English
Related papers

Related papers: Humanline: Online Alignment as Perceptual Loss

200 papers

Direct Preference Optimization (DPO) has emerged as a lightweight and effective alternative to Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with AI Feedback (RLAIF) for aligning large language and…

Artificial Intelligence · Computer Science 2025-12-16 Zihui Zhao , Zechang Li

Expressive generative models have advanced robotic manipulation by capturing complex, multi-modal action distributions over temporally extended trajectories. However, fine-tuning these policies via RL remains challenging due to instability…

Robotics · Computer Science 2026-04-03 Yuhui Chen , Haoran Li , Zhennan Jiang , Yuxing Qin , Yuxuan Wan , Weiheng Liu , Dongbin Zhao

Aligning denoising generative models with human preferences or verifiable rewards remains a key challenge. While policy-gradient online reinforcement learning (RL) offers a principled post-training framework, its direct application is…

Machine Learning · Computer Science 2026-04-28 Bingda Tang , Yuhui Zhang , Xiaohan Wang , Jiayuan Mao , Ludwig Schmidt , Serena Yeung-Levy

Direct alignment methods typically train large language models (LLMs) by contrasting the likelihoods of preferred and dispreferred responses. While effective at capturing relative preferences, these methods are widely observed to suppress…

Computation and Language · Computer Science 2025-12-04 Kaiyang Guo , Yinchuan Li , Zhitang Chen

A critical component of the current generation of language models is preference alignment, which aims to precisely control the model's behavior to meet human needs and values. The most notable among such methods is Reinforcement Learning…

Artificial Intelligence · Computer Science 2024-10-22 Oh Joon Kwon , Daiki E. Matsunaga , Kee-Eung Kim

This paper presents Perceptual Preference Optimization (PerPO), a perception alignment method aimed at addressing the visual discrimination challenges in generative pre-trained multimodal large language models (MLLMs). To align MLLMs with…

Artificial Intelligence · Computer Science 2025-02-10 Zining Zhu , Liang Zhao , Kangheng Lin , Jinze Yang , En Yu , Chenglong Liu , Haoran Wei , Jianjian Sun , Zheng Ge , Xiangyu Zhang

Direct Preference Optimization (DPO) has emerged as a more computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimization (PPO), eliminating the need for reward models and online…

Computation and Language · Computer Science 2024-10-28 Xin Mao , Feng-Lin Li , Huimin Xu , Wei Zhang , Wang Chen , Anh Tuan Luu

Offline-to-online reinforcement learning (RL), by combining the benefits of offline pretraining and online finetuning, promises enhanced sample efficiency and policy performance. However, existing methods, effective as they are, suffer from…

Machine Learning · Computer Science 2023-05-26 Jianxiong Li , Xiao Hu , Haoran Xu , Jingjing Liu , Xianyuan Zhan , Ya-Qin Zhang

With the rapid advancement of large language models and vision-language models, employing large models as Web Agents has become essential for automated web interaction. However, training Web Agents with reinforcement learning faces critical…

Machine Learning · Computer Science 2025-09-22 Ziyuan Chen , Zhenghui Zhao , Zhangye Han , Miancan Liu , Xianhang Ye , Yiqing Li , Hongbo Min , Jinkui Ren , Xiantao Zhang , Guitao Cao

Preference optimization is crucial for aligning large language models (LLMs) with human values and intentions. A significant challenge in this process is the distribution mismatch between pre-collected offline preference data and the…

Computation and Language · Computer Science 2026-03-02 Junming Yang , Ning Xu , Biao Liu , Shiqi Qiao , Xin Geng

Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. This setting is particularly well-suited for continuous control robotic…

Machine Learning · Computer Science 2022-03-18 Xi Chen , Ali Ghadirzadeh , Tianhe Yu , Yuan Gao , Jianhao Wang , Wenzhe Li , Bin Liang , Chelsea Finn , Chongjie Zhang

Direct Preference Optimization (DPO), which derives reward signals directly from pairwise preference data, has shown its effectiveness on aligning Large Language Models (LLMs) with human preferences. Despite its widespread use across…

Computation and Language · Computer Science 2024-04-09 Duanyu Feng , Bowen Qin , Chen Huang , Zheng Zhang , Wenqiang Lei

The task adaptation and alignment of Large Multimodal Models (LMMs) have been significantly advanced by instruction tuning and further strengthened by recent preference optimization. Yet, most LMMs still suffer from severe modality…

Machine Learning · Computer Science 2025-10-10 Chenxi Liu , Tianyi Xiong , Yanshuo Chen , Ruibo Chen , Yihan Wu , Junfeng Guo , Tianyi Zhou , Heng Huang

Deep reinforcement learning has been able to solve various tasks successfully, however, due to the construction of policy gradient and training dynamics, tuning deep reinforcement learning models remains challenging. As one of the most…

Machine Learning · Computer Science 2026-02-11 Hanyong Wang , Menglong Yang

Online and offline RLHF methods, such as PPO and DPO, have been highly successful in aligning AI with human preferences. Despite their success, however, these methods suffer from fundamental limitations: (a) Models trained with RLHF can…

Machine Learning · Computer Science 2025-04-15 Eugene Choi , Arash Ahmadian , Matthieu Geist , Oilvier Pietquin , Mohammad Gheshlaghi Azar

Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…

Machine Learning · Computer Science 2023-01-05 Daniel Shin , Anca D. Dragan , Daniel S. Brown

Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. This problem setting offers the promise of utilizing such datasets to acquire policies without any…

Machine Learning · Computer Science 2020-11-24 Tianhe Yu , Garrett Thomas , Lantao Yu , Stefano Ermon , James Zou , Sergey Levine , Chelsea Finn , Tengyu Ma

Online on-policy preference learning algorithms for language model alignment such as online direct policy optimization (DPO) can significantly outperform their offline counterparts. We provide a theoretical explanation for this phenomenon…

Machine Learning · Computer Science 2026-01-14 Juno Kim , Jihun Yun , Jason D. Lee , Kwang-Sung Jun

Reinforcement Learning (RL) from Human Preference-based feedback is a popular paradigm for fine-tuning generative models, which has produced impressive models such as GPT-4 and Claude3 Opus. This framework often consists of two steps:…

Machine Learning · Computer Science 2024-04-17 Jonathan D. Chang , Wenhao Zhan , Owen Oertell , Kianté Brantley , Dipendra Misra , Jason D. Lee , Wen Sun

Direct preference optimization (DPO) is a form of reinforcement learning from human feedback (RLHF) where the policy is learned directly from preferential feedback. Although many models of human preferences exist, the critical task of…

Machine Learning · Computer Science 2025-03-04 Branislav Kveton , Xintong Li , Julian McAuley , Ryan Rossi , Jingbo Shang , Junda Wu , Tong Yu