English
Related papers

Related papers: Coefficients-Preserving Sampling for Reinforcement…

200 papers

Recent progress in flow-based generative models and reinforcement learning (RL) has improved text-image alignment and visual quality. However, current RL training for flow models still has two main problems: (i) GRPO-style fixed per-prompt…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Kaijie Chen , Zhiyang Xu , Ying Shen , Zihao Lin , Yuguang Yao , Lifu Huang

We propose Diffusion-Sharpening, a fine-tuning approach that enhances downstream alignment by optimizing sampling trajectories. Existing RL-based fine-tuning methods focus on single training timesteps and neglect trajectory-level alignment,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Ye Tian , Ling Yang , Xinchen Zhang , Yunhai Tong , Mengdi Wang , Bin Cui

We propose a reinforcement learning (RL) framework for the dynamic selection of the filter parameter in Evolve-Filter (EF) regularization strategies for incompressible turbulent flows. Instead of prescribing the filter radius heuristically,…

Numerical Analysis · Mathematics 2026-03-03 Anna Ivagnes , Maria Strazzullo , Gianluigi Rozza

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…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Guanjie Chen , Shirui Huang , Kai Liu , Jianchen Zhu , Xiaoye Qu , Peng Chen , Yu Cheng , Yifu Sun

Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making tasks. Within this…

Machine Learning · Computer Science 2024-11-19 Feng Chen , Fuguang Han , Cong Guan , Lei Yuan , Zhilong Zhang , Yang Yu , Zongzhang Zhang

We present a novel generative modeling method called diffusion normalizing flow based on stochastic differential equations (SDEs). The algorithm consists of two neural SDEs: a forward SDE that gradually adds noise to the data to transform…

Machine Learning · Computer Science 2021-10-15 Qinsheng Zhang , Yongxin Chen

Sampling is ubiquitous in machine learning methodologies. Due to the growth of large datasets and model complexity, we want to learn and adapt the sampling process while training a representation. Towards achieving this grand goal, a…

Machine Learning · Computer Science 2022-12-14 Jason Xiaotian Dou , Alvin Qingkai Pan , Runxue Bao , Haiyi Harry Mao , Lei Luo , Zhi-Hong Mao

Diffusion and flow-based models have enabled significant progress in generation tasks across various modalities and have recently found applications in predictive learning. However, unlike typical generation tasks that encourage sample…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Yu Zhang , Xingzhuo Guo , Haoran Xu , Jialong Wu , Mingsheng Long

Reinforcement learning (RL) finetuning has become a key technique for enhancing the reasoning abilities of large language models (LLMs). However, its effectiveness critically depends on the selection of training data. Recent advances…

Machine Learning · Computer Science 2026-03-12 Yixiu Mao , Yun Qu , Qi Wang , Heming Zou , Xiangyang Ji

In model-free deep reinforcement learning (RL) algorithms, using noisy value estimates to supervise policy evaluation and optimization is detrimental to the sample efficiency. As this noise is heteroscedastic, its effects can be mitigated…

Machine Learning · Computer Science 2022-05-04 Vincent Mai , Kaustubh Mani , Liam Paull

Continual learning enables large language models to adapt to evolving tasks without retraining from scratch, yet catastrophic forgetting remains a central obstacle. Among continual learning methods, regularization-based approaches are…

Machine Learning · Computer Science 2026-05-26 Mingxu Zhang , Yuhan Li , Lujundong Li , Dazhong Shen , Hui Xiong , Ying Sun

Vision-Language-Action (VLA) models enable robots to understand and perform complex tasks from multimodal input. Although recent work explores using reinforcement learning (RL) to automate the laborious data collection process in scaling…

Machine Learning · Computer Science 2026-01-30 Kang Chen , Zhihao Liu , Tonghe Zhang , Zhen Guo , Si Xu , Hao Lin , Hongzhi Zang , Xiang Li , Quanlu Zhang , Zhaofei Yu , Guoliang Fan , Tiejun Huang , Yu Wang , Chao Yu

Reinforcement learning (RL) has emerged as a promising paradigm for training reasoning-oriented models by leveraging rule-based reward signals. However, RL training typically tends to improve single-sample success rates (i.e., Pass@1) while…

Computation and Language · Computer Science 2026-04-21 Yifu Huo , Chenglong Wang , Ziming Zhu , Shunjie Xing , Peinan Feng , Tongran Liu , Qiaozhi He , Tianhua Zhou , Xiaojia Chang , Jingbo Zhu , Zhengtao Yu , Tong Xiao

Offline reinforcement learning (RL) offers a promising direction for learning policies from pre-collected datasets without requiring further interactions with the environment. However, existing methods struggle to handle out-of-distribution…

Machine Learning · Computer Science 2024-03-12 Zhepeng Cen , Zuxin Liu , Zitong Wang , Yihang Yao , Henry Lam , Ding Zhao

This paper considers a class of reinforcement learning problems, which involve systems with two types of states: stochastic and pseudo-stochastic. In such systems, stochastic states follow a stochastic transition kernel while the…

Machine Learning · Computer Science 2023-11-09 Honghao Wei , Xin Liu , Weina Wang , Lei Ying

Current camera image and signal processing pipelines (ISPs), including deep-trained versions, tend to apply a single filter that is uniformly applied to the entire image. This is despite the fact that most acquired camera images have…

Computer Vision and Pattern Recognition · Computer Science 2023-06-28 Chandrajit Bajaj , Yi Wang , Yunhao Yang

Training an agent to solve control tasks directly from high-dimensional images with model-free reinforcement learning (RL) has proven difficult. A promising approach is to learn a latent representation together with the control policy.…

Machine Learning · Computer Science 2020-07-10 Denis Yarats , Amy Zhang , Ilya Kostrikov , Brandon Amos , Joelle Pineau , Rob Fergus

Reinforcement learning (RL) post-training has become a trending paradigm for enhancing the capabilities of large language models (LLMs). Most existing RL systems for LLMs operate in a fully synchronous manner, where training must wait for…

Machine Learning · Computer Science 2025-11-11 Zekai Qu , Yinxu Pan , Ao Sun , Chaojun Xiao , Xu Han

Reinforcement learning (RL) post-training has enabled newer capabilities in models, such as agentic tool-use for search. However, these models struggle primarily due to limitations with sparse outcome-based rewards and a lack of training…

Machine Learning · Computer Science 2026-05-08 Harsh Goel , Akhil Udathu , Susmija Jabireddy , Pradnesh Kalkar , Atharva Parulekar

The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in…

Image and Video Processing · Electrical Eng. & Systems 2024-09-26 Lingchen Sun , Rongyuan Wu , Jie Liang , Zhengqiang Zhang , Hongwei Yong , Lei Zhang