TreeRL: LLM Reinforcement Learning with On-Policy Tree Search in ACL'25

A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.

[COLING 2025] Automated Molecular Concept Generation and Labeling with Large Language Models

Source code of Multi-Token Assisted Decoding

Official codebase for the Scattered Forest Search: Smarter Code Space Exploration and Inference Scaling with LLMs

DataSciBench: An LLM Agent Benchmark for Data Science (Findings of ACL 2026)

RL Scaling and Test-Time Scaling (ICML'25)

The website of paper "Strategist: Learning Strategic Skills by LLMs via Bi-Level Tree Search"

Repository for Data Distillation for Offline Reinforcement Learning

Sci-BeRT model for paper reference source tracing. Submission for 2024 PST-KDD Cup.

Code and Data for "MIRAI: Evaluating LLM Agents for Event Forecasting"

LLM101n: Let's build a Storyteller

Course project for CS 145 - KDD 2024 AQA Challenge

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)

The official repo of paper "Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller"

Enhancing Large Vision Language Models with Self-Training on Image Comprehension.

Path-RAG: Knowledge-Guided Key Region Retrieval for Open-ended Pathology Visual Question Answering

The official Meta Llama 3 GitHub site

🤝 The code for "Can Large Language Model Agents Simulate Human Trust Behaviors?"

HLSyn benchmark for paper "Towards a Comprehensive Benchmark for FPGA Targeted High-Level Synthesis"

Official code for Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion (ICML 2024, Oral).

The official implementation of Self-Play Fine-Tuning (SPIN)

Reference implementation for DPO (Direct Preference Optimization)

SciGLM: Training Scientific Language Models with Self-Reflective Instruction Annotation and Tuning (NeurIPS D&B Track 2024)

HLSyn benchmark for paper "Towards a Comprehensive Benchmark for FPGA Targeted High-Level Synthesis"

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

This repository contains a LLM benchmark for the social deduction game `Resistance Avalon'

Learning to Group Auxiliary Datasets for Molecule, NeurIPS2023