Lei Song

PixelCraft: A Multi-Agent system for High-Fidelity Visual Reasoning on Structured Images

Rethinking Reward Models for Multi-Domain Test-Time Scaling

In-Context Compositional Q-Learning for Offline Reinforcement Learning

Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context Learning

Sample-efficient LLM Optimization with Reset Replay

Unveiling Markov heads in Pretrained Language Models for Offline Reinforcement Learning

From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning

NaDRO: Leveraging Dual-Reward Strategies for LLMs Training on Noisy Data

Efficient Discovery of Pareto Front for Multi-Objective Reinforcement Learning

From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning

Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning

HeurAgenix: A Multi-Agent LLM-Based Paradigm for Adaptive Heuristic Evolution and Selection in Combinatorial Optimization