English
Related papers

Related papers: ElasticFlow: One-Step Physics-Consistent Policy wi…

200 papers

Language models based on discrete diffusion have attracted widespread interest for their potential to provide faster generation than autoregressive models. Despite their promise, these models typically produce samples whose quality sharply…

Computation and Language · Computer Science 2026-05-21 Chanhyuk Lee , Jaehoon Yoo , Manan Agarwal , Sheel Shah , Jerry Huang , Aditi Raghunathan , Seunghoon Hong , Nicholas M. Boffi , Jinwoo Kim

Learning robust visuomotor policies that generalize across diverse objects and interaction dynamics remains a central challenge in robotic manipulation. Most existing approaches rely on direct observation-to-action mappings or compress…

Robotics · Computer Science 2025-09-24 Sangjun Noh , Dongwoo Nam , Kangmin Kim , Geonhyup Lee , Yeonguk Yu , Raeyoung Kang , Kyoobin Lee

We introduce MelodyFlow, an efficient text-controllable high-fidelity music generation and editing model. It operates on continuous latent representations from a low frame rate 48 kHz stereo variational auto encoder codec. Based on a…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-17 Gael Le Lan , Bowen Shi , Zhaoheng Ni , Sidd Srinivasan , Anurag Kumar , Brian Ellis , David Kant , Varun Nagaraja , Ernie Chang , Wei-Ning Hsu , Yangyang Shi , Vikas Chandra

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:…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Huijie Zhang , Aliaksandr Siarohin , Willi Menapace , Michael Vasilkovsky , Sergey Tulyakov , Qing Qu , Ivan Skorokhodov

Recent diffusion and flow matching models have demonstrated strong capabilities in image generation and editing by progressively removing noise through iterative sampling. While this enables flexible inversion for semantic-preserving edits,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Yasong Dai , Zeeshan Hayder , David Ahmedt-Aristizabal , Hongdong Li

Recent vision-language-action (VLA) models can generate plausible end-effector motions, yet they often fail in long-horizon, contact-rich tasks because the underlying hand-object interaction (HOI) structure is not explicitly represented. An…

Robotics · Computer Science 2026-02-17 Huajian Zeng , Lingyun Chen , Jiaqi Yang , Yuantai Zhang , Fan Shi , Peidong Liu , Xingxing Zuo

Recent advances in flow-based generative models have enabled training-free, text-guided image editing by inverting an image into its latent noise and regenerating it under a new target conditional guidance. However, existing methods…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Thinh Dao , Zhen Wang , Kien T. Pham , Long Chen

We introduce ImitationFlow, a novel Deep generative model that allows learning complex globally stable, stochastic, nonlinear dynamics. Our approach extends the Normalizing Flows framework to learn stable Stochastic Differential Equations.…

Machine Learning · Computer Science 2020-10-27 Julen Urain , Michelle Ginesi , Davide Tateo , Jan Peters

Behavior cloning (BC) has become a staple imitation learning paradigm in robotics due to its ease of teaching robots complex skills directly from expert demonstrations. However, BC suffers from an inherent generalization issue. To solve…

Robotics · Computer Science 2025-08-12 Tianyu Li , Sunan Sun , Shubhodeep Shiv Aditya , Nadia Figueroa

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…

Robotics · Computer Science 2026-02-06 Entong Su , Tyler Westenbroek , Anusha Nagabandi , Abhishek Gupta

Flow-matching policies hold great promise for reinforcement learning (RL) by capturing complex, multi-modal action distributions. However, their practical application is often hindered by prohibitive inference latency and ineffective online…

Machine Learning · Computer Science 2026-03-17 He Zhang , Ying Sun , Hui Xiong

This paper proposes a new design method for a stochastic control policy using a normalizing flow (NF). In reinforcement learning (RL), the policy is usually modeled as a distribution model with trainable parameters. When this…

Robotics · Computer Science 2024-12-18 Taisuke Kobayashi , Takumi Aotani

We introduce Simulation Streams, a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynamic simulations and agentic workflows. Our primary goal is to create a minimally interfering…

Artificial Intelligence · Computer Science 2025-02-03 Peter Sunehag , Joel Z. Leibo

Recent works have demonstrated success in controlling sentence attributes ($e.g.$, sentiment) and structure ($e.g.$, syntactic structure) based on the diffusion language model. A key component that drives theimpressive performance for…

Computation and Language · Computer Science 2024-03-26 Shujian Zhang , Lemeng Wu , Chengyue Gong , Xingchao Liu

Agentic workflows in large language model systems integrate retrieval, reasoning, and memory, but existing frameworks suffer from scalability and reproducibility limitations due to fragmented data orchestration, serialization overhead, and…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-05 Arup Kumar Sarker , Mills Staylor , Aymen Alsaadi , Gregor von Laszewski , Shantenu Jha , Geoffrey Fox

Flow Matching enables simulation-free training of generative models on Riemannian manifolds, yet sampling typically still relies on numerically integrating a probability-flow ODE. We propose Riemannian MeanFlow (RMF), extending MeanFlow to…

Machine Learning · Computer Science 2026-05-21 Zichen Zhong , Haoliang Sun , Yukun Zhao , Yongshun Gong , Yilong Yin

Flow-based image generative models exhibit stable training and produce high quality samples when using multi-step sampling procedures. One-step generative models can produce high quality image samples but can be difficult to optimize as…

Machine Learning · Computer Science 2026-04-13 Chia-Hong Hsu , Frank Wood

Among on-policy reinforcement learning algorithms, Proximal Policy Optimization (PPO) demonstrates is widely favored for its simplicity, numerical stability, and strong empirical performance. Standard PPO relies on surrogate objectives…

Machine Learning · Computer Science 2026-02-03 Shunpeng Yang , Ben Liu , Hua Chen

Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to higher resolutions for flow refinement. In this work, we take…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Daikun Liu , Lei Cheng , Teng Wang , changyin Sun

Diffusion Large Language Models (dLLMs) are rapidly emerging alongside autoregressive models as a powerful paradigm for complex reasoning, with reinforcement learning increasingly used for downstream alignment. Existing trajectory-based RL…

Machine Learning · Computer Science 2025-11-20 Ranfei Chen , Ming Chen , Kaifei Wang