English
Related papers

Related papers: A Unified Density Operator View of Flow Control an…

200 papers

In the era of large-scale training, model merging has evolved into a tool for creating multitasking models efficiently. It enables the knowledge of models to be fused, without the need for heavy computation as required in traditional…

Diffusion and flow policies are gaining prominence in online reinforcement learning (RL) due to their expressive power, yet training them efficiently remains a critical challenge. A fundamental difficulty in online RL is the lack of direct…

Machine Learning · Computer Science 2026-01-14 Zeyang Li , Sunbochen Tang , Navid Azizan

Flow models have rapidly become the go-to method for training and deploying large-scale generators, owing their success to inference-time flexibility via adjustable integration steps. A crucial ingredient in flow training is the choice of…

Generative models have become increasingly powerful tools for robot motion generation, enabling flexible and multimodal trajectory generation across various tasks. Yet, most existing approaches remain limited in handling multiple types of…

Robotics · Computer Science 2026-01-15 Zewen Yang , Xiaobing Dai , Dian Yu , Zhijun Li , Majid Khadiv , Sandra Hirche , Sami Haddadin

Balancing policy expressiveness with the exploration-exploitation trade-off is a core challenge in online Reinforcement Learning (RL). While Stochastic Differential Equation (SDE)-based diffusion policies can represent complex, multimodal…

Machine Learning · Computer Science 2026-05-27 Ting Gao , Stavros Orfanoudakis , Nan Lin , Winnie Daamen , Serge Hoogendoorn , Elvin Isufi

Distribution Matching Distillation (DMD) facilitates efficient inference by distilling multi-step diffusion models into few-step variants. Concurrently, Reinforcement Learning (RL) has emerged as a vital tool for aligning generative models…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Dengyang Jiang , Dongyang Liu , Zanyi Wang , Qilong Wu , Liuzhuozheng Li , Hengzhuang Li , Xin Jin , David Liu , Changsheng Lu , Zhen Li , Bo Zhang , Mengmeng Wang , Steven Hoi , Peng Gao , Harry Yang

We propose Functional Flow Matching (FFM), a function-space generative model that generalizes the recently-introduced Flow Matching model to operate in infinite-dimensional spaces. Our approach works by first defining a path of probability…

Machine Learning · Computer Science 2023-12-07 Gavin Kerrigan , Giosue Migliorini , Padhraic Smyth

Flow-matching policies have emerged as a powerful paradigm for generalist robotics. These models are trained to imitate an action chunk, conditioned on sensor observations and textual instructions. Often, training demonstrations are…

Machine Learning · Computer Science 2025-07-22 Samuel Pfrommer , Yixiao Huang , Somayeh Sojoudi

Video generation models trained on heterogeneous data with likelihood-surrogate objectives can produce visually plausible rollouts that violate physical constraints in embodied manipulation. Although reinforcement-learning post-training…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Zhenyang Ni , Yijiang Li , Ruochen Jiao , Simon Sinong Zhan , Sipeng Chen , Zhenfei Yin , Minshuo Chen , Philip Torr , Zhaoran Wang , Qi Zhu

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…

Machine Learning · Computer Science 2026-05-19 Chenrui Ma , Xi Xiao , Lin Zhao , Tianyang Wang , Ferdinando Fioretto , Yanning Shen

Recent advancements adopt online reinforcement learning (RL) from LLMs to text-to-image rectified flow diffusion models for reward alignment. The use of group-level rewards successfully aligns the model with the targeted reward. However, it…

Machine Learning · Computer Science 2026-01-06 Yiyang Wang , Xi Chen , Xiaogang Xu , Yu Liu , Hengshuang Zhao

Recent advancements in reinforcement learning (RL) have achieved great success in fine-tuning diffusion-based generative models. However, fine-tuning continuous flow-based generative models to align with arbitrary user-defined reward…

Machine Learning · Computer Science 2025-02-11 Jiajun Fan , Shuaike Shen , Chaoran Cheng , Yuxin Chen , Chumeng Liang , Ge Liu

Existing Flow Matching (FM) text-to-image models suffer from two critical bottlenecks under multi-task alignment: the reward sparsity induced by scalar-valued rewards, and the gradient interference arising from jointly optimizing…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Zhen Fang , Wenxuan Huang , Yu Zeng , Yiming Zhao , Shuang Chen , Kaituo Feng , Yunlong Lin , Lin Chen , Zehui Chen , Shaosheng Cao , Feng Zhao

Generative models excel at motion synthesis for a fixed number of agents but struggle to generalize with variable agents. Based on limited, domain-specific data, existing methods employ autoregressive models to generate motion recursively,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Guanhe Huang , Oya Celiktutan

Process Reward Models (PRMs) are crucial for guiding Large Language Models (LLMs) in complex scenarios by providing dense reward signals. However, existing PRMs primarily rely on heuristic approaches, which struggle with cross-domain…

Computation and Language · Computer Science 2025-07-25 Zhangyue Yin , Qiushi Sun , Zhiyuan Zeng , Qinyuan Cheng , Xipeng Qiu , Xuanjing Huang

Flow and diffusion models produce high-quality samples, but adapting them to user preferences or constraints post-training remains costly and brittle, a challenge commonly called reward alignment. We argue that efficient reward alignment…

Generating high-dimensional visual modalities is a computationally intensive task. A common solution is progressive generation, where the outputs are synthesized in a coarse-to-fine spectral autoregressive manner. While diffusion models…

Computer Vision and Pattern Recognition · Computer Science 2025-06-25 Moayed Haji-Ali , Willi Menapace , Ivan Skorokhodov , Arpit Sahni , Sergey Tulyakov , Vicente Ordonez , Aliaksandr Siarohin

Diffusion and flow-matching models scale because pretraining is supervised regression: a clean sample is noised analytically, and a model regresses against a closed-form target. RL post-training aligns the model with a reward. In image…

Machine Learning · Computer Science 2026-05-19 Andreas Bergmeister , Stefanie Jegelka , Nikolas Nüsken , Carles Domingo-Enrich , Jakiw Pidstrigach

Reward models are crucial for aligning large language models (LLMs) with human values and intentions. Existing approaches follow either Generative (GRMs) or Discriminative (DRMs) paradigms, yet both suffer from limitations: GRMs typically…

Computation and Language · Computer Science 2026-03-03 Longze Chen , Lu Wang , Renke Shan , Ze Gong , Run Luo , Jiaming Li , Jing Luo , Qiyao Wang , Min Yang

We consider the problem of designing constraint-aware flow matching (FM) models that address the issue of constraint violations commonly observed in vanilla generative models. We consider two scenarios, viz.: (a) when a differentiable…

Machine Learning · Computer Science 2026-05-01 Zhengyan Huan , Jacob Boerma , Li-Ping Liu , Shuchin Aeron