Hongcheng-Gao / Awesome-Long2short-on-LRMsLinks
Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains papers, codes, datasets, evaluations, and analyses.
โ241Updated 2 months ago
Alternatives and similar repositories for Awesome-Long2short-on-LRMs
Users that are interested in Awesome-Long2short-on-LRMs are comparing it to the libraries listed below
Sorting:
- ๐ A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyondโ277Updated last month
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!โ68Updated 4 months ago
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.โ142Updated 2 weeks ago
- Paper list for Efficient Reasoning.โ573Updated last week
- โ252Updated last month
- โ52Updated 2 months ago
- Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelsโ547Updated this week
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.โ275Updated 3 weeks ago
- TokenSkip: Controllable Chain-of-Thought Compression in LLMsโ171Updated last month
- โ65Updated 3 months ago
- Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"โ132Updated 3 weeks ago
- Model merging is a highly efficient approach for long-to-short reasoning.โ76Updated 2 months ago
- This is the repository of DEER, a Dynamic Early Exit in Reasoning method for Large Reasoning Language Models.โ161Updated last month
- The related works and background techniques about Openai o1โ224Updated 7 months ago
- โ102Updated 2 months ago
- [ICLR 2025] Language Imbalance Driven Rewarding for Multilingual Self-improvingโ20Updated this week
- A comprehensive collection of process reward models.โ96Updated 2 weeks ago
- A series of technical report on Slow Thinking with LLMโ713Updated last month
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuningโ474Updated 9 months ago
- โ258Updated 2 months ago
- โ151Updated 10 months ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. ๐งฎโจโ239Updated last year
- A Framework for LLM-based Multi-Agent Reinforced Training and Inferenceโ179Updated last month
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learningโ234Updated 2 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"โ268Updated 3 weeks ago
- Latest Advances on Long Chain-of-Thought Reasoningโ459Updated 2 weeks ago
- A versatile toolkit for applying Logit Lens to modern large language models (LLMs). Currently supports Llama-3.1-8B and Qwen-2.5-7B, enabโฆโ95Updated 5 months ago
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".โ56Updated 8 months ago
- [ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"โ71Updated 7 months ago
- Repository for Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learningโ165Updated last year