Related papers: AdvantageFlow: Advantage-Weighted Least Squares fo…

Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-frequency variations. Flow Matching (FM) offers an efficient…

Vision-Language-Action (VLA) models such as OpenVLA, Octo, and $\pi_0$ have shown strong generalization by leveraging large-scale demonstrations, yet their performance is still fundamentally constrained by the quality and coverage of…

Diffusion models have recently shown promise in offline RL. However, these methods often suffer from high training costs and slow convergence, particularly when using transformer-based denoising backbones. While several optimization…

Generative modeling has recently shown remarkable promise for visuomotor policy learning, enabling flexible and expressive control across diverse embodied AI tasks. However, existing generative policies often struggle with data…

Unsupervised Reinforcement Learning from Internal Feedback (RLIF) has emerged as a promising paradigm for eliciting the latent capabilities of Large Language Models (LLMs) without external supervision. However, current methods rely on…

Model-based reinforcement learning (MBRL) with autoregressive world models suffers from compounding errors, whereas diffusion world models mitigate this by generating trajectory segments jointly. However, existing diffusion guides are…

Processing data at high speeds is becoming increasingly critical as digital economies generate enormous data. The current paradigms for timely data processing are edge computing and data stream processing (DSP). Edge computing places…

Deploying pretrained visual models in real-world environments often suffers from significant performance degradation due to the diversity of testing scenarios. Continuous adaptation of learning models on edge devices via unlabeled data…

Distilled autoregressive (AR) video models enable efficient streaming generation but frequently misalign with human visual preferences. Existing reinforcement learning (RL) frameworks are not naturally suited to these architectures,…

This paper introduces Generalized Attention Flow (GAF), a novel feature attribution method for Transformer-based models to address the limitations of current approaches. By extending Attention Flow and replacing attention weights with the…

Imitation learning has emerged as an effective approach for bootstrapping sequential decision-making in robotics, achieving strong performance even in high-dimensional dexterous manipulation tasks. Recent behavior cloning methods further…

Reinforcement learning (RL) post-training is crucial for aligning generative models with human preferences, but its prohibitive computational cost remains a major barrier to widespread adoption. We introduce \textbf{TreeGRPO}, a novel RL…

Multi-step prediction models, such as diffusion and rectified flow models, have emerged as state-of-the-art solutions for generation tasks. However, these models exhibit higher latency in sampling new frames compared to single-step methods.…

Modern reinforcement learning (RL) algorithms have found success by using powerful probabilistic models, such as transformers, energy-based models, and diffusion/flow-based models. To this end, RL researchers often choose to pay the price…

Reinforcement Learning from Human Feedback~(RLHF) plays a crucial role in aligning Large Language Models~(LLMs). The dominant algorithm, Proximal Policy Optimization~(PPO), employs a critic network to estimate advantages, which introduces…

Large-scale diffusion models have achieved remarkable performance in generative tasks. Beyond their initial training applications, these models have proven their ability to function as versatile plug-and-play priors. For instance, 2D…

Efficiently aligning large-scale video diffusion models with human intent requires a scalable and trajectory-aware pathway that bridges the inherent discrepancy between training noise distributions and practical inference trajectories.…

We propose continuous adversarial flow models, a type of continuous-time flow model trained with an adversarial objective. Unlike flow matching, which uses a fixed mean-squared-error criterion, our approach introduces a learned…

Deep learning classifiers are susceptible to well-crafted, imperceptible variations of their inputs, known as adversarial attacks. In this regard, the study of powerful attack models sheds light on the sources of vulnerability in these…

MeanFlow has recently emerged as a powerful framework for few-step generative modeling trained from scratch, but its success is not yet fully understood. In this work, we show that the MeanFlow objective naturally decomposes into two parts:…