arXiv subjects

Ye Shi

Publications and source records attributed to Ye Shi.

At least 37 records · Page 2Linked to original sources

arXiv2026

Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation

Imitation learning with diffusion models has advanced robotic control by capturing the multi-modal action distributions. However, existing methods typically treat observations only as high-level conditions to the denoising network, rather than integrating them into the stochastic dynamics of the diffusion process itself. As a result, the sampling is forced to begin from random noise, weakening the coupling between perception and control and often yielding suboptimal performance. We propose BridgePolicy, a generative visuomotor policy that directly integrates observations into the stochastic dynamics via a diffusion-bridge formulation. By constructing an observation-informed trajectory, BridgePolicy enables sampling to start from a rich and informative prior rather than random noise, substantially improving precision and reliability in control. A key difficulty is that diffusion bridge normally connects distributions of matched dimensionality, while robotic observations are heterogeneous and not naturally aligned with actions. To overcome this, we introduce a semantic aligner to unify the visual and state inputs and align the observations with action representations, making diffusion bridge applicable to heterogeneous robot data. Extensive experiments across 52 simulation tasks on three benchmarks and 5 real-world tasks demonstrate that BridgePolicy consistently outperforms state-of-the-art generative policies. Our code is available at https://jianghcsr.github.io/BridgePolicy_page/.

cs.AI↗

arXiv2026

Steering Generative Reinforcement Learning into Stable Robotic Controller

Diffusion and flow-based generative policies provide a powerful policy class for reinforcement learning by inducing rich stochastic exploration through iterative action generation. However, the stochasticity of diffusion policies is not suitable for stable and precise control in high-dimensional robotic systems, where small action variations can accumulate into inconsistent motion and reduced robustness. To address this issue, we propose SteerGenPO, a latent-space reinforcement learning framework that steers a trained generative policy into a robust deterministic robotic controller. The key idea is to replace stochastic latent sampling of the trained generative policy with a learned latent actor that predicts a state-dependent latent input for the generative policies. This separates exploration and control: stochastic generative sampling provides diverse action proposals during policy learning, while deterministic latent steering provides stable and adaptive control at deployment. We evaluate SteerGenPO on six Isaac Lab benchmarks and a Unitree G1 locomotion task. The results show SteerGenPO improves over both classical RL and generative RL baselines, while its deterministic latent steering produces more stable inference-time behaviors and more reliable command responses.

cs.RO↗

arXiv2026

Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative Analysis

Diffusion Bridge and Flow Matching have both demonstrated compelling empirical performance in transformation between arbitrary distributions. However, there remains confusion about which approach is generally preferable, and the substantial discrepancies in their modeling assumptions and practical implementations have hindered a unified theoretical account of their relative merits. We have, for the first time, provided a unified theoretical and experimental validation of these two models. We recast their frameworks through the lens of Stochastic Optimal Control and prove that the cost function of the Diffusion Bridge is lower, guiding the system toward more stable and natural trajectories. Simultaneously, from the perspective of Optimal Transport, interpolation coefficients $t$ and $1-t$ of Flow Matching become increasingly ineffective when the training data size is reduced. To corroborate these theoretical claims, we propose a novel, powerful architecture for Diffusion Bridge built on a latent Transformer, and implement a Flow Matching model with the same structure to enable a fair performance comparison in various experiments. Comprehensive experiments are conducted across Image Restoration, Translation, and Style Transfer tasks, systematically varying both the distributional discrepancy (different difficulty) and the training data size. Extensive empirical results align perfectly with our theoretical predictions and allow us to delineate the respective advantages and disadvantages of these two models. Our code is available at https://github.com/zhukaizhen/diffusion_bridge_flow_matching.

cs.CV↗

arXiv2026

GenPO++: Generative Policy Optimization with Jacobian-free Likelihood Ratios

Generative policies provide expressive and multimodal action distributions, making them attractive for reinforcement learning (RL) in complex continuous-control tasks. Among them, flow-based policies are especially appealing because they generate actions through deterministic transport maps. However, applying such generative policies to likelihood-based on-policy learning remains limited by the difficulty of evaluating the probability of executed actions. Existing flow RL methods either replace the true action-density ratio with approximate surrogates, which can introduce biased updates, or recover exact likelihoods through dummy-action augmentation, which enlarges the policy space and increases computation. In this work, we propose GenPO++, a reversible generative policy optimization framework that uses history states as auxiliary memory in a high-order reversible ODE solver, yielding exact inversion without changing the original action dimension. The resulting generative policy map has a log-determinant determined only by fixed solver coefficients, enabling exact and Jacobian-free likelihood-ratio computation. This design preserves the expressiveness of generative flow policies while avoiding both action ratio bias and dummy-action overhead. We evaluate GenPO++ on large-scale simulated control, fine-tuning, and real-world robotic manipulation tasks, where it achieves competitive or superior performance over state-of-the-art on-policy RL methods, while improving training stability and computational efficiency.

cs.LG↗

arXiv2026

Conformal Reliability: A New Evaluation Metric for Conditional Generation

Conditional generative models have recently achieved remarkable success in various applications. However, a suitable metric for evaluating the reliability of these models, which takes into account their inherent uncertainty, is still lacking. Existing metrics, which typically assess a single output, may fail to capture the variability or potential risks in generation. In this paper, we propose a novel evaluation metric called reliability score based on conformal prediction, which measures the worst-case performance within the prediction set at a pre-specified confidence level. However, computing this score is challenging due to the high-dimensional nature of the output space and the nonconvexity of both the metric function and the prediction set. To efficiently compute this score, we introduce Conformal ReLiability (CReL), a framework that can (i) construct the prediction set with desired coverage; and (ii) accurately optimize the reliability score within the constructed prediction set. We provide theoretical results on coverage and demonstrate empirically that our method produces more informative prediction sets than existing approaches. Experiments on synthetic data and the image-to-text and text-to-image tasks further demonstrate the interpretability of our new metric, and the validity and effectiveness of our computational framework. Source code can be found at https://ggc29.github.io/CReL/.

cs.LG↗

arXiv2026

Diffusion-based learning framework for Constrained Nonconvex Optimization with Weighted Bootstrapped Refinement

Recent advances in diffusion models show promising potential to accelerate nonconvex problem solving by leveraging their multimodality. However, most existing diffusion-based optimization approaches rely on supervised learning and lack a mechanism to enforce constraint satisfaction, which is required in real-world applications. In that case, we investigate and theoretically analyze the inherent problem of supervised diffusion solvers and identify the distributional misalignment problem, i.e., the generated solution distribution often exhibits low probability mass on the feasible region. To resolve this issue, we propose DiOpt, a new diffusion-based learning framework for constrained nonconvex optimization, which effectively learns the mapping from noise to the constraint region. Specifically, this framework operates in two distinct phases: an initial warm-start phase, implemented via supervised learning, followed by a bootstrapping training phase. This dual-phase architecture is designed to iteratively refine solutions, thereby improving the objective function with high constraint satisfaction. Finally, we also employ a solution selection technique in inference for better optimality. Notably, DiOpt is the first successful integration of the diffusion solver in constrained nonconvex optimization. Evaluations on diverse nonconvex tasks demonstrate the superiority of DiOpt in both optimality and constraint satisfaction. Our official page is released at https://dingsht.tech/diopt-webpage.

cs.LG↗

arXiv2026

Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance

Recent advances in reinforcement learning (RL) have achieved great successes by leveraging the multimodality and exploration capability of diffusion policies. Among these approaches, one representative branch focuses on the sampling-based policy optimization. This design enables better exploration capability of the diffusion model, particularly at the beginning of training, but suffer from low exploitation in Q-value information, resulting in a slow policy convergence. Another branch pays attention to gradient-based policy optimization, which sufficiently exploits the gradient of the Q function yet tends to collapse into a unimodal policy with low diversity. To address this issue, we propose CGPO, \textbf{C}ritic-\textbf{G}uided diffusion \textbf{P}olicy \textbf{O}ptimization, which effectively balances exploration and exploitation with the training-free guidance technique integrated into the denoising process of diffusion policy. Concretely, CGPO steers action generation toward high-value regions defined by the critic network and uses the guided actions as regression objectives. In this manner, CGPO reduces the time required to obtain high-quality actions and improves final performance with better balance between the exploration-exploitation tradeoff. We validate the effectiveness of CGPO on 5 MuJoCo locomotion tasks, and CGPO achieves state-of-the-art performance compared with existing diffusion-based RL methods. Notably, CGPO is the first success to incorporate diffusion policy into real-world RL, with its superior performance on Franka robot arm grasping tasks. Our official page is released at https://dingsht.tech/cgpo-webpage.

cs.RO↗

arXiv2026

DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcing

We study real-time audio-responsive character control as a deployment-faithful problem: strictly causal, bounded-latency streaming that must generate coherent full-body motion at interactive frame rates while the audio condition can change abruptly, including tempo shifts, drops, or user edits. Prior music-to-motion systems are largely optimized for offline generation with global context, and degrade in streaming rollouts where conditioning history becomes stale or unreliable. We introduce DiscoForcing, a streaming audio-driven diffusion framework that combines a causal music encoder that captures rhythmic structure and phase dynamics with a diffusion-forcing sequence model trained under heterogeneous noise levels across the temporal horizon. Building on this, we design a hybrid temporal schedule and a history-guided streaming sampler to explicitly trade off responsiveness against long-horizon consistency under non-stationary audio. Implemented in an end-to-end real-time interactive system with online avatar playback and humanoid deployment workflows, DiscoForcing delivers more stable long-horizon rollouts and sharper audio-motion alignment than prior baselines under matched causality and latency constraints while maintaining real-time throughput.

cs.CV↗

arXiv2026

DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion

Achieving versatile humanoid locomotion with a single policy presents a critical scalability challenge. Prevailing methods often rely on distilling multiple terrain-specific teacher policies into a unified student policy. However, while such distillation captures basic locomotion primitives, it struggles to organically compose these skills to adapt to complex environments, resulting in poor generalization to novel composite terrains unseen during training. To overcome this, we present DreamPolicy, a unified framework that integrates offline data with a diffusion-based world model, enabling a single policy to master both known and unseen terrains. Central to our approach is a terrain-aware world model, driven by an autoregressive diffusion world model trained on aggregated rollouts from specialized policies. This model synthesizes physically plausible future trajectories, which serve as dynamic objectives for a conditioned policy, thereby bypassing manual reward engineering. Unlike distillation, our world model captures generalizable locomotion skills, allowing for robust zero-shot transfer to unseen composite terrains. DreamPolicy naturally scales with data availability. As the offline dataset expands, the diffusion world model continuously acquires richer skills. Experiments demonstrate that DreamPolicy outperforms the strongest baseline by up to 27\% on unseen terrains and 38\% on combined terrains. By unifying world model-based planning and policy learning, DreamPolicy breaks the "one task, one policy" bottleneck and establishes a scalable, data-driven paradigm for generalist humanoid control.

cs.RO↗

arXiv2026

Commanding Humanoid by Free-form Language: A Large Language Action Model with Unified Motion Vocabulary

Enabling humanoid robots to follow free-form natural language commands is a critical step toward seamless human-robot interaction and general-purpose embodied AI. However, existing methods remain limited, often constrained to simple instructions or forced to sacrifice motion diversity for physical plausibility. To address this gap, we present Humanoid-LLA, a Large Language Action model that translates unconstrained natural language directly into executable whole-body motions for humanoid robots. Our approach tackles two core challenges: paired language-humanoid motion data scarcity and physical instability. First, we bridge high-level language semantics with physically-grounded control by learning a unified human-humanoid motion vocabulary. Second, we introduce a novel two-stage fine-tuning framework that begins with supervised motion Chain-of-Thought learning, followed by reinforcement learning refined with physical feedback to ensure robustness and stability. Extensive evaluation in simulation and real-world cross-embodiment experiments demonstrates that Humanoid-LLA achieves superior generalization to novel language commands and diverse motion generation while maintaining high physical fidelity.

cs.RO↗

arXiv2026

Unsupervised Learning for AC Optimal Power Flow with Fast Physics-Aware Layer

Learning to solve the Alternating Current Optimal Power Flow (AC-OPF) problem by neural networks (NNs) is a promising approach in real-time applications. Existing methods to ensure the physical feasibility of NN outputs embed a power flow (PF) solver within networks. However, the gradient through the PF solver, namely, implicit differentiation, needs manual Jacobian derivation and the solution of linear systems, which is computationally prohibitive and hinders integration with modern automatic differentiation (AD) frameworks. To address these challenges, we propose FPL-OPF, a novel unsupervised learning framework that incorporates a Fast Physics-aware Layer for AC-OPF problems. FPL-OPF embeds a fast PF iterative solver within the NN and takes solely the last few or even the final iterations into the AD graph. This design ensures high computational efficiency for both the forward and backward passes, circumventing complex custom backward implementations. Theoretically, we rigorously prove that the gradient from this design serves as a high-fidelity surrogate of the true implicit gradient under mild conditions. Extensive experiments demonstrate that FPL-OPF achieves significant speedups over state-of-the-art unsupervised learning approaches, while maintaining near-zero constraint violations and competitive optimality. Our code is available at https://github.com/wowotou1998/fpl-opf

cs.CE↗

arXiv2026

Gaze-guided Hand-Object Interaction Synthesis: Dataset and Method

Gaze plays a crucial role in revealing human attention and intention, particularly in hand-object interaction scenarios, where it guides and synchronizes complex tasks that require precise coordination between the brain, hand, and object. Motivated by this, we introduce a novel task: Gaze-Guided Hand-Object Interaction Synthesis, with potential applications in augmented reality, virtual reality, and assistive technologies. To support this task, we present GazeHOI, the first dataset to capture simultaneous 3D modeling of gaze, hand, and object interactions. This task poses significant challenges due to the inherent sparsity and noise in gaze data, as well as the need for high consistency and physical plausibility in generating hand and object motions. To tackle these issues, we propose a stacked gaze-guided hand-object interaction diffusion model, named GHO-Diffusion. The stacked design effectively reduces the complexity of motion generation. We also introduce HOI-Manifold Guidance during the sampling stage of GHO-Diffusion, enabling fine-grained control over generated motions while maintaining the data manifold. Additionally, we propose a spatial-temporal gaze feature encoding for the diffusion condition and select diffusion results based on consistency scores between gaze-contact maps and gaze-interaction trajectories. Extensive experiments highlight the effectiveness of our method and the unique contributions of our dataset. More details in https://takiee.github.io/gaze-hoi/.

cs.CV↗

arXiv2026

Human-Object Interaction via Automatically Designed VLM-Guided Motion Policy

Human-object interaction (HOI) synthesis is crucial for applications in animation, simulation, and robotics. However, existing approaches either rely on expensive motion capture data or require manual reward engineering, limiting their scalability and generalizability. In this work, we introduce the first unified physics-based HOI framework that leverages Vision-Language Models (VLMs) to enable long-horizon interactions with diverse object types, including static, dynamic, and articulated objects. We introduce VLM-Guided Relative Movement Dynamics (RMD), a fine-grained spatio-temporal bipartite representation that automatically constructs goal states and reward functions for reinforcement learning. By encoding structured relationships between human and object parts, RMD enables VLMs to generate semantically grounded, interaction-aware motion guidance without manual reward tuning. To support our methodology, we present Interplay, a novel dataset with thousands of long-horizon static and dynamic interaction plans. Extensive experiments demonstrate that our framework outperforms existing methods in synthesizing natural, human-like motions across both simple single-task and complex multi-task scenarios. For more details, please refer to our project webpage: https://vlm-rmd.github.io/.

cs.CV↗

arXiv2026

UniHM: Unified Dexterous Hand Manipulation with Vision Language Model

Planning physically feasible dexterous hand manipulation is a central challenge in robotic manipulation and Embodied AI. Prior work typically relies on object-centric cues or precise hand-object interaction sequences, foregoing the rich, compositional guidance of open-vocabulary instruction. We introduce UniHM, the first framework for unified dexterous hand manipulation guided by free-form language commands. We propose a Unified Hand-Dexterous Tokenizer that maps heterogeneous dexterous-hand morphologies into a single shared codebook, improving cross-dexterous hand generalization and scalability to new morphologies. Our vision language action model is trained solely on human-object interaction data, eliminating the need for massive real-world teleoperation datasets, and demonstrates strong generalizability in producing human-like manipulation sequences from open-ended language instructions. To ensure physical realism, we introduce a physics-guided dynamic refinement module that performs segment-wise joint optimization under generative and temporal priors, yielding smooth and physically feasible manipulation sequences. Across multiple datasets and real-world evaluations, UniHM attains state-of-the-art results on both seen and unseen objects and trajectories, demonstrating strong generalization and high physical feasibility. Our project page at \href{https://unihm.github.io/}{https://unihm.github.io/}.

cs.RO↗

arXiv2026

A Review of Online Diffusion Policy RL Algorithms for Scalable Robotic Control

Diffusion policies have emerged as a powerful approach for robotic control, demonstrating superior expressiveness in modeling multimodal action distributions compared to conventional policy networks. However, their integration with online reinforcement learning remains challenging due to fundamental incompatibilities between diffusion model training objectives and standard RL policy improvement mechanisms. This paper presents the first comprehensive review and empirical analysis of current Online Diffusion Policy Reinforcement Learning (Online DPRL) algorithms for scalable robotic control systems. We propose a novel taxonomy that categorizes existing approaches into four distinct families--Action-Gradient, Q-Weighting, Proximity-Based, and Backpropagation Through Time (BPTT) methods--based on their policy improvement mechanisms. Through extensive experiments on a unified NVIDIA Isaac Lab benchmark encompassing 12 diverse robotic tasks, we systematically evaluate representative algorithms across five critical dimensions: task diversity, parallelization capability, diffusion step scalability, cross-embodiment generalization, and environmental robustness. Our analysis identifies key findings regarding the fundamental trade-offs inherent in each algorithmic family, particularly concerning sample efficiency and scalability. Furthermore, we reveal critical computational and algorithmic bottlenecks that currently limit the practical deployment of online DPRL. Based on these findings, we provide concrete guidelines for algorithm selection tailored to specific operational constraints and outline promising future research directions to advance the field toward more general and scalable robotic learning systems.

cs.LG↗

arXiv2026

Distributional Reinforcement Learning with Diffusion Bridge Critics

Recent advances in diffusion-based reinforcement learning (RL) methods have demonstrated promising results in a wide range of continuous control tasks. However, existing works in this field focus on the application of diffusion policies while leaving the diffusion critics unexplored. In fact, since policy optimization fundamentally relies on the critic, accurate value estimation is far more important than policy expressiveness. Furthermore, given the stochasticity of most reinforcement learning tasks, it has been confirmed that the critic is more appropriately depicted with a distributional model. Motivated by these points, we propose a novel distributional RL method with Diffusion Bridge Critics (DBC). DBC directly models the inverse cumulative distribution function (CDF) of the Q value. This allows us to accurately capture the value distribution and prevents it from collapsing into a trivial Gaussian distribution owing to the strong distribution-matching capability of the diffusion bridge. Moreover, we further derive an analytic integral formula to address discretization errors in DBC, which is essential in value estimation. To our knowledge, DBC is the first work to employ the diffusion bridge model as the critic. Notably, DBC is also a plug-and-play component and can be integrated into most existing RL frameworks. Experimental results on MuJoCo robot control benchmarks demonstrate the superiority of DBC compared with previous distributional critic models.

cs.LG↗

arXiv2026

Fine-grained Classification of A Million Life Trajectories from Wikipedia

Life trajectories of notable people convey essential messages for human dynamics research. These trajectories consist of (\textit{person, time, location, activity type}) tuples recording when and where a person was born, went to school, started a job, or fought in a war. However, current studies only cover limited activity types such as births and deaths, lacking large-scale fine-grained trajectories. Using a tool that extracts (\textit{person, time, location}) triples from Wikipedia, we formulate the problem of classifying these triples into 24 carefully-defined types using textual context as complementary information. The challenge is that triple entities are often scattered in noisy contexts. We use syntactic graphs to bring triple entities and relevant information closer, fusing them with text embeddings to classify life trajectory activities. Since Wikipedia text quality varies, we use LLMs to refine the text for more standardized syntactic graphs. Our framework achieves 84.5\% accuracy, surpassing baselines. We construct the largest fine-grained life trajectory dataset with 3.8 million labeled activities for 589,193 individuals spanning 3 centuries. In the end, we showcase how these trajectories can support grand narratives of human dynamics across time and space. Code/data are publicly available.

cs.CY↗

arXiv2026

NLPrompt: Noise-Label Prompt Learning for Vision-Language Models

The emergence of vision-language foundation models, such as CLIP, has revolutionized image-text representation, enabling a broad range of applications via prompt learning. Despite its promise, real-world datasets often contain noisy labels that can degrade prompt learning performance. In this paper, we demonstrate that using mean absolute error (MAE) loss in prompt learning, named PromptMAE, significantly enhances robustness against noisy labels while maintaining high accuracy. Though MAE is straightforward and recognized for its robustness, it is rarely used in noisy-label learning due to its slow convergence and poor performance outside prompt learning scenarios. To elucidate the robustness of PromptMAE, we leverage feature learning theory to show that MAE can suppress the influence of noisy samples, thereby improving the signal-to-noise ratio and enhancing overall robustness. Additionally, we introduce PromptOT, a prompt-based optimal transport data purification method to enhance the robustness further. PromptOT employs text features in vision-language models as prototypes to construct an optimal transportation matrix. This matrix effectively partitions datasets into clean and noisy subsets, allowing for the application of cross-entropy loss to the clean subset and MAE loss to the noisy subset. Our Noise-Label Prompt Learning method, named NLPrompt, offers a simple and efficient approach that leverages the expressive representations and precise alignment capabilities of vision-language models for robust prompt learning. We validate NLPrompt through extensive experiments across various noise settings, demonstrating significant performance improvements.

cs.CV↗