语言大模型 / LLM

Dopamine Audiobook: A Training-free MLLM Agent for Emotional and Immersive Audiobook Generation

Yan Rong, Shan Yang, Chenxing Li, Dong Yu, Li Liu

专题命中 后训练与偏好优化 ：large language model(abstract)；language model(abstract)

Learning User Preferences for Image Generation Model

Wenyi Mo, Ying Ba, Tianyu Zhang, Yalong Bai, Biye Li

专题命中 后训练与偏好优化 ：large language model(abstract)；language model(abstract)

AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning

Shihao Yuan, Yahui Liu, Yang Yue, Jingyuan Zhang, Wangmeng Zuo, Qi Wang, Fuzheng Zhang, Guorui Zhou

专题命中 后训练与偏好优化 ：large language model(abstract)；language model(abstract)

Comments 27 pages, 15 figures

Unified Vision-Language-Action Model

Yuqi Wang, Xinghang Li, Wenxuan Wang, Junbo Zhang, Yingyan Li, Yuntao Chen, Xinlong Wang, Zhaoxiang Zhang

机构 * CASIA（中国科学院自动化研究所） ； BAAI（阿里巴巴人工智能研究院） ； THU（清华大学） ； HKISI（香港理工大学） 纠错

专题命中 后训练与偏好优化 ：language model(abstract)；post-training(abstract)

Comments technical report

Aligning Anime Video Generation with Human Feedback

Bingwen Zhu, Yudong Jiang, Baohan Xu, Siqian Yang, Mingyu Yin, Yidi Wu, Huyang Sun, Zuxuan Wu

机构 * Fudan University（复旦大学） ； Bilibili Inc（哔哩哔哩公司） 纠错

专题命中 后训练与偏好优化 ：language model(abstract)；preference optimization(abstract)

Comments 10 pages, 7 figures, 7 tables

Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning

Xiaokun Wang, Peiyu Wang, Jiangbo Pei, Wei Shen, Yi Peng, Yunzhuo Hao, Weijie Qiu, Ai Jian, Tianyidan Xie, Xuchen Song, Yang Liu, Yahui Zhou

机构 * Skywork AI（Skywork人工智能公司） ； Kunlun Inc.（昆仑公司） 纠错

专题命中 后训练与偏好优化 ：language model(abstract)；preference optimization(abstract)

Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment

Xueyao Zhang, Yuancheng Wang, Chaoren Wang, Ziniu Li, Zhuo Chen, Zhizheng Wu

专题命中 后训练与偏好优化 ：pretraining(abstract)；preference optimization(abstract)

Comments Accepted by ACL 2025

Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces

Souhail Hadgi, Luca Moschella, Andrea Santilli, Diego Gomez, Qixing Huang, Emanuele Rodolà, Simone Melzi, Maks Ovsjanikov

机构 * École polytechnique（巴黎政治学院） ； Sapienza University of Rome（罗马大学） ； University of Milano-Bicocca（米兰-布雷拉大学） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

专题命中 后训练与偏好优化 ：foundation model(abstract)；post-training(abstract)

Comments CVPR 2025

Generating Plausible Distractors for Multiple-Choice Questions via Student Choice Prediction

Yooseop Lee, Suin Kim, Yohan Jo

机构 * Graduate School of Data Science, Seoul National University（数据科学研究生院，首尔国立大学） 纠错

专题命中 后训练与偏好优化 ：preference optimization(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments This paper has been accepted for publication at ACL 2025

PPO-BR: Dual-Signal Entropy-Reward Adaptation for Trust Region Policy Optimization

Ben Rahman

专题命中 后训练与偏好优化 ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments This manuscript builds upon an earlier version posted to TechRxiv. This arXiv version includes an updated comparison with GRPO (Group Relative Policy Optimization)

Transferring Textual Preferences to Vision-Language Understanding through Model Merging

Chen-An Li, Tzu-Han Lin, Yun-Nung Chen, Hung-yi Lee

机构 * National Taiwan University（台湾大学） 纠错

专题命中 后训练与偏好优化 ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to ACL 2025 main

M-RewardBench: Evaluating Reward Models in Multilingual Settings

Srishti Gureja, Lester James V. Miranda, Shayekh Bin Islam, Rishabh Maheshwary, Drishti Sharma, Gusti Winata, Nathan Lambert, Sebastian Ruder, Sara Hooker, Marzieh Fadaee

专题命中 后训练与偏好优化 ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 16 pages, 6 figures, 10 tables. Website: https://m-rewardbench.github.io/ , Updated results with latest models. Added more author information

Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization

Sunghwan Kim, Dongjin Kang, Taeyoon Kwon, Hyungjoo Chae, Dongha Lee, Jinyoung Yeo

专题命中 后训练与偏好优化 ：RLHF(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to ACL 2025

VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulation

Chaofan Zhang, Peng Hao, Xiaoge Cao, Xiaoshuai Hao, Shaowei Cui, Shuo Wang

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院） ； Samsung R&D Institute China–Beijing（三星中国北京研发中心） ； Beijing Academy of Artificial Intelligence（北京人工智能研究院） 纠错

专题命中 后训练与偏好优化 ：language model(abstract)；preference optimization(abstract)

JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift

Julien Piet, Xiao Huang, Dennis Jacob, Annabella Chow, Maha Alrashed, Geng Zhao, Zhanhao Hu, Chawin Sitawarin, Basel Alomair, David Wagner

专题命中 后训练与偏好优化 ：language model(abstract)；RLHF(abstract)

Comments 18 pages, 19 figures

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation

Leigang Qu, Haochuan Li, Wenjie Wang, Xiang Liu, Juncheng Li, Liqiang Nie, Tat-Seng Chua

专题命中 后训练与偏好优化 ：preference optimization(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments CVPR 2025 Camera-ready. Project page: https://silmm.github.io/

SEAlign: Alignment Training for Software Engineering Agent

Kechi Zhang, Huangzhao Zhang, Ge Li, Jinliang You, Jia Li, Yunfei Zhao, Zhi Jin

专题命中 后训练与偏好优化 ：post-training(abstract)；preference optimization(abstract)

LEGION: Learning to Ground and Explain for Synthetic Image Detection

Hengrui Kang, Siwei Wen, Zichen Wen, Junyan Ye, Weijia Li, Peilin Feng, Baichuan Zhou, Bin Wang, Dahua Lin, Linfeng Zhang, Conghui He

专题命中 后训练与偏好优化 ：large language model(abstract)；language model(abstract)

Comments Project Page: https://opendatalab.github.io/LEGION

PromptLNet: Region-Adaptive Aesthetic Enhancement via Prompt Guidance in Low-Light Enhancement Net

Jun Yin, Yangfan He, Miao Zhang, Pengyu Zeng, Tianyi Wang, Shuai Lu, Xueqian Wang

专题命中 后训练与偏好优化 ：large language model(abstract)；language model(abstract)

HelpSteer2-Preference: Complementing Ratings with Preferences

Zhilin Wang, Alexander Bukharin, Olivier Delalleau, Daniel Egert, Gerald Shen, Jiaqi Zeng, Oleksii Kuchaiev, Yi Dong

专题命中 后训练与偏好优化 ：RLHF(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to ICLR 2025; 28 pages, 3 figures

AgentRM: Enhancing Agent Generalization with Reward Modeling

Yu Xia, Jingru Fan, Weize Chen, Siyu Yan, Xin Cong, Zhong Zhang, Yaxi Lu, Yankai Lin, Zhiyuan Liu, Maosong Sun

专题命中 后训练与偏好优化 ：LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?

Xueru Wen, Jie Lou, Yaojie Lu, Hongyu Lin, Xing Yu, Xinyu Lu, Ben He, Xianpei Han, Debing Zhang, Le Sun

专题命中 后训练与偏好优化 ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at ICLR2025 Spotlight

Curry-DPO: Enhancing Alignment using Curriculum Learning & Ranked Preferences

Pulkit Pattnaik, Rishabh Maheshwary, Kelechi Ogueji, Vikas Yadav, Sathwik Tejaswi Madhusudhan

专题命中 后训练与偏好优化 ：preference optimization(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Published at EMNLP 2024 as long (findings) conference paper

Carrot and Stick: Eliciting Comparison Data and Beyond

Yiling Chen, Shi Feng, Fang-Yi Yu

专题命中 后训练与偏好优化 ：large language model(abstract)；language model(abstract)

Comments 33 pages, 8 figures

Text2Interaction: Establishing Safe and Preferable Human-Robot Interaction

Jakob Thumm, Christopher Agia, Marco Pavone, Matthias Althoff

专题命中 后训练与偏好优化 ：large language model(abstract)；language model(abstract)

Comments Accepted for the Conference on Robot Learning (CoRL) 2024. Available at: https://openreview.net/forum?id=s0VNSnPeoA

Wikimedia data for AI: a review of Wikimedia datasets for NLP tasks and AI-assisted editing

Isaac Johnson, Lucie-Aimée Kaffee, Miriam Redi

专题命中 后训练与偏好优化 ：language model(abstract)；post-training(abstract)

Comments Accepted to NLP for Wikipedia Workshop at EMNLP '24

Evaluating Robustness of Reward Models for Mathematical Reasoning

Sunghwan Kim, Dongjin Kang, Taeyoon Kwon, Hyungjoo Chae, Jungsoo Won, Dongha Lee, Jinyoung Yeo

专题命中 后训练与偏好优化 ：RLHF(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Work in progress

PopAlign: Population-Level Alignment for Fair Text-to-Image Generation

Shufan Li, Harkanwar Singh, Aditya Grover

专题命中 后训练与偏好优化 ：RLHF(abstract)；preference optimization(abstract)

Comments 18 pages, 10 figures

Improving Dialogue Agents by Decomposing One Global Explicit Annotation with Local Implicit Multimodal Feedback

Dong Won Lee, Hae Won Park, Yoon Kim, Cynthia Breazeal, Louis-Philippe Morency

专题命中 后训练与偏好优化 ：LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 10 pages, 3 figures, 2 tables

Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decoding

Jiacheng Liu, Andrew Cohen, Ramakanth Pasunuru, Yejin Choi, Hannaneh Hajishirzi, Asli Celikyilmaz

专题命中 后训练与偏好优化 ：language model(abstract)；分类 cs.CL、cs.AI、cs.LG