语言大模型 / LLM

Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization

Alberto Compagnoni, Davide Caffagni, Nicholas Moratelli, Lorenzo Baraldi, Marcella Cornia, Rita Cucchiara

机构 * University of Modena and Reggio Emilia（摩德纳和雷吉奥艾米利亚大学） 纠错

专题命中 后训练与偏好优化 ：preference optimization(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments BMVC 2025

The Uneven Impact of Post-Training Quantization in Machine Translation

Benjamin Marie, Atsushi Fujita

机构 * NICT（日本信息与通信技术研究所） 纠错

专题命中 后训练与偏好优化 ：post-training(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Quantum Verifiable Rewards for Post-Training Qiskit Code Assistant

Nicolas Dupuis, Adarsh Tiwari, Youssef Mroueh, David Kremer, Ismael Faro, Juan Cruz-Benito

机构 * IBM Quantum（IBM量子） 纠错

专题命中 后训练与偏好优化 ：post-training(title,abstract)；分类 cs.AI

RLMR: Reinforcement Learning with Mixed Rewards for Creative Writing

Jianxing Liao, Tian Zhang, Xiao Feng, Yusong Zhang, Rui Yang, Haorui Wang, Bosi Wen, Ziying Wang, Runzhi Shi

机构 * Tencent（腾讯） 纠错

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

OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning

Yuan Gong, Xionghui Wang, Jie Wu, Shiyin Wang, Yitong Wang, Xinglong Wu

机构 * ByteDance Inc.（字节跳动公司） 纠错

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

Comments project url: https://one-reward.github.io

DanceGRPO: Unleashing GRPO on Visual Generation

Zeyue Xue, Jie Wu, Yu Gao, Fangyuan Kong, Lingting Zhu, Mengzhao Chen, Zhiheng Liu, Wei Liu, Qiushan Guo, Weilin Huang, Ping Luo

机构 * The University of Hong Kong（香港大学） 纠错

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

Comments Project Page: https://dancegrpo.github.io/

DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness

Ruining Li, Chuanxia Zheng, Christian Rupprecht, Andrea Vedaldi

机构 * Visual Geometry Group, University of Oxford（牛津大学视觉几何组） 纠错

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

Comments Accepted at ICCV 2025 (Highlight). Project page: https://ruiningli.com/dso