THUDM / T1
Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
☆101Updated 2 months ago
Alternatives and similar repositories for T1:
Users that are interested in T1 are comparing it to the libraries listed below
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate"☆135Updated 2 months ago
- Interpretable Contrastive Monte Carlo Tree Search Reasoning☆48Updated 5 months ago
- Code for Paper: Teaching Language Models to Critique via Reinforcement Learning☆90Updated this week
- Repo of paper "Free Process Rewards without Process Labels"☆140Updated last month
- ☆105Updated 2 months ago
- ☆99Updated 2 weeks ago
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆112Updated 3 weeks ago
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆120Updated 7 months ago
- The official repository of the Omni-MATH benchmark.☆80Updated 3 months ago
- ☆148Updated 4 months ago
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆101Updated 4 months ago
- official implementation of paper "Process Reward Model with Q-value Rankings"☆52Updated 2 months ago
- ☆151Updated 3 weeks ago
- "Improving Mathematical Reasoning with Process Supervision" by OPENAI☆108Updated last week
- Critique-out-Loud Reward Models☆57Updated 5 months ago
- Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]☆131Updated 6 months ago
- ☆78Updated this week
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆90Updated last month
- Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"☆74Updated 10 months ago
- Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (EMNLP 2024 Main Conference)☆57Updated 5 months ago
- [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy☆60Updated 4 months ago
- We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆61Updated 5 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆174Updated last month
- Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"☆30Updated 10 months ago
- Code implementation of synthetic continued pretraining☆99Updated 3 months ago
- [EMNLP 2024] Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".☆74Updated 3 months ago
- Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering☆57Updated 4 months ago
- Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied wit…☆122Updated 9 months ago
- Unofficial Implementation of Chain-of-Thought Reasoning Without Prompting☆32Updated last year
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆180Updated 3 weeks ago