English
Related papers

Related papers: Fine-tuning Flow Matching Generative Models with I…

200 papers

Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this…

Artificial Intelligence · Computer Science 2025-10-08 Zhuofeng Li , Haoxiang Zhang , Seungju Han , Sheng Liu , Jianwen Xie , Yu Zhang , Yejin Choi , James Zou , Pan Lu

Generative speech enhancement offers a promising alternative to traditional discriminative methods by modeling the distribution of clean speech conditioned on noisy inputs. Post-training alignment via reinforcement learning (RL) effectively…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-26 Haoxu Wang , Biao Tian , Yiheng Jiang , Zexu Pan , Shengkui Zhao , Bin Ma , Daren Chen , Xiangang Li

Human trajectory forecasting is important for intelligent multimedia systems operating in visually complex environments, such as autonomous driving and crowd surveillance. Although Conditional Flow Matching (CFM) has shown strong ability in…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Xuepeng Jing , Wenhuan Lu , Hao Meng , Zhizhi Yu , Jianguo Wei

Rectified flow models have become a de facto standard in image generation due to their stable sampling trajectories and high-fidelity outputs. Despite their strong generative capabilities, they face critical limitations in image editing…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Sung-Hoon Yoon , Minghan Li , Gaspard Beaudouin , Congcong Wen , Muhammad Rafay Azhar , Mengyu Wang

Well-designed prompts can guide text-to-image models to generate amazing images. However, the performant prompts are often model-specific and misaligned with user input. Instead of laborious human engineering, we propose prompt adaptation,…

Computation and Language · Computer Science 2024-01-01 Yaru Hao , Zewen Chi , Li Dong , Furu Wei

This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gradients through the differentiable generation process of flow matching. However,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Zhanhao Liang , Tao Yang , Jie Wu , Chengjian Feng , Liang Zheng

Flow matching models (FMs) have revolutionized text-to-image (T2I) generation, with reinforcement learning (RL) serving as a critical post-training strategy for alignment with reward objectives. In this research, we show that current RL…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Fu-Yun Wang , Han Zhang , Michael Gharbi , Hongsheng Li , Taesung Park

Foundational language models show a remarkable ability to learn new concepts during inference via context data. However, similar work for images lag behind. To address this challenge, we introduce FLoWN, a flow matching model that learns to…

Machine Learning · Computer Science 2025-04-22 Daniel Saragih , Deyu Cao , Tejas Balaji , Ashwin Santhosh

Scene flow prediction is a crucial underlying task in understanding dynamic scenes as it offers fundamental motion information. However, contemporary scene flow methods encounter three major challenges. Firstly, flow estimation solely based…

Computer Vision and Pattern Recognition · Computer Science 2024-11-15 Zhiyang Lu , Qinghan Chen , Ming Cheng

Inference-time guided sampling steers state-of-the-art diffusion and flow models without fine-tuning by interpreting the generation process as a controllable trajectory. This provides a simple and flexible way to inject external constraints…

Artificial Intelligence · Computer Science 2026-05-21 Xuehui Yu , Fucheng Cai , Meiyi Wang , Xiaopeng Fan , Harold Soh

Recent progress in text-to-music generation has enabled models to synthesize high-quality musical segments, full compositions, and even respond to fine-grained control signals, e.g. chord progressions. State-of-the-art (SOTA) systems differ…

Sound · Computer Science 2025-09-05 Or Tal , Felix Kreuk , Yossi Adi

The dataset distributions in offline reinforcement learning (RL) often exhibit complex and multi-modal distributions, necessitating expressive policies to capture such distributions beyond widely-used Gaussian policies. To handle such…

Machine Learning · Computer Science 2026-02-23 Jongseong Chae , Jongeui Park , Yongjae Shin , Gyeongmin Kim , Seungyul Han , Youngchul Sung

Deep generative models have shown impressive results in text-to-image synthesis. However, current text-to-image models often generate images that are inadequately aligned with text prompts. We propose a fine-tuning method for aligning such…

Channel estimation is a fundamental challenge in massive multiple-input multiple-output systems, where estimation accuracy governs the spectral efficiency and link reliability. In this work, we introduce Recursive Flow (RC-Flow), a novel…

Information Theory · Computer Science 2026-01-26 Zehua Jiang , Fenghao Zhu , Chongwen Huang , Richeng Jin , Zhaohui Yang , Xiaoming Chen , Zhaoyang Zhang , Mérouane Debbah

Recent work has shown that inference-time reasoning and reflection can improve text-to-image generation without retraining. However, existing approaches often rely on implicit, holistic critiques or unconstrained prompt rewrites, making…

Computer Vision and Pattern Recognition · Computer Science 2026-01-22 V. Kovalev , A. Kuvshinov , A. Buzovkin , D. Pokidov , D. Timonin

We propose Flow-Anchored Noise-conditioned Q-Learning (FAN), a highly efficient and high-performing offline reinforcement learning (RL) algorithm. Recent work has shown that expressive flow policies and distributional critics improve…

Machine Learning · Computer Science 2026-05-29 Sungyoung Lee , Dohyeong Kim , Eshan Balachandar , Zelal Su Mustafaoglu , Keshav Pingali

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Computation and Language · Computer Science 2024-02-20 Meng Cao , Lei Shu , Lei Yu , Yun Zhu , Nevan Wichers , Yinxiao Liu , Lei Meng

Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in few step text to image generators. However, existing RL based approaches for flow matching…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Zhixiong Yue , Zixuan Ni , Feiyang Ye , Jinshan Zhang , Sheng Shen , Zhenpeng Mi

Robotic manipulation remains challenging for reinforcement learning due to contact-rich dynamics, long horizons, and training instability. Although off-policy actor-critic algorithms such as SAC and TD3 perform well in simulation, they…

Robotics · Computer Science 2026-04-03 Yu Zhang , Karl Mason

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…

Computer Vision and Pattern Recognition · Computer Science 2025-02-21 Xiaofeng Yang , Cheng Chen , Xulei Yang , Fayao Liu , Guosheng Lin