语言大模型 / LLM - arXivDaily 专题

2511.03997 2025-11-07 cs.CV 50%

PhysCorr: Dual-Reward DPO for Physics-Constrained Text-to-Video Generation with Automated Preference Selection

Peiyao Wang, Weining Wang, Qi Li

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

2511.01083 2025-11-04 cs.RO 50%

Deployable Vision-driven UAV River Navigation via Human-in-the-loop Preference Alignment

Zihan Wang, Jianwen Li, Li-Fan Wu, Nina Mahmoudian

机构 * School of Mechanical Engineering, Purdue University（机械工程学院，普渡大学）

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

Comments Submitted to ICRA 2026

2503.16500 2025-10-21 cs.HC cs.RO 50%

The Impact of VR and 2D Interfaces on Human Feedback in Preference-Based Robot Learning

Jorge de Heuvel, Daniel Marta, Simon Holk, Iolanda Leite, Maren Bennewitz

机构 * Humanoid Robots Lab, University of Bonn, Germany（波恩大学人形机器人实验室）； Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden（皇家理工学院机器人、感知与学习部门）； Robotics Institute Germany（德国机器人研究所）； The Lamarr Institute, Bonn, Germany（德国波恩拉玛尔研究所）； Center for Robotics, University of Bonn, Germany（德国波恩机器人中心）

专题命中后训练与偏好优化：RLHF(abstract)

2510.13331 2025-10-17 cs.CV 50%

Group-Wise Optimization for Self-Extensible Codebooks in Vector Quantized Models

Hong-Kai Zheng, Piji Li

机构 * College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, China（人工智能学院，南京航空航天大学）； MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing, China（国家工业和信息化部模式分析与机器智能重点实验室，南京）； The Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing, China（教育部脑机智能技术重点实验室，南京）

专题命中后训练与偏好优化：post-training(abstract)

2410.13564 2025-10-08 cs.CV 50%

Imagining the Unseen: Generative Location Modeling for Object Placement

Jooyeol Yun, Davide Abati, Mohamed Omran, Jaegul Choo, Amirhossein Habibian, Auke Wiggers

机构 * Qualcomm AI Research（高通人工智能研究）

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

Comments Accepted by ICCV 2025 DRL4Real Workshop

2503.10439 2025-10-06 cs.CV 50%

EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning

Simone Magistri, Tomaso Trinci, Albin Soutif-Cormerais, Joost van de Weijer, Andrew D. Bagdanov

机构 * Communication Center (MICC), University of Florence, Italy Tomaso Trinci. ORCID: 0000-0002-4052-1930 Global Optimization Laboratory, University of Florence, Italy Albin Soutif - Cormerais. ORCID: 0009-0008-1564-2029 LAMP Team, Computer Vision Center, Barcelona, Spain Joost van de Weijer. ORCID: 0000-0002-9656-9706 LAMP Team, Computer Vision Center, Universitat Aut\` o noma de Barcelona, Spain Andrew D. Bagdanov. ORCID: 0000-0001-6408-7043 Media Integration ； Communication Center (MICC), University of Florence, Italy Equal contribution

专题命中后训练与偏好优化：post-training(abstract)

Comments Extension of our previous conference paper https://openreview.net/forum?id=7D9X2cFnt1

2509.05606 2025-10-03 cs.CV 50%

Patch-Level Kernel Alignment for Dense Self-Supervised Learning

Juan Yeo, Ijun Jang, Taesup Kim

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

专题命中后训练与偏好优化：post-training(abstract)

2506.24118 2025-10-02 cs.CY cs.SI 50%

Scaling Human Judgment in Community Notes with LLMs

Haiwen Li, Soham De, Manon Revel, Andreas Haupt, Brad Miller, Keith Coleman, Jay Baxter, Martin Saveski, Michiel A. Bakker

专题命中后训练与偏好优化：LLM(abstract)

2509.23082 2025-09-30 cs.CV 50%

Follow-Your-Preference: Towards Preference-Aligned Image Inpainting

Yutao Shen, Junkun Yuan, Toru Aonishi, Hideki Nakayama, Yue Ma

机构 * The University of Tokyo（东京大学）； Zhejiang University（浙江大学）； Tsinghua University（清华大学）

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

Comments 16 pages,9 figures, 4 tables

2509.17940 2025-09-23 cs.RO cs.CV 50%

DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving

Shuyao Shang, Yuntao Chen, Yuqi Wang, Yingyan Li, Zhaoxiang Zhang

机构 * NLPR, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所神经网络与模式识别实验室）； University of Chinese Academy of Sciences（中国科学院大学）

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

Comments NeurIPS 2025

2509.17627 2025-09-23 cs.CV 50%

OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

Jinshu Chen, Xinghui Li, Xu Bai, Tianxiang Ma, Pengze Zhang, Zhuowei Chen, Gen Li, Lijie Liu, Songtao Zhao, Bingchuan Li, Qian He

机构 * Intelligent Creation Lab, ByteDance（字节跳动智能创作实验室）

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

Comments Github Page: https://phantom-video.github.io/OmniInsert/

2509.15968 2025-09-22 cs.RO cs.CV 50%

CoReVLA: A Dual-Stage End-to-End Autonomous Driving Framework for Long-Tail Scenarios via Collect-and-Refine

Shiyu Fang, Yiming Cui, Haoyang Liang, Chen Lv, Peng Hang, Jian Sun

机构 * College of Transportation, Tongji University（同济大学交通运输学院）

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

2509.06887 2025-09-11 cs.IR 50%

UniSearch: Rethinking Search System with a Unified Generative Architecture

Jiahui Chen, Xiaoze Jiang, Zhibo Wang, Quanzhi Zhu, Junyao Zhao, Feng Hu, Kang Pan, Ao Xie, Maohua Pei, Zhiheng Qin, Hongjing Zhang, Zhixin Zhai, Xiaobo Guo, Runbin Zhou, Kefeng Wang, Mingyang Geng, Cheng Chen, Jingshan Lv, Yupeng Huang, Xiao Liang, Han Li

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

2509.01232 2025-09-03 cs.CV 50%

FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Framework

Lingzhou Mu, Qiang Wang, Fan Jiang, Mengchao Wang, Yaqi Fan, Mu Xu, Kai Zhang

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

Comments https://fantasy-amap.github.io/fantasy-hsi/

2407.15842 2025-08-28 cs.CV cs.GR 50%

DiffArtist: Towards Structure and Appearance Controllable Image Stylization

Ruixiang Jiang, Changwen Chen

机构 * The Hong Kong Polytechnic University（香港理工大学）

专题命中后训练与偏好优化：LLM(abstract)

Comments Accepted to ACM MM 2025, Homepage: https://DiffusionArtist.github.io

2410.11571 2025-08-21 cs.RO 50%

SDS -- See it, Do it, Sorted: Quadruped Skill Synthesis from Single Video Demonstration

Maria Stamatopoulou, Jeffrey Li, Dimitrios Kanoulas

机构 * Robot Perception Lab, University College London, United Kingdom（伦敦大学学院机器人感知实验室）

专题命中后训练与偏好优化：prompting(abstract)

2508.11904 2025-08-19 cs.CV 50%

SafeCtrl: Region-Based Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress

Lingyun Zhang, Yu Xie, Yanwei Fu, Ping Chen

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

2508.06036 2025-08-11 cs.CV 50%

More Is Better: A MoE-Based Emotion Recognition Framework with Human Preference Alignment

Jun Xie, Yingjian Zhu, Feng Chen, Zhenghao Zhang, Xiaohui Fan, Hongzhu Yi, Xinming Wang, Chen Yu, Yue Bi, Zhaoran Zhao, Xiongjun Guan, Zhepeng Wang

机构 * Lenovo Research（联想研究）； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； University of Chinese Academy of Sciences（中国科学院大学）； Tsinghua University（清华大学）； Beijing Jiaotong University（北京交通大学）； Shandong University（山东大学）

专题命中后训练与偏好优化：language model(abstract)

2508.03619 2025-08-06 physics.chem-ph 50%

FlowBack-Adjoint: Physics-Aware and Energy-Guided Conditional Flow-Matching for All-Atom Protein Backmapping

Alex Berlaga, Michael S. Jones, Andrew L. Ferguson

专题命中后训练与偏好优化：post-training(abstract)

2508.00834 2025-08-05 cs.CV 50%

Team PA-VCG's Solution for Competition on Understanding Chinese College Entrance Exam Papers in ICDAR'25

Wei Wu, Wenjie Wang, Yang Tan, Ying Liu, Liang Diao, Lin Huang, Kaihe Xu, Wenfeng Xie, Ziling Lin

机构 * Visual Computing Group, Ping An Property & Casualty Insurance Company（平安财产保险有限公司视觉计算组）

专题命中后训练与偏好优化：post-training(abstract)

Comments Technical Report

2507.22356 2025-07-31 cs.RO 50%

In-Situ Soil-Property Estimation and Bayesian Mapping with a Simulated Compact Track Loader

W. Jacob Wagner, Ahmet Soylemezoglu, Katherine Driggs-Campbell

机构 * W. Jacob Wagner（独立研究者）； Ahmet Soylemezoglu（独立研究者）； Katherine Driggs-Campbell（独立研究者）

专题命中后训练与偏好优化：post-training(abstract)

Comments 29 pages, 12 figures, 5 algorithms, ISTVS 2025

2507.04072 2025-07-08 cs.IR 50%

CTR-Guided Generative Query Suggestion in Conversational Search

Erxue Min, Hsiu-Yuan Huang, Xihong Yang, Min Yang, Xin Jia, Yunfang Wu, Hengyi Cai, Junfeng Wang, Shuaiqiang Wang, Dawei Yin

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

2412.03177 2025-06-30 cs.CV 50%

PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation

Qihan Huang, Weilong Dai, Jinlong Liu, Wanggui He, Hao Jiang, Mingli Song, Jie Song

机构 * Zhejiang University（浙江大学）； Alibaba Group（阿里巴巴集团）

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

2506.12590 2025-06-17 cs.SE 50%

A Mapping Study About Training in Industry Context in Software Engineering

Breno Alves de Andrade, Rodrigo Siqueira, Lidiane Gomes, Antonio Oliveira, Danilo Monteiro Ribeiro

专题命中后训练与偏好优化：post-training(abstract)

2506.10813 2025-06-13 cs.CV eess.IV eess.SP 50%

Unsupervised Deformable Image Registration with Structural Nonparametric Smoothing

Hang Zhang, Xiang Chen, Renjiu Hu, Rongguang Wang, Jinwei Zhang, Min Liu, Yaonan Wang, Gaolei Li, Xinxing Cheng, Jinming Duan

机构 * Cornell University（康奈尔大学）； Hunan University（湖南大学）； University of Pennsylvania（宾夕法尼亚大学）； Johns Hopkins University（约翰霍普金斯大学）； Shanghai Jiao Tong University（上海交通大学）； University of Birmingham（伯明翰大学）； University of Manchester（曼彻斯特大学）

专题命中后训练与偏好优化：post-training(abstract)

Comments Accepted for publication at Information Processing in Medical Imaging (IPMI) 2025

2506.06602 2025-06-10 cs.CV 50%

Zero Shot Composed Image Retrieval

Santhosh Kakarla, Gautama Shastry Bulusu Venkata

机构 * George Mason University（乔治·玛森大学）

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

Comments 8 pages, 3 figures

2505.14405 2025-05-21 cs.CV 50%

Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency

Jiafeng Liang, Shixin Jiang, Xuan Dong, Ning Wang, Zheng Chu, Hui Su, Jinlan Fu, Ming Liu, See-Kiong Ng, Bing Qin

机构 * Harbin Institute of Technology（哈尔滨工业大学）； Peng Cheng Laboratory（鹏城实验室）； National University of Singapore（新加坡国立大学）； Meituan Inc.（美团公司）

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

2505.05159 2025-05-16 eess.AS 50%

FlexSpeech: Towards Stable, Controllable and Expressive Text-to-Speech

Linhan Ma, Dake Guo, He Wang, Jin Xu, Lei Xie

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

Comments 10 pages, 5 figures

2504.10329 2025-04-22 cs.CV 50%

InstructEngine: Instruction-driven Text-to-Image Alignment

Xingyu Lu, Yuhang Hu, YiFan Zhang, Kaiyu Jiang, Changyi Liu, Tianke Zhang, Jinpeng Wang, Chun Yuan, Bin Wen, Fan Yang, Tingting Gao, Di Zhang

机构 * Tsinghua University（清华大学）； Kuaishou Technology（快手科技）； CASIA（中国科学院自动化研究所）

专题命中后训练与偏好优化：RLHF(abstract)

Comments 8 pages, 7 figures

2504.08291 2025-04-14 cs.CV 50%

DreamFuse: Adaptive Image Fusion with Diffusion Transformer

Junjia Huang, Pengxiang Yan, Jiyang Liu, Jie Wu, Zhao Wang, Yitong Wang, Liang Lin, Guanbin Li

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

Comments under review

1. 后训练与偏好优化 4541 篇

PhysCorr: Dual-Reward DPO for Physics-Constrained Text-to-Video Generation with Automated Preference Selection

Deployable Vision-driven UAV River Navigation via Human-in-the-loop Preference Alignment

The Impact of VR and 2D Interfaces on Human Feedback in Preference-Based Robot Learning

Group-Wise Optimization for Self-Extensible Codebooks in Vector Quantized Models

Imagining the Unseen: Generative Location Modeling for Object Placement

EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning

Patch-Level Kernel Alignment for Dense Self-Supervised Learning

Scaling Human Judgment in Community Notes with LLMs

Follow-Your-Preference: Towards Preference-Aligned Image Inpainting

DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving

OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

CoReVLA: A Dual-Stage End-to-End Autonomous Driving Framework for Long-Tail Scenarios via Collect-and-Refine

UniSearch: Rethinking Search System with a Unified Generative Architecture

FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Framework

DiffArtist: Towards Structure and Appearance Controllable Image Stylization

SDS -- See it, Do it, Sorted: Quadruped Skill Synthesis from Single Video Demonstration

SafeCtrl: Region-Based Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress

More Is Better: A MoE-Based Emotion Recognition Framework with Human Preference Alignment

FlowBack-Adjoint: Physics-Aware and Energy-Guided Conditional Flow-Matching for All-Atom Protein Backmapping

Team PA-VCG's Solution for Competition on Understanding Chinese College Entrance Exam Papers in ICDAR'25

In-Situ Soil-Property Estimation and Bayesian Mapping with a Simulated Compact Track Loader

CTR-Guided Generative Query Suggestion in Conversational Search

PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation

A Mapping Study About Training in Industry Context in Software Engineering

Unsupervised Deformable Image Registration with Structural Nonparametric Smoothing

Zero Shot Composed Image Retrieval

Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency

FlexSpeech: Towards Stable, Controllable and Expressive Text-to-Speech

InstructEngine: Instruction-driven Text-to-Image Alignment

DreamFuse: Adaptive Image Fusion with Diffusion Transformer