method · first seen 4 Oct 2026
token-level credit assignment
Distributing sequence-level reward signals to individual generated tokens to refine policy updates.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement LearningPapers · 4 Oct 2026 · Lin Qiu, Yao Liu, Diyi Hu, Hanqing Zeng, Onur Gungor, Chujie Chen, Jiayi Liu, Ji…
- VAttnPO: Visual Attention-Guided Policy OptimizationPapers · 12 Oct 2026 · Lihao Zheng, Zhenwei Shao, Zhou Yu, Yan Yang, Haoyi Sun, Qian Wang, Ning Mao, Pa…
- Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group SamplingPapers · 14 Oct 2026 · Wei Chen, Yubing Wu, Zhou Xu, Haoyue Zhang, Delu Zeng, Jiahao Wang, Junmei Yang,…
- Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RLPapers · 15 Oct 2026 · Skylar Zhai, Haonan Wang, Zhining Liu, Linxin Song, Xuwei Ding, Jingcheng Liang,…
- Direction-Aware Token Credit Assignment with Reward-Model GradientsPapers · 23 Oct 2026 · Yikuan Hu, Jifeng Zhu, Minle Su, Jiaqin Yue, Gujie Shao, Yanzhe Chen, Haoxuan Ji…
- DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language ModelsPapers · 26 Oct 2026 · Hongze Chen, Miao Pan, Lizhou Liang, Qinfeng Li, Xinyin Ma, Yongliang Shen, Weis…
Latest sources
- Personalized Memory Rubrics: Learning What to Remember per User via Rubric-Guided Credit AssignmentPapers · 10 Nov 2026 · Yupeng Han, Kai Zhang, Shuochen Liu, Ze Liu, Xianquan Wang, Zhihong Pan, Xiangyu…
- Margin-Guided Token Credit for Reinforcement Learning with Verifiable RewardsPapers · 10 Nov 2026 · Chi Liu, Xin Chen, Yuchuan Weng, Srinivasan Manoharan
- Using Experience Twice: Dynamic Process Rubrics for Privileged Token-Level Credit AssignmentPapers · 4 Nov 2026 · Shumao Wu, Kongcheng Zhang, Jianqiang Huang, Baisheng Lai
- DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language ModelsPapers · 26 Oct 2026 · Hongze Chen, Miao Pan, Lizhou Liang, Qinfeng Li, Xinyin Ma, Yongliang Shen, Weis…
- Direction-Aware Token Credit Assignment with Reward-Model GradientsPapers · 23 Oct 2026 · Yikuan Hu, Jifeng Zhu, Minle Su, Jiaqin Yue, Gujie Shao, Yanzhe Chen, Haoxuan Ji…
- Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RLPapers · 15 Oct 2026 · Skylar Zhai, Haonan Wang, Zhining Liu, Linxin Song, Xuwei Ding, Jingcheng Liang,…
- Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group SamplingPapers · 14 Oct 2026 · Wei Chen, Yubing Wu, Zhou Xu, Haoyue Zhang, Delu Zeng, Jiahao Wang, Junmei Yang,…
- VAttnPO: Visual Attention-Guided Policy OptimizationPapers · 12 Oct 2026 · Lihao Zheng, Zhenwei Shao, Zhou Yu, Yan Yang, Haoyi Sun, Qian Wang, Ning Mao, Pa…
- Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement LearningPapers · 4 Oct 2026 · Lin Qiu, Yao Liu, Diyi Hu, Hanqing Zeng, Onur Gungor, Chujie Chen, Jiayi Liu, Ji…