David Simchi-Levi

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Recommendation & Information Retrieval (1)RLHF & Preference Learning (1)Tool Use & Agents (1)

Frequent co-authors

Rui Ai (1)Yu Pan (1)Chonghuan Wang (1)

Papers (1)

Mar 31, 2026

MIT CSAIL1d ago

ShapE-GRPO: Shapley-Enhanced Reward Allocation for Multi-Candidate LLM Training

Stop rewarding all LLM-generated candidates equally: ShapE-GRPO uses Shapley values to fairly distribute credit within sets, leading to better training and faster convergence.

Rui Ai, Yu Pan, David Simchi-Levi +1

Recommendation & Information Retrieval RLHF & Preference Learning Tool Use & Agents

Search

David Simchi-Levi

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)