Pinned Loading

1. Code for NeurIPS 2021 paper "ReAct: Out-of-distribution Detection With Rectified Activations"

   Python 57 10

2. Code for ICML 2022 paper "Out-of-distribution Detection with Deep Nearest Neighbors"

   Python 200 18

5. A curated list of resources on Reinforcement Learning with Verifiable Rewards (RLVR) and the reasoning capability boundary of Large Language Models (LLMs).

   87 6

6. Code repository for "RL Grokking Recipe: How RL Unlocks and Transfers New Algorithms in LLMs""

   Python 33 1