Shuyao "Tim" Xu

@Tim-Siu · User

GitHub profile ↗ · Compare

@ NUS

National University of SingaporeSingapore36 followers40 repositories

Repositories

Tim-Siu/reft-exp

A research repo for experiments about Reinforcement Finetuning

★ 56PythonForks 2

Tim-Siu/G-OPD

Official repository for the paper "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation"

★ 0Forks 0

Tim-Siu/harbor

Harbor is a framework for running agent evaluations and creating and using RL environments.

★ 0Forks 0

Tim-Siu/nanochat

The assignment from a frontier LLM lab. Let's do something to nanochat!

★ 0PythonForks 0

Tim-Siu/verl

verl: Volcano Engine Reinforcement Learning for LLMs

★ 0PythonForks 0

Tim-Siu/mini-swe-agent

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!

★ 0PythonForks 0

Tim-Siu/slime

slime is an LLM post-training framework for RL Scaling.

★ 0PythonForks 0

Tim-Siu/lighteval

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

★ 0Forks 0

Tim-Siu/trl

Train transformer language models with reinforcement learning.

★ 0PythonForks 0

Tim-Siu/markbind

MarkBind is a tool for generating content-heavy websites from source files in Markdown format

★ 0HTMLForks 0

Tim-Siu/teammates

This is the project website for the TEAMMATES feedback management tool for education

★ 0JavaForks 0