langfengQ

PhD @ NTU Singapore | My research focuses on reinforcement learning (RL), large language models (LLMs), LLM post-training, and LLM-based agents.

SingaporeNanyang Technological University

Github Data

Followers 28

Following 8

Links

https://x.com/langfengq https://langfengq.github.io/

AI Project

Public repos: 14Public gists: 0

CoSo

Source code for "Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning"

language: Python

created at: 2025-05-01

updated at: 2025-06-12

verl-agent

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

star: 409fork: 26

language: Python

created at: 2025-03-23

updated at: 2025-06-24