Related papers: One Step Is Enough: Dispersive MeanFlow Policy Opt…

Mean flow (MeanFlow) enables efficient, high-fidelity image generation, yet its single-function evaluation (1-NFE) generation often cannot yield compelling results. We address this issue by introducing RMFlow, an efficient multimodal…

Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs due to its extensive group-based sampling requirement. While recent selective data utilization methods can mitigate this…

Diffusion Q-Learning (DQL) has established diffusion policies as a high-performing paradigm for offline reinforcement learning, but its reliance on multi-step denoising for action generation renders both training and inference slow and…

Diffusion models have been verified to be effective in generating complex distributions from natural images to motion trajectories. Recent diffusion-based methods show impressive performance in 3D robotic manipulation tasks, whereas they…

Diffusion models (DMs) have recently demonstrated remarkable success in modeling large-scale data distributions. However, many downstream tasks require guiding the generated content based on specific differentiable metrics, typically…

Diffusion policies have recently emerged as a powerful paradigm for visuomotor control in robotic manipulation due to their ability to model the distribution of action sequences and capture multimodality. However, iterative denoising leads…

Generative motion prediction must satisfy three simultaneous requirements for real-world autonomy: high accuracy, diverse multimodal futures, and strictly bounded latency. Diffusion models meet the first two but violate the third, requiring…

Diffusion Models have revolutionized the field of human motion generation by offering exceptional generation quality and fine-grained controllability through natural language conditioning. Their inherent stochasticity, that is the ability…

Order dispatch is a critical task in ride-sharing systems with Autonomous Vehicles (AVs), directly influencing efficiency and profits. Recently, Multi-Agent Reinforcement Learning (MARL) has emerged as a promising solution to this problem…

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…

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,…

Recent research has made significant progress in optimizing diffusion models for downstream objectives, which is an important pursuit in fields such as graph generation for drug design. However, directly applying these models to graph…

Recently, Masked Diffusion Models (MDMs) have shown promising potential across vision, language, and cross-modal generation. However, a notable discrepancy exists between their training and inference procedures. In particular, MDM inference…

We propose Drifting Field Policy (DFP), a non-ODE one-step generative policy built on the drifting model paradigm. We frame the policy update as a reverse-KL Wasserstein-2 gradient flow toward a soft target policy, so that each DFP update…

The policy gradient method enjoys the simplicity of the objective where the agent optimizes the cumulative reward directly. Moreover, in the continuous action domain, parameterized distribution of action distribution allows easy control of…

Diffusion models have achieved remarkable success in generating realistic and versatile images from text prompts. Inspired by the recent advancements of language models, there is an increasing interest in further improving the models by…

Iterative generative models such as Flow Matching and Diffusion models have demonstrated strong test-time scaling behavior, where additional inference computation can improve generation quality. In contrast, Drift Models offer efficient…

Diffusion models offer powerful generative capabilities for robot trajectory planning, yet their practical deployment on robots is hindered by a critical bottleneck: a reliance on imitation learning from expert demonstrations. This paradigm…

Denoising Diffusion Probabilistic Models (DDPMs) are powerful generative deep learning models that have been very successful at image generation, and, very recently, in path planning and control. In this paper, we investigate how to…

MeanFlow enables one-step generation in continuous spaces by learning an average velocity over a time interval rather than the instantaneous velocity field of flow matching. However, discrete state spaces do not have smooth trajectories or…