PinnedLoading

1. compute-optimal-ttscompute-optimal-ttsPublic

   Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".

   Python 267 21

2. GenPRMGenPRMPublic

   Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".

   Python 79 2

3. Awesome-Process-Reward-ModelsAwesome-Process-Reward-ModelsPublic

   A comprehensive collection of process reward models.

   95 1

4. wizard-III/ArcherCodeRwizard-III/ArcherCodeRPublic

   ArcherCodeR is an open-source initiative enhancing code reasoning in large language models through scalable, rule-governed reinforcement learning.

   Python 5

5. MRNMRNPublic

   [NeurIPS 2022] Official codebase for "Meta-Reward-Net: Implicitly Differentiable Reward Learning for Preference-based Reinforcement Learning".

   Python 23 5

6. ChangWinde/RATChangWinde/RATPublic

   [AAAI 2025 Oral] Official code for "RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors"

   Python 14