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
40.56/100
前 14.1%
全站排名 #9,050
发表论文10 篇
平均评分
年均产出3.3 篇/年
Li Erran Li
研究方向
reasoning · AI for science · machine learning · NLP · deep learning · Artificial intelligence · generative AI · LLMs · large multi-modal models · large agent models · reinforcement learning · machine learning systems · computer vision · robotic learning · autonomous driving
31
TIPS: Turn-level Information-Potential Reward Shaping for Search-Augmented LLMs
ICLR 2026Poster
21
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Tree-based Search
ICLR 2026Poster
4
Geometric Constraints as General Interfaces for Robot Manipulation
ICLR 2026Withdrawn
8
DeepScaleR: Effective RL Scaling of Reasoning Models via Iterative Context Lengthening
ICLR 2026Rejected
12
Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards
ICLR 2026Withdrawn
32
Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet Agents
ICLR 2025Rejected
通讯31
Digi-Q: Learning VLM Q-Value Functions for Training Device-Control Agents
ICLR 2025Poster
三作11
Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet Agents
ICML 2025Poster
通讯