Colin
Co1lin
PhD student @Columbia.
Languages
Repos
82
Stars
83
Forks
12
Top Language
Python
Loading contributions...
Top Repositories
Simultaneous evaluation on both functionality and security of LLM-generated code.
Server Usage Documentation of AIR
A script for JS practice purpose.
The classic Chinese card game Landlords. An assignment for Qt network programming, in summer term 2020.
useful docker images
Repositories
82Simultaneous evaluation on both functionality and security of LLM-generated code.
Server Usage Documentation of AIR
No description provided.
TDD-Bench-Verified is a new benchmark for generating test cases for test-driven development (TDD)
A clean, modular SDK for building AI agents with OpenHands V1.
Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.
Evaluation harness for OpenHands V1.
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
No description provided.
useful docker images
Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.
No description provided.
For our ACL25 Paper: Can Language Models Replace Programmers? RepoCod Says ‘Not Yet’ - by Shanchao Liang and Yiran Hu and Nan Jiang and Lin Tan
Android App of iLearn (I learn, or intelligent learning), project for Java Program Design and Training course, 2021 Summer at THU.
A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 30.67% tasks (pass@1) in SWE-bench lite with each task costs less than $0.7.
Go ahead and axolotl questions
An elegant \LaTeX\ résumé template. 大陆镜像 https://gods.coding.net/p/resume/git
EvalPlus for rigourous evaluation of LLM-synthesized code
The classic Chinese card game Landlords. An assignment for Qt network programming, in summer term 2020.
The fundamental package for scientific computing with Python.
A yellow page for Tsinghua/THU service/info/utils
Never use print for debugging again
The artifact for Quarl.
将Typora伪装成LaTeX的中文样式主题，本科生轻量级课程论文撰写的好帮手。This is a theme disguising Typora into Chinese LaTeX style.
Personal practice of HPC course, 2022 Spring @ THU.
No description provided.
A script for JS practice purpose.
The MiniDecaf test cases.
No description provided.
rCore Lab for 2021 Autumn