Reward Modeling

Follow this topic Ask about this topic

Momentum

24 papers in the last four weeks, up 118% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 197

All topics

Claim-Level Rubric Rewards for Video Caption Reinforcement Learning
Jul 6, 2026Mingqi Gao, Hongyuan Dong, Yifei Chen +6Reward Modeling Video Captioning
1Tsinghua Shenzhen International Graduate School, Tsinghua University · 3LLM Department, Tencent · University of Chinese Academy of Sciences
Attention Limited Reward Learning
Jul 6, 2026Wenqian XingPairwise Preference Learning Reward Modeling
Management Science and Engineering Department, Stanford University
Reward Lightning: Fast Video Generation via Homologous Preference Distillation
Jul 4, 2026Jiaxiang Cheng, Bing Ma, Xuhua Ren +4Diffusion Model Alignment Reward Modeling
Tencent Hunyuan, China
Rank-Then-Act: Reward-Free Control from Frame-Order Progress
Jul 2, 2026Yuriy Maksyuta, George Bredis, Ruslan Rakhimov +1RL Control Reward Modeling
T-Tech
Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling
Jul 2, 2026Dazhi Fu, Jiuding Yang, Yiwen Guo +1Reward Modeling LLM-as-a-Judge
School of Data Science, The Chinese University of Hong Kong, Shenzhen, China · LIGHTSPEED · Independent Researcher
Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist
Jun 30, 2026Yuanhao Ban, Tong Xie, Sohyun An +6Reward Modeling Compositional T2I Generation
1Arena Intelligence Inc · 2UCLA
Test-Time Verification for Text-to-SQL via Outcome Reward Models
Jun 29, 2026Mattia Tritto, Giuseppe Farano, Dario Di Palma +4Reward Modeling LLM Answer Verification
Polytechnic University of Bari, Bari, Italy · IBM T.J. Watson Research Center, Yorktown Heights, NY, USA
Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models
Jun 29, 2026Subramanyam Sahoo, Aman Chadha, Vinija Jain +1Reward Modeling Reward Hacking
1Horizon Research · 2Apple · 3Meta +1
Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation
Jun 29, 2026Shihao Zhang, Yunzhi Li, Yuguang Yan +4Reward Modeling Diffusion Model Guidance
Huawei Central Research Institute · Guangdong University of Technology
To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation
Jun 28, 2026Jiuheng Lin, Chen Zhang, Yansong FengCoT Faithfulness Reward Modeling
Wangxuan Institute of Computer Technology, Peking University
HPRO: Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-Speech
Jun 26, 2026Sihang Nie, Xiaofen Xing, Rui Xing +5Reward Modeling Speech Prosody
South China University of Technology, China · Huya Inc., China · Tongyi Fun Team, Alibaba Group, China +1
Qwen-Image-2.0-RL Technical Report
Jun 25, 2026Yixian Xu, Kaiyuan Gao, Yuxiang Chen +25Reward Modeling RL for Diffusion Models
Equal contribution. · Corresponding author.
PEBS: Per-rater Empirical-Bayes Shrinkage for RLHF Reward-Model Calibration
Jun 25, 2026Arnav RajReward Modeling Post-Hoc Calibration
Department of Computer Science and Engineering, Indian Institute of Technology Delhi, New Delhi, India.
SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing
Jun 25, 2026Yankai Yang, Yancheng Long, Wei Chen +7Reward Modeling Group Relative Policy Optimization
Harbin Institute of Technology, Shenzhen · Kuaishou Technology
The Verification Horizon: No Silver Bullet for Coding Agent Rewards
Jun 24, 2026Binghai Wang, Chenlong Zhang, Dayiheng Liu +10Reward Modeling Reward Hacking
Qwen Team
MAPL: Multi-Objective Preference Learning for Robot Locomotion
Jun 24, 2026Xiyue Chen, Muhan Lin, Shuyang Shi +1Multi-Objective Reinforcement Learning Reward Modeling
Department of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47906, USA · Department of Computer Science, Purdue University, West Lafayette, IN 47906, USA · independent researcher
Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback
Jun 23, 2026Andreas Chouliaras, Luke Connolly, Dimitris ChatzpoulosReward Modeling Human-in-the-Loop AI
School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland
Discretizing Reward Models
Jun 19, 2026Vijay Viswanathan, Shiqi Wang, Devamanyu Hazarika +4Reward Modeling Reinforcement Learning
1Carnegie Mellon University · 2Meta Superintelligence Labs
PrivacyAlign: Contextual Privacy Alignment for LLM Agents
Jun 19, 2026Manveer Singh Tamber, Abhay Puri, Marc-Etienne Brunet +3Reward Modeling Privacy Leakage in Language Models
University of Waterloo · †Work done during internship at ServiceNow AI Research · 2ServiceNow AI Research +2
Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using Implicit Feedback from Users
Jun 18, 2026Haw-Shiuan Chang, Jeffrey Gomez, Mehul Patwari +2Reward Modeling LLM Alignment
University of Massachusetts, Amherst, USA · York University, Canada
Reward as An Agent for Embodied World Models
Jun 18, 2026Pu Li, Zhigang Lin, Qiang Wu +3Reward Modeling Reward Hacking
Kairos Team
Uncertainty-Aware Reward Modeling for Stable RLHF
Jun 18, 2026Licheng Pan, Haocheng Yang, Haoxuan Li +7Reward Modeling Reward Hacking
Zhejiang University · Xiaohongshu Inc · National University of Singapore +1
Learning User Simulators with Turing Rewards
Jun 17, 2026Yingshan Susan Wang, Cedegao E. Zhang, Linlu Qiu +5Reward Modeling RL for Language Models
Massachusetts Institute of Technology · Stanford University · MIT-IBM Watson AI Lab
Online Reward-Punishment Learning from Fixed-Channel Perceptual Event Streams without Environment Rewards
Jun 17, 2026Zirong LiReward Modeling Reinforcement Learning
Tiangong University
Steerable Cultural Preference Optimization of Reward Models
Jun 17, 2026Minsik Oh, Advit Deepak, Sophie Wu +2Reward Modeling Cultural Bias in Language Models
1Stanford University · University of Amsterdam
TuneJury: An Open Metric for Improving Music Generation Preference Alignment
Jun 15, 2026Yonghyun Kim, Junwon Lee, Haiwen Xia +5Text-to-Music Generation Music Generation Evaluation
Georgia Tech · KAIST · Peking University +3
Graph Structured Combinatorial Semi-Bandit with Nonlinear Reward Associations through Separable Signals
Jun 12, 2026Christoph Bauschmann, Setareh MaghsudiReward Modeling Multi-Armed Bandits
Department of Electrical Engineering and Information Technology Ruhr University Bochum Bochum, Germany
Reward Modeling for Multi-Agent Orchestration
Jun 11, 2026King Yeung Tsang, Zihao Zhao, Vishal Venkataramani +5Reward Modeling Multi-Agent Orchestration
Rutgers University · Salesforce AI Research
Understanding helpfulness and harmless tension in reward models
Jun 11, 2026Eshaan Tanwar, Pepa AtanasovaReward Modeling LLM Alignment
University of Copenhagen
Plan-and-Verify Video Reward Reasoning with Spatio-Temporal Scene Graph Grounding
Jun 10, 2026Hyomin Kim, Junghye Kim, Joanie Hayoun Chung +4Reward Modeling Text-to-Video Generation
Department of Artificial Intelligence, Korea University · Department of Statistics, Korea University

Jul 6, 2026, cs.CVJ/K move · Enter open · S save

Claim-Level Rubric Rewards for Video Caption Reinforcement Learning

Mingqi Gao, Hongyuan Dong, Yifei Chen, Zhisheng Zhong+5

1Tsinghua Shenzhen International Graduate School, Tsinghua University · 3LLM Department, Tencent · University of Chinese Academy of Sciences

Reward Modeling Video Captioning Rubric-Based RL Reinforcement Learning with Verifiable Rewards

Open paper AskPDF arXiv

In this paper, we introduce Claim-Level Rubric Rewards (CuRe), a structured reward framework designed to address the reward-design bottleneck in reinforcement learning for dense video captioning. Existing reward designs generally fall into two categories: holistic response-level judgment across heterogeneous criteria, or alignment-based evaluation against reference captions. However, both paradigms suffer from fundamental limitations. Holistic rewards struggle to ensure factual accuracy and are prone to stylistic reward hacking, while reference-based rewards overly rely on rigid textual alignment, failing to preserve the completeness and diversity inherent to open-ended generation tasks. To address these challenges, CuRe reformulates reward modeling as fine-grained claim-level verification. Specifically, CuRe decomposes captions into category-aware atomic claims through a structured rubric, converting holistic evaluation into simpler and more reliable claim-level verification.

Momentum

Related topics

Latest papers 197