English
Related papers

Related papers: Finite Difference Flow Optimization for RL Post-Tr…

200 papers

Offline reinforcement learning (RL) provides a compelling paradigm for training autonomous systems without the risks of online exploration, particularly in safety-critical domains. However, jointly achieving strong safety and performance…

Machine Learning · Computer Science 2026-02-10 Manan Tayal , Mumuksh Tayal

Reinforcement learning (RL) in few-shot scenarios with limited sensor data is challenging due to insufficient training samples, particularly in applications like Dynamic Voltage and Frequency Scaling (DVFS) where sensor readings are…

Machine Learning · Computer Science 2026-01-13 Mohammad Pivezhandi , Abusayeed Saifullah

The advent of the "pre-train, prompt" paradigm has recently extended its generalization ability and data efficiency to graph representation learning, following its achievements in Natural Language Processing (NLP). Initial graph prompt…

Machine Learning · Computer Science 2025-01-20 Jiapeng Zhu , Zichen Ding , Jianxiang Yu , Jiaqi Tan , Xiang Li , Weining Qian

This paper proposes a novel formulation for reinforcement learning (RL) with large language models, explaining why and under what conditions the true sequence-level reward can be optimized via a surrogate token-level objective in policy…

Machine Learning · Computer Science 2025-12-04 Chujie Zheng , Kai Dang , Bowen Yu , Mingze Li , Huiqiang Jiang , Junrong Lin , Yuqiong Liu , Hao Lin , Chencan Wu , Feng Hu , An Yang , Jingren Zhou , Junyang Lin

Diffusion Language Models (dLLMs) have emerged as promising alternatives to Auto-Regressive (AR) models. While recent efforts have validated their pre-training potential and accelerated inference speeds, the post-training landscape for…

Machine Learning · Computer Science 2026-01-07 Ying Zhu , Jiaxin Wan , Xiaoran Liu , Siyang He , Qiqi Wang , Xu Guo , Tianyi Liang , Zengfeng Huang , Ziwei He , Xipeng Qiu

Text-to-multiview (T2MV) diffusion models have shown great promise in generating multiple views of a scene from a single text prompt. While few-step backbones enable real-time T2MV generation, they often compromise key aspects of generation…

Machine Learning · Computer Science 2026-03-18 Ziyi Zhang , Li Shen , Deheng Ye , Yong Luo , Huangxuan Zhao , Meng Liu , Wei Yu , Lefei Zhang

Generative diffusion models (DM) have been extensively utilized in image super-resolution (ISR). Most of the existing methods adopt the denoising loss from DDPMs for model optimization. We posit that introducing reward feedback learning to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-05 Xiaopeng Sun , Qinwei Lin , Yu Gao , Yujie Zhong , Chengjian Feng , Dengjie Li , Zheng Zhao , Jie Hu , Lin Ma

We seek to understand what facilitates sample-efficient learning from historical datasets for sequential decision-making, a problem that is popularly known as offline reinforcement learning (RL). Further, we are interested in algorithms…

Machine Learning · Computer Science 2024-02-07 Thanh Nguyen-Tang , Raman Arora

Reinforcement learning (RL) is an innovative approach to financial decision making, offering specialized solutions to complex investment problems where traditional methods fail. This review analyzes 167 articles from 2017--2025, focusing on…

Computational Finance · Quantitative Finance 2025-12-12 Mohammad Rezoanul Hoque , Md Meftahul Ferdaus , M. Kabir Hassan

Supervised fine-tuning (SFT) and reinforcement learning (RL) are widely used post-training techniques for foundation models. However, their roles in enhancing model generalization capabilities remain unclear. This paper studies the…

Artificial Intelligence · Computer Science 2025-05-27 Tianzhe Chu , Yuexiang Zhai , Jihan Yang , Shengbang Tong , Saining Xie , Dale Schuurmans , Quoc V. Le , Sergey Levine , Yi Ma

Temporal information is essential to learning effective policies with Reinforcement Learning (RL). However, current state-of-the-art RL algorithms either assume that such information is given as part of the state space or, when learning…

Machine Learning · Computer Science 2021-01-07 Wenling Shang , Xiaofei Wang , Aravind Srinivas , Aravind Rajeswaran , Yang Gao , Pieter Abbeel , Michael Laskin

Recently DeepSeek R1 has shown that reinforcement learning (RL) can substantially improve the reasoning capabilities of Large Language Models (LLMs) through a simple yet effective design. The core of R1 lies in its rule-based reward…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Haozhan Shen , Peng Liu , Jingcheng Li , Chunxin Fang , Yibo Ma , Jiajia Liao , Qiaoli Shen , Zilun Zhang , Kangjia Zhao , Qianqian Zhang , Ruochen Xu , Tiancheng Zhao

Continual learning for vision-language models has achieved remarkable performance through synthetic replay, where samples are generated using Stable Diffusion to regularize during finetuning and retain knowledge. However, real-world…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Kaihong Wang , Donghyun Kim , Margrit Betke

There has been significant progress in deep reinforcement learning (RL) in recent years. Nevertheless, finding suitable hyperparameter configurations and reward functions remains challenging even for experts, and performance heavily relies…

Machine Learning · Computer Science 2024-10-10 Julian Dierkes , Emma Cramer , Holger H. Hoos , Sebastian Trimpe

Reinforcement Learning (RL) post-training has become the standard for aligning generative models with human preferences, yet most methods rely on a single scalar reward. When multiple criteria matter, the prevailing practice of ``early…

Machine Learning · Computer Science 2026-04-23 Shelly Golan , Michael Finkelson , Ariel Bereslavsky , Yotam Nitzan , Or Patashnik

Controlling the generative model to adapt a new domain with limited samples is a difficult challenge and it is receiving increasing attention. Recently, methods based on meta-learning have shown promising results for few-shot domain…

Computation and Language · Computer Science 2023-09-07 Pengsen Cheng , Jinqiao Dai , Jiamiao Liu , Jiayong Liu , Peng Jia

Reinforcement learning (RL) has emerged as an effective paradigm for improving the reasoning capability of vision-language models (VLMs). However, RL-based optimization typically depends on costly high-quality annotations that are difficult…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Lin Qiu , Hanqing Zeng , Yao Liu , Bingjun Sun , Guangdeng Liao , Ji Liu

Recent studies have successfully integrated large vision-language models (VLMs) into low-level robotic control by supervised fine-tuning (SFT) with expert robotic datasets, resulting in what we term vision-language-action (VLA) models.…

Robotics · Computer Science 2025-01-29 Yanjiang Guo , Jianke Zhang , Xiaoyu Chen , Xiang Ji , Yen-Jen Wang , Yucheng Hu , Jianyu Chen

While one commonly trains large diffusion models by collecting datasets on target downstream tasks, it is often desired to align and finetune pretrained diffusion models with some reward functions that are either designed by experts or…

Machine Learning · Computer Science 2025-05-20 Zhen Liu , Tim Z. Xiao , Weiyang Liu , Yoshua Bengio , Dinghuai Zhang

Ensuring reliability in modern software systems requires rigorous pre-production testing across highly heterogeneous and evolving environments. Because exhaustive evaluation is infeasible, practitioners must decide how to allocate limited…

Software Engineering · Computer Science 2025-10-08 Yu Zhu