Personal Page

codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)

An Elegant Academic Homepage Builder

Official code for paper "Revisiting Model Interpolation for Efficient Reasoning"

Evaluating Large Language Models for CUDA Code Generation ComputeEval is a framework designed to generate and evaluate CUDA code from Large Language Models.

SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks

A course of learning LLM inference serving on Apple Silicon for systems engineers.

KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems

HPCTransCompile: An AI Compiler Generated Dataset for High-Performance CUDA Transpilation and LLM Preliminary Exploration

Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"

Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)

verl: Volcano Engine Reinforcement Learning for LLMs

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

PaSa -- an advanced paper search agent powered by large language models. It can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant refe…

Fully open reproduction of DeepSeek-R1

[ICLR 2025] "Training LMs on Synthetic Edit Sequences Improves Code Synthesis" (Piterbarg, Pinto, Fergus)

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

🐋 An unofficial implementation of Self-Alignment with Instruction Backtranslation.