Joshua-Ren / Learning_dynamics_LLMLinks
☆138Updated last month
Alternatives and similar repositories for Learning_dynamics_LLM
Users that are interested in Learning_dynamics_LLM are comparing it to the libraries listed below
Sorting:
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆73Updated 4 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆191Updated this week
- [ICLR 2025 Workshop] "Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models"☆25Updated this week
- ☆222Updated this week
- A Sober Look at Language Model Reasoning☆74Updated last week
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆124Updated 3 months ago
- AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models, ICLR 2025 (Outstanding Paper)☆265Updated last week
- ☆65Updated 2 months ago
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆88Updated 8 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆41Updated 11 months ago
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!☆54Updated 2 months ago
- ☆190Updated 2 months ago
- ☆46Updated 2 months ago
- ☆203Updated 4 months ago
- [ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"☆64Updated 6 months ago
- ☆64Updated 3 weeks ago
- ☆107Updated 3 months ago
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆28Updated 3 weeks ago
- ☆46Updated 2 weeks ago
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆73Updated this week
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆120Updated this week
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆222Updated last month
- [NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct☆177Updated 5 months ago
- ☆292Updated last week
- A comprehensive collection of process reward models.☆92Updated 2 weeks ago
- Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆75Updated 2 weeks ago
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆156Updated 3 months ago
- Repo of paper "Free Process Rewards without Process Labels"☆153Updated 3 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆65Updated 3 weeks ago
- 😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond☆252Updated 2 weeks ago