xufangzhi / phi-DecodingLinks
[ACL 2025] An inference-time decoding strategy with adaptive foresight sampling
☆105Updated 5 months ago
Alternatives and similar repositories for phi-Decoding
Users that are interested in phi-Decoding are comparing it to the libraries listed below
Sorting:
- [ACL 2025] Are Your LLMs Capable of Stable Reasoning?☆30Updated 2 months ago
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆114Updated 5 months ago
- B-STAR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners☆85Updated 5 months ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆177Updated 3 months ago
- ☆90Updated 11 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆111Updated 9 months ago
- [NeurIPS 2024] OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI☆105Updated 7 months ago
- ☆73Updated 7 months ago
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆82Updated 7 months ago
- ☆63Updated 4 months ago
- ☆85Updated 9 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆185Updated 4 months ago
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆75Updated 5 months ago
- ☆69Updated last year
- [EMNLP'2025 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"☆65Updated 6 months ago
- [NeurIPS 2025 Spotlight] ReasonFlux-Coder: Open-Source LLM Coders with Co-Evolving Reinforcement Learning☆126Updated last month
- SIFT: Grounding LLM Reasoning in Contexts via Stickers☆58Updated 7 months ago
- [ICLR'25] Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"☆78Updated 11 months ago
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆178Updated 3 months ago
- HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models☆52Updated 10 months ago
- ☆50Updated 8 months ago
- Process Reward Models That Think☆59Updated last week
- ☆99Updated 5 months ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks (EMNLP'24)☆147Updated last year
- [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression☆112Updated 6 months ago
- Co-LLM: Learning to Decode Collaboratively with Multiple Language Models☆122Updated last year
- Interpretable Contrastive Monte Carlo Tree Search Reasoning☆48Updated 11 months ago
- The official repository of the Omni-MATH benchmark.☆88Updated 10 months ago
- Reformatted Alignment☆112Updated last year
- Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization☆76Updated 3 weeks ago