English
Related papers

Related papers: SIPO: Stabilized and Improved Preference Optimizat…

200 papers

Direct Preference Optimization (DPO) optimizes language models to align with human preferences. Utilizing on-policy samples, generated directly by the policy model, typically results in better performance due to its distribution consistency…

Machine Learning · Computer Science 2025-03-21 Yunan Wang , Jijie Li , Bo-Wen Zhang , Liangdong Wang , Guang Liu

Preference optimization methods such as DPO align large language models (LLMs) using paired comparisons, but their effectiveness can be highly sensitive to the quality and difficulty of preference pairs. A common heuristic treats…

Artificial Intelligence · Computer Science 2026-02-03 Jinlong Pang , Zhaowei Zhu , Na Di , Yichi Zhang , Yaxuan Wang , Chen Qian , Yang Liu

Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback (RLHF) for large language models (LLMs) by directly optimizing human preferences without an explicit reward model. We find that during DPO training,…

Computation and Language · Computer Science 2026-01-01 Junshu Pan , Wei Shen , Shulin Huang , Qiji Zhou , Yue Zhang

Diffusion policies (DP) have demonstrated significant potential in visual navigation by capturing diverse multi-modal trajectory distributions. However, standard imitation learning (IL), which most DP methods rely on for training, often…

Robotics · Computer Science 2026-02-02 Runhua Zhang , Junyi Hou , Changxu Cheng , Qiyi Chen , Tao Wang , Wuyue Zhao

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…

Machine Learning · Computer Science 2025-08-20 Hongze Tan , Yuchen Li

Diffusion policies are a powerful paradigm for robotic control, but fine-tuning them with human preferences is fundamentally challenged by the multi-step structure of the denoising process. To overcome this, we introduce a Unified Markov…

Robotics · Computer Science 2026-02-03 Amitesh Vatsa , Zhixian Xie , Wanxin Jin

Traditional preference tuning methods for LLMs/Visual Generative Models often rely solely on reward model labeling, which can be opaque, offer limited insights into the rationale behind preferences, and are prone to issues such as reward…

Machine Learning · Computer Science 2026-01-13 Hanyang Zhao , Haoxian Chen , Yucheng Guo , Genta Indra Winata , Tingting Ou , Ziyu Huang , David D. Yao , Wenpin Tang

Recommender systems predict personalized item rankings based on user preference distributions derived from historical behavior data. Recently, diffusion models (DMs) have gained attention in recommendation for their ability to model complex…

Information Retrieval · Computer Science 2025-04-22 Shuo Liu , An Zhang , Guoqing Hu , Hong Qian , Tat-seng Chua

Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated responses. This is…

Computation and Language · Computer Science 2025-05-23 Jack Lanchantin , Angelica Chen , Shehzaad Dhuliawala , Ping Yu , Jason Weston , Sainbayar Sukhbaatar , Ilia Kulikov

Direct Preference Optimization (DPO) and its variants have become increasingly popular for aligning language models with human preferences. These methods aim to teach models to better distinguish between chosen (or preferred) and rejected…

Computation and Language · Computer Science 2025-06-09 Xiliang Yang , Feng Jiang , Qianen Zhang , Lei Zhao , Xiao Li

Direct Preference Optimization (DPO) has been widely used for aligning language models with human preferences in a supervised manner. However, several key questions remain unresolved: the rationale behind its log-ratio reward, how the…

Machine Learning · Computer Science 2025-10-03 Yunjae Won , Hyunji Lee , Hyeonbin Hwang , Minjoon Seo

Aligning large language models (LLMs) with human values is an increasingly critical step in post-training. Direct Preference Optimization (DPO) has emerged as a simple, yet effective alternative to reinforcement learning from human feedback…

Artificial Intelligence · Computer Science 2025-07-29 Yifan Wang , Runjin Chen , Bolian Li , David Cho , Yihe Deng , Ruqi Zhang , Tianlong Chen , Zhangyang Wang , Ananth Grama , Junyuan Hong

In this work, we focus on the alignment problem of diffusion models with a continuous reward function, which represents specific objectives for downstream tasks, such as increasing darkness or improving the aesthetics of images. The central…

Machine Learning · Computer Science 2024-10-03 Zhiwei Tang , Jiangweizhi Peng , Jiasheng Tang , Mingyi Hong , Fan Wang , Tsung-Hui Chang

As development of large language models (LLM) progresses, aligning them with human preferences has become increasingly important. We propose stepwise DPO (sDPO), an extension of the recently popularized direct preference optimization (DPO)…

Computation and Language · Computer Science 2024-10-08 Dahyun Kim , Yungi Kim , Wonho Song , Hyeonwoo Kim , Yunsu Kim , Sanghoon Kim , Chanjun Park

Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted adversarial example generation as a problem of aligning with…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Kaixun Jiang , Zhaoyu Chen , Haijing Guo , Jinglun Li , Jiyuan Fu , Pinxue Guo , Hao Tang , Bo Li , Wenqiang Zhang

Direct Preference Optimization (DPO) has been widely adopted for large language model alignment due to its simple training procedure and lack of an explicit reward model. However, in iterative DPO, when the policy model from the previous…

Information Retrieval · Computer Science 2026-05-25 Lingling Fu , Yongfu Xu

Diffusion models have achieved promising results for Structure-Based Drug Design (SBDD). Nevertheless, high-quality protein subpocket and ligand data are relatively scarce, which hinders the models' generation capabilities. Recently, Direct…

Biomolecules · Quantitative Biology 2026-02-11 Xiwei Cheng , Xiangxin Zhou , Yuwei Yang , Yu Bao , Quanquan Gu

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

In the field of large language models (LLMs), aligning models with the diverse preferences of users is a critical challenge. Direct Preference Optimization (DPO) has played a key role in this area. It works by using pairs of preferences…

Computation and Language · Computer Science 2024-05-29 Yueqin Yin , Zhendong Wang , Yi Gu , Hai Huang , Weizhu Chen , Mingyuan Zhou

Diffusion alignment adapts pretrained diffusion models to sample from reward-tilted distributions along the denoising trajectory. This process naturally admits a Sequential Monte Carlo (SMC) interpretation, where the denoising model acts as…

Machine Learning · Computer Science 2026-02-13 Zijing Ou , Jacob Si , Junyi Zhu , Ondrej Bohdal , Mete Ozay , Taha Ceritli , Yingzhen Li