影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
39.01/100
前 15.1%
全站排名 #9,735
发表论文10 篇
平均评分
年均产出3.3 篇/年
Dong Li
研究方向
AI Agent · Large Language Model Alignment · RLHF · reinforcement learning · representation learning · model-based reinforcement learning
19
$Re^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving
ICLR 2026Poster
21
Boosting Multi-Domain Reasoning of LLMs via Curvature-Guided Policy Optimization
ICLR 2026Poster
21
Preference Optimization via Key-step Error Exploration for Multi-step Reasoning in LLMs
ICLR 2026Desk Rejected
17
CAPO: Conflict-Aware Policy Optimization for Large Language Models
ICLR 2026Rejected
11
Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling
ICLR 2026Rejected
10
Probing Confidence Regions for Early Exits in Chain-of-Thought
ICLR 2026Rejected