent human interventions. Because replay buffers mix trajectories generated by different behaviors, the observed returns can be mismatched with the quality of the current policy. Prior VLA post-training methods often rely on progress-style value signals, which reflect the average quality of historical behaviors, leading to mismatched learning signals for the current policy. In this paper, we propose ALOE, an off-policy evaluation framework whose value function directly evaluates current-policy behavior for each iteration. Specifically, ALOE combines chunked temporal-difference bootstrapping and conservative value aggregation to perform stable current-policy evaluation, then uses these estimates for advantage-weighted policy improvement. This design improves credit assignment to critical action chunks under sparse rewards and supports stable policy improvement. We evaluate ALOE on four real-world manipulation tasks encompassing long-horizon and high-precision scenarios: smartphone packing, laundry folding, multi-object sorting, and phone assembly. Across all tasks, ALOE outperforms other VLA post-training methods, highlighting the benefit of off-policy value estimates for real-world VLA post-training. Videos are available at our project website https://rooshy-yang.github.io/aloe.

cs.RO↗
arXiv2026

What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models

Reinforcement learning (RL) fine-tuning has shown promise for Vision-Language-Action (VLA) models in robotic manipulation, but deployment-time visual shifts pose practical challenges. A key difficulty is that standard task rewards supervise task success, but offer limited guidance on whether a visual change is task-irrelevant or changes the behavior required for manipulation. We propose PAIR-VLA (Paired Action Invariance & Sensitivity for Visually Robust VLA), an RL fine-tuning framework to address this difficulty by adding two auxiliary objectives over paired visual variants during PPO optimization: an invariance term that reduces the discrepancy between action distributions for a task-preserving pair (e.g., different distractors), and a sensitivity objective that encourages separable action distributions for a task-altering pair (e.g., target object in a different pose). Together, these objectives turn visual variants from mere observation diversity into behavior-level guidance on policy responses during RL fine-tuning. We evaluate on ManiSkill3 across two representative VLA architectures, OpenVLA and $π_{0.5}$, under diverse out-of-distribution visual shifts including unseen distractors, texture changes, target object pose variation, viewpoint shifts, and lighting changes. Our method consistently improves over standard PPO, achieving average improvements of 16.62% on $π_{0.5}$ and 9.10% on OpenVLA. Notably, ablations further show generalization across visual shifts: invariance guidance learned from distractor and texture variants transfers to target-pose and lighting shifts, while adding sensitivity guidance on target-pose variants further improves robustness to nuisance shifts, highlighting the broader transferability of behavior-level RL guidance.

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↗
arXiv2026

Enhancing LLM Reasoning via Non-Human-Like Reasoning Path Preference Optimization

Current approaches for strengthening LLM reasoning tend to introduce a training bias toward human-like reasoning trajectories. In step-wise preference optimization, in particular, dependence on human or higher-capacity model annotations for intermediate steps limits exploration of alternative, non-human-like reasoning paths and thus constrains achievable performance. Furthermore, through a small-scale pilot study, we observed that in approximately 75% of cases, the model's first erroneous step occurs after the lowest-confidence point. This suggests that guiding the model at its lowest-confidence point before an error provides more accurate supervision than locating the first explicit error. In this paper, we propose Confidence-Guided Reasoning Path Preference Optimization (CGPO), a method that leverages a confidence signal to identify points of maximal uncertainty in the model's reasoning process and applies self-generated, non-human-like reasoning-path guidance to mitigate trajectory drift. Our experiments span diverse models applied to both code and mathematical reasoning tasks. The results show that, with the same amount of training data, our method using data generated by a small model can achieve better performance in most cases compared with approaches using data generated by a strong model or human-annotated.

cs.CL↗
arXiv2026

ChatAD: Reasoning-Enhanced Time-Series Anomaly Detection with Multi-Turn Instruction Evolution

LLM-driven Anomaly Detection (AD) helps enhance the understanding and explanatory abilities of anomalous behaviors in Time Series (TS). Existing methods face challenges of inadequate reasoning ability, deficient multi-turn dialogue capability, and narrow generalization. To this end, we 1) propose a multi-agent-based TS Evolution algorithm named TSEvol. On top of it, we 2) introduce the AD reasoning and multi-turn dialogue Dataset TSEData-20K and contribute the Chatbot family for AD, including ChatAD-Llama3-8B, Qwen2.5-7B, and Mistral-7B. Furthermore, 3) we propose the TS Kahneman-Tversky Optimization (TKTO) to enhance ChatAD's cross-task generalization capability. Lastly, 4) we propose a LLM-driven Learning-based AD Benchmark LLADBench to evaluate the performance of ChatAD and nine baselines across seven datasets and tasks. Our three ChatAD models achieve substantial gains, up to 34.50% in accuracy, 34.71% in F1, and a 37.42% reduction in false positives. Besides, via KTKO, our optimized ChatAD achieves competitive performance in reasoning and cross-task generalization on classification, forecasting, and imputation.

cs.AI↗
arXiv2025

Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories

Scaling vision-language-action (VLA) model pre-training requires large volumes of diverse, high-quality manipulation trajectories. Most current data is obtained via human teleoperation, which is expensive and difficult to scale. Reinforcement learning (RL) methods learn useful skills through autonomous exploration, making them a viable approach for generating data. However, standard RL training collapses to a narrow execution pattern, limiting its utility for large-scale pre-training. We propose Discover, Lea rn and Reinforce (DLR), an information-theoretic pattern discovery framework that generates multiple distinct, high-success behavioral patterns for VLA pretraining. Empirically, DLR generates a markedly more diverse trajectory corpus on LIBERO. Specifically, it learns multiple distinct, high-success strategies for the same task where standard RL discovers only one, and hence it covers substantially broader regions of the state-action space. When adapted to unseen downstream task suites, VLA models pretrained on our diverse RL data surpass counterparts trained on equal-sized standard RL datasets. Moreover, DLR exhibits positive data-scaling behavior that single-pattern RL lacks. These results position multi-pattern RL as a practical, scalable data engine for embodied foundation models.

cs.RO↗
arXiv2025

What Do Latent Action Models Actually Learn?

Latent action models (LAMs) aim to learn action-relevant changes from unlabeled videos by compressing changes between frames as latents. However, differences between video frames can be caused by controllable changes as well as exogenous noise, leading to an important concern -- do latents capture the changes caused by actions or irrelevant noise? This paper studies this issue analytically, presenting a linear model that encapsulates the essence of LAM learning, while being tractable.This provides several insights, including connections between LAM and principal component analysis (PCA), desiderata of the data-generating policy, and justification of strategies to encourage learning controllable changes using data augmentation, data cleaning, and auxiliary action-prediction. We also provide illustrative results based on numerical simulation, shedding light on the specific structure of observations, actions, and noise in data that influence LAM learning.

cs.LG↗
arXiv2025

How Do VLAs Effectively Inherit from VLMs?

Vision-language-action (VLA) models hold the promise to attain generalizable embodied control. To achieve this, a pervasive paradigm is to leverage the rich vision-semantic priors of large vision-language models (VLMs). However, the fundamental question persists: How do VLAs effectively inherit the prior knowledge from VLMs? To address this critical question, we introduce a diagnostic benchmark, GrinningFace, an emoji tabletop manipulation task where the robot arm is asked to place objects onto printed emojis corresponding to language instructions. This task design is particularly revealing -- knowledge associated with emojis is ubiquitous in Internet-scale datasets used for VLM pre-training, yet emojis themselves are largely absent from standard robotics datasets. Consequently, they provide a clean proxy: successful task completion indicates effective transfer of VLM priors to embodied control. We implement this diagnostic task in both simulated environment and a real robot, and compare various promising techniques for knowledge transfer. Specifically, we investigate the effects of parameter-efficient fine-tuning, VLM freezing, co-training, predicting discretized actions, and predicting latent actions. Through systematic evaluation, our work not only demonstrates the critical importance of preserving VLM priors for the generalization of VLA but also establishes guidelines for future research in developing truly generalizable embodied AI systems.

cs.RO↗
arXiv2025

Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Training

Vision-language-action (VLA) models have shown strong generalization across tasks and embodiments; however, their reliance on large-scale human demonstrations limits their scalability owing to the cost and effort of manual data collection. Reinforcement learning (RL) offers a potential alternative to generate demonstrations autonomously, yet conventional RL algorithms often struggle on long-horizon manipulation tasks with sparse rewards. In this paper, we propose a modified diffusion policy optimization algorithm to generate high-quality and low-variance trajectories, which contributes to a diffusion RL-powered VLA training pipeline. Our algorithm benefits from not only the high expressiveness of diffusion models to explore complex and diverse behaviors but also the implicit regularization of the iterative denoising process to yield smooth and consistent demonstrations. We evaluate our approach on the LIBERO benchmark, which includes 130 long-horizon manipulation tasks, and show that the generated trajectories are smoother and more consistent than both human demonstrations and those from standard Gaussian RL policies. Further, training a VLA model exclusively on the diffusion RL-generated data achieves an average success rate of 81.9%, which outperforms the model trained on human data by +5.3% and that on Gaussian RL-generated data by +12.6%. The results highlight our diffusion RL as an effective alternative for generating abundant, high-quality, and low-variance demonstrations for VLA models.

cs.RO↗
arXiv2025

villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

Vision-Language-Action (VLA) models have emerged as a popular paradigm for learning robot manipulation policies that can follow language instructions and generalize to novel scenarios. Recent works have begun to explore the incorporation of latent actions, abstract representations of motion between two frames, into VLA pre-training. In this paper, we introduce villa-X, a novel Vision-Language-Latent-Action (ViLLA) framework that advances latent action modeling for learning generalizable robot manipulation policies. Our approach improves both how latent actions are learned and how they are incorporated into VLA pre-training. We demonstrate that villa-X can generate latent action plans in a zero-shot fashion, even for unseen embodiments and open-vocabulary symbolic understanding. This capability enables villa-X to achieve superior performance across diverse simulation tasks in SIMPLER and on two real-world robotic setups involving both gripper and dexterous hand manipulation. These results establish villa-X as a principled and scalable paradigm for learning generalizable robot manipulation policies. We believe it provides a strong foundation for future research.

cs.RO↗
arXiv2025

PIG-Nav: Key Insights for Pretrained Image Goal Navigation Models

Recent studies have explored pretrained (foundation) models for vision-based robotic navigation, aiming to achieve generalizable navigation and positive transfer across diverse environments while enhancing zero-shot performance in unseen settings. In this work, we introduce PIG-Nav (Pretrained Image-Goal Navigation), a new approach that further investigates pretraining strategies for vision-based navigation models and contributes in two key areas. Model-wise, we identify two critical design choices that consistently improve the performance of pretrained navigation models: (1) integrating an early-fusion network structure to combine visual observations and goal images via appropriately pretrained Vision Transformer (ViT) image encoder, and (2) introducing suitable auxiliary tasks to enhance global navigation representation learning, thus further improving navigation performance. Dataset-wise, we propose a novel data preprocessing pipeline for efficiently labeling large-scale game video datasets for navigation model training. We demonstrate that augmenting existing open navigation datasets with diverse gameplay videos improves model performance. Our model achieves an average improvement of 22.6% in zero-shot settings and a 37.5% improvement in fine-tuning settings over existing visual navigation foundation models in two complex simulated environments and one real-world environment. These results advance the state-of-the-art in pretrained image-goal navigation models. Notably, our model maintains competitive performance while requiring significantly less fine-tuning data, highlighting its potential for real-world deployment with minimal labeled supervision.

cs.CV↗
arXiv2025

Policy Filtration for RLHF to Mitigate Noise in Reward Models

While direct policy optimization methods exist, pioneering LLMs are fine-tuned with reinforcement learning from human feedback (RLHF) to generate better responses under the supervision of a reward model learned from preference data. One major challenge of RLHF is the inaccuracy of the intermediate reward model, especially in the tasks that requires complex reasoning for the reward model to score a response. We find that the reliability of the reward model varies across responses assigned with different rewards. This motivates us to filter the samples whose rewards may be unreliable to improve the signal-to-noise ratio during policy learning, resulting in Policy Filtration for Proximal Policy Optimization (PF-PPO). To choose a proper policy filtering strategy, we use the coefficient of determination (R2) between the rewards and actual scores on filtered samples as the metrics to help us find promising strategies since it measures how well the rewards filtered by PF-PPO indicate real performance. We provide extensive experiments to validate the effectiveness of PF-PPO in code generation and math reasoning tasks. In code generation, PF-PPO achieves the state-of-the-art performance of 7-billion-parameter models on HumanEval (+7.9%), MBPP (+0.7%), and LeetCode Contest (+10.0%) which is a more challenging benchmark created by us. In math reasoning, PF-PPO yields performance increase using different reward models and benchmarks (Ape210K and CMATH). Code is available on https://github.com/DtYXs/verl/tree/pf-ppo.

cs.LG↗
arXiv2025

AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence

Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step's length into a fixed size. These approaches overlook the fact that specific words do not typically mark true decision points in a text. To address this, we propose AdaptiveStep, a method that divides reasoning steps based on the model's confidence in predicting the next word. This division method provides more decision-making information at each step, enhancing downstream tasks, such as reward model learning. Moreover, our method does not require manual annotation. We demonstrate its effectiveness through experiments with AdaptiveStep-trained PRMs in mathematical reasoning and code generation tasks. Experimental results indicate that the outcome PRM achieves state-of-the-art Best-of-N performance, surpassing greedy search strategy with token-level value-guided decoding, while also reducing construction costs by over 30% compared to existing open-source PRMs. In addition, we provide a thorough analysis and case study on the PRM's performance, transferability, and generalization capabilities.

cs.AI↗
arXiv2025

Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Prediction

Reward-driven proactive dialogue agents require precise estimation of user satisfaction as an intrinsic reward signal to determine optimal interaction strategies. Specifically, this framework triggers clarification questions when detecting potential user dissatisfaction during interactions in the industrial dialogue system. Traditional works typically rely on training a neural network model based on weak labels which are generated by a simple model trained on user actions after current turn. However, existing methods suffer from two critical limitations in real-world scenarios: (1) Noisy Reward Supervision, dependence on weak labels derived from post-hoc user actions introduces bias, particularly failing to capture satisfaction signals in ASR-error-induced utterances; (2) Long-Tail Feedback Sparsity, the power-law distribution of user queries causes reward prediction accuracy to drop in low-frequency domains. The noise in the weak labels and a power-law distribution of user utterances results in that the model is hard to learn good representation of user utterances and sessions. To address these limitations, we propose two auxiliary tasks to improve the representation learning of user utterances and sessions that enhance user satisfaction prediction. The first one is a contrastive self-supervised learning task, which helps the model learn the representation of rare user utterances and identify ASR errors. The second one is a domain-intent classification task, which aids the model in learning the representation of user sessions from long-tailed domains and improving the model's performance on such domains. The proposed method is evaluated on DuerOS, demonstrating significant improvements in the accuracy of error recognition on rare user utterances and long-tailed domains.

cs.LG↗
arXiv2024

IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

We introduce Image-GOal Representations (IGOR), aiming to learn a unified, semantically consistent action space across human and various robots. Through this unified latent action space, IGOR enables knowledge transfer among large-scale robot and human activity data. We achieve this by compressing visual changes between an initial image and its goal state into latent actions. IGOR allows us to generate latent action labels for internet-scale video data. This unified latent action space enables the training of foundation policy and world models across a wide variety of tasks performed by both robots and humans. We demonstrate that: (1) IGOR learns a semantically consistent action space for both human and robots, characterizing various possible motions of objects representing the physical interaction knowledge; (2) IGOR can "migrate" the movements of the object in the one video to other videos, even across human and robots, by jointly using the latent action model and world model; (3) IGOR can learn to align latent actions with natural language through the foundation policy model, and integrate latent actions with a low-level policy model to achieve effective robot control. We believe IGOR opens new possibilities for human-to-robot knowledge transfer and control.

cs.RO↗
arXiv2024

Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL

With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses. Prompt tuning regards selecting appropriate keywords included into the input, thereby adapting to the downstream task without adjusting or fine-tuning the model parameters. There is a wide range of work in prompt tuning, from approaches that directly harness the backpropagated gradient signals from the model, to those employing black-box optimization such as reinforcement learning (RL) methods. Our primary focus is on RLPrompt, which aims to find optimal prompt tokens leveraging soft Q-learning. While the results show promise, we have observed that the prompts frequently appear unnatural, which impedes their interpretability. We address this limitation by using sparse Tsallis entropy regularization, a principled approach to filtering out unlikely tokens from consideration. We extensively evaluate our approach across various tasks, including few-shot text classification, unsupervised text style transfer, and textual inversion from images. The results indicate a notable improvement over baselines, highlighting the efficacy of our approach in addressing the challenges of prompt tuning. Moreover, we show that the prompts discovered using our method are more natural and interpretable compared to those from other baselines.

cs.LG↗