dvlab-research / Step-DPOLinks
Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"
☆376Updated 7 months ago
Alternatives and similar repositories for Step-DPO
Users that are interested in Step-DPO are comparing it to the libraries listed below
Sorting:
- The related works and background techniques about Openai o1☆224Updated 7 months ago
- This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.☆320Updated last year
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆282Updated last month
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆660Updated 7 months ago
- ☆339Updated 2 months ago
- Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models☆267Updated 11 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆296Updated last month
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆476Updated 10 months ago
- Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"☆133Updated last month
- LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment☆362Updated last year
- A series of technical report on Slow Thinking with LLM☆722Updated last week
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆248Updated 3 months ago
- A comprehensive collection of process reward models.☆104Updated last month
- ☆271Updated 3 months ago
- ☆312Updated 2 months ago
- ☆261Updated last month
- Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains…☆244Updated last week
- ☆206Updated 6 months ago
- A version of verl to support tool use☆333Updated last week
- ☆546Updated 7 months ago
- Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.☆147Updated last month
- [TMLR 2025] Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models☆574Updated this week
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆244Updated 4 months ago
- ☆317Updated 2 months ago
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆128Updated 4 months ago
- ☆48Updated 3 months ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆241Updated last year
- ☆204Updated 4 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆188Updated 5 months ago
- 😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and Beyond☆286Updated last week