Weihua Du

DualDistill. [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"

CodeGym. [ICLR2026] The official repository for the CodeGym project: "Generalizable End-to-End Tool-Use RL with Synthetic CodeGym"

TURN. [ICML2025] Official Repo for Paper "Optimizing Temperature for Language Models with Multi-Sample Inference"

AdaExplore. The official implementation for paper "AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation"

AutoTruss. [IJCAI 2023] The official repo of paper 'Automatic Truss Design with Reinforcement Learning'

GradAlign. Python