Bo Liu's picture

6 8 1

Bo Liu

Benjamin-eecs

·

https://benjamin-eecs.github.io/

AI & ML interests

Reinforcement Learning, Reasoning, Machine Learning Systems

Recent Activity

authored a paper 2 days ago

SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning

updated a dataset 2 days ago

spiral-rl/Spiral-Kuhn-Poker-Qwen3-32B-SFT

updated a model 2 days ago

spiral-rl/Spiral-Qwen3-4B

View all activity

Organizations

Benjamin-eecs 's models 2

Benjamin-eecs/Llama-3.1-8B-Instruct-NLRL-TicTacToe-Policy

Feature Extraction • 8B • Updated Nov 24, 2024 • 12

Benjamin-eecs/Llama-3.1-8B-Instruct-NLRL-TicTacToe-Value

Feature Extraction • 8B • Updated Nov 24, 2024 • 22