yafuly / TPOLinks
Test-time preferenece optimization (ICML 2025).
☆139Updated last month
Alternatives and similar repositories for TPO
Users that are interested in TPO are comparing it to the libraries listed below
Sorting:
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate"☆157Updated 2 weeks ago
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆113Updated 2 months ago
- ☆112Updated 3 weeks ago
- Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆75Updated 2 weeks ago
- ☆61Updated this week
- ☆202Updated 4 months ago
- [ACL'25] We propose a novel fine-tuning method, Separate Memory and Reasoning, which combines prompt tuning with LoRA.☆60Updated last month
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆220Updated last month
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆82Updated 4 months ago
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆54Updated 6 months ago
- Tool-Star: Empowering LLM-brained Multi-Tool Reasoner via Reinforcement Learning☆155Updated this week
- [ICML 2025] Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search☆99Updated 2 weeks ago
- Large Language Models Can Self-Improve in Long-context Reasoning☆70Updated 6 months ago
- A unified suite for generating elite reasoning problems and training high-performance LLMs, including pioneering attention-free architect…☆58Updated 3 weeks ago
- [NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct☆177Updated 5 months ago
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆124Updated 3 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆94Updated 3 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains☆141Updated last week
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆103Updated last month
- This is the official implementation of the paper "S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"☆65Updated 2 months ago
- ☆220Updated 3 weeks ago
- RL Scaling and Test-Time Scaling (ICML'25)☆105Updated 5 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆65Updated 2 weeks ago
- The official repository of the Omni-MATH benchmark.☆84Updated 6 months ago
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆72Updated 2 months ago
- OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning☆144Updated 5 months ago
- Repo of paper "Free Process Rewards without Process Labels"☆153Updated 3 months ago
- ☆231Updated last week
- [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆63Updated 7 months ago
- [NeurIPS 2024 D&B Track] GTA: A Benchmark for General Tool Agents☆96Updated 2 months ago