Pinned Loading
Repositories
Showing 10 of 17 repositories
- rank-then-act Public
Official implementation of the paper "Rank-Then-Act: Reward-Free Control from Frame-Order Progress"
- netherite-prime-agent Public
Letting an LLM play netherite (Minecraft 1.11.2 rewritten in C) through Prime Agent
-
- steering-reasoning Public
Official implementation of "Steering LLM Reasoning Through Bias-Only Adaptation" and "Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors"
- verl-loras Public Forked from thelongestusernameofall/verl
verl: Volcano Engine Reinforcement Learning for LLMs