Related papers: One-Step Flow Q-Learning: Addressing the Diffusion…

We present FlowLM, a flow matching language model transformed from pre-trained diffusion language models via efficient fine-tuning. By re-aligning the curved sampling trajectories of diffusion models into straight-line flows, FlowLM enables…

Offline reinforcement learning (RL) aims to learn policies from pre-existing datasets without further interactions, making it a challenging task. Q-learning algorithms struggle with extrapolation errors in offline settings, while supervised…

Generative models such as diffusion and flow-matching offer expressive policies for offline reinforcement learning (RL) by capturing rich, multimodal action distributions, but their iterative sampling introduces high inference costs and…

Offline reinforcement learning (RL) aims to learn optimal policies from previously collected datasets. Recently, due to their powerful representational capabilities, diffusion models have shown significant potential as policy models for…

A hallmark of modern large-scale machine learning techniques is the use of training objectives that provide dense supervision to intermediate computations, such as teacher forcing the next token in language models or denoising step-by-step…

We present DistillFlow, a knowledge distillation approach to learning optical flow. DistillFlow trains multiple teacher models and a student model, where challenging transformations are applied to the input of the student model to generate…

Flow-matching models have enabled high-quality text-to-speech synthesis, but their iterative sampling process during inference incurs substantial computational cost. Although distillation is widely used to reduce the number of inference…

Recent advances in large multi-modal generative models have demonstrated impressive capabilities in multi-modal generation, including image and video generation. These models are typically built upon multi-step frameworks like diffusion and…

Drawing upon recent advances in language model alignment, we formulate offline Reinforcement Learning as a two-stage optimization problem: First pretraining expressive generative policies on reward-free behavior datasets, then fine-tuning…

Vision-based deep reinforcement learning (RL) typically obtains performance benefit by using high capacity and relatively large convolutional neural networks (CNN). However, a large network leads to higher inference costs (power, latency,…

Recent research has highlighted the powerful capabilities of imitation learning in robotics. Leveraging generative models, particularly diffusion models, these approaches offer notable advantages such as strong multi-task generalization,…

In this paper, we propose a federated deep reinforcement learning framework to solve a multi-objective optimization problem, where we consider minimizing the expected long-term task completion delay and energy consumption of IoT devices.…

Real-time robotic control demands fast action generation. However, existing generative policies based on diffusion and flow matching require multi-step sampling, fundamentally limiting deployment in time-critical scenarios. We propose…

Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hacking, such as quality degradation, over-stylization, or…

Off-policy, value-based reinforcement learning methods such as Q-learning are appealing because they can learn from arbitrary experience, including data collected by older policies or other agents. In practice, however, bootstrapping makes…

Hierarchical goal-conditioned reinforcement learning (H-GCRL) provides a powerful framework for tackling complex, long-horizon tasks by decomposing them into structured subgoals. However, its practical adoption is hindered by poor data…

Offline reinforcement learning (RL) aims to learn the optimal policy from a fixed dataset generated by behavior policies without additional environment interactions. One common challenge that arises in this setting is the…

Most existing offline RL methods presume the availability of action labels within the dataset, but in many practical scenarios, actions may be missing due to privacy, storage, or sensor limitations. We formalise the setting of action-free…

Diffusion Models have emerged as a leading class of generative models, yet their iterative sampling process remains computationally expensive. Timestep distillation is a promising technique to accelerate generation, but it often requires…

We propose ReinFlow, a simple yet effective online reinforcement learning (RL) framework that fine-tunes a family of flow matching policies for continuous robotic control. Derived from rigorous RL theory, ReinFlow injects learnable noise…