[EMNLP 2025] LightThinker: Thinking Step-by-Step Compression
☆135Apr 12, 2025Updated 11 months ago
Alternatives and similar repositories for LightThinker
Users that are interested in LightThinker are comparing it to the libraries listed below
Sorting:
- The official repository of NeurIPS'25 paper "Ada-R1: From Long-Cot to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization"☆22Nov 9, 2025Updated 4 months ago
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆206Nov 30, 2025Updated 3 months ago
- ☆46Sep 27, 2025Updated 5 months ago
- [NeurIPS 2025@FoRLM] R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search☆17Jan 24, 2026Updated last month
- Marketplace ML experiment - training without backprop☆27Sep 9, 2025Updated 6 months ago
- ☆20Jun 17, 2024Updated last year
- [TMLR 2025] Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models☆756Feb 28, 2026Updated 3 weeks ago
- ☆64Jan 12, 2026Updated 2 months ago
- Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models☆45Sep 19, 2025Updated 6 months ago
- Official code implementation for the ACL 2025 paper: 'CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis'☆33May 19, 2025Updated 10 months ago
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆98Feb 21, 2025Updated last year
- Code for Heima☆59Apr 21, 2025Updated 11 months ago
- ☆22Dec 11, 2024Updated last year
- ☆13May 23, 2021Updated 4 years ago
- [EMNLP 25] An effective and interpretable weight-editing method for mitigating overly short reasoning in LLMs, and a mechanistic study un…☆17Dec 17, 2025Updated 3 months ago
- Aligning Agentic World Models via Knowledgeable Experience Learning☆32Jan 25, 2026Updated last month
- ☆27Jul 18, 2025Updated 8 months ago
- [WSDM 2026] LookAhead Tuning: Safer Language Models via Partial Answer Previews☆17Dec 14, 2025Updated 3 months ago
- Implementation of AdaCQR(COLING 2025)☆13Dec 30, 2024Updated last year
- Source code and dataset for paper "End-to-End Transition-Based Online Dialogue Disentanglement"☆17May 17, 2021Updated 4 years ago
- Training Large Language Model to Reason in a Continuous Latent Space☆1,536Aug 12, 2025Updated 7 months ago
- ☆146Sep 12, 2025Updated 6 months ago
- (ACL 2025 Main) Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification - Offici…☆20Dec 26, 2025Updated 2 months ago
- ☆33Oct 13, 2025Updated 5 months ago
- An Ultra-Long Output Reinforcement Learning Approach☆23Jul 31, 2025Updated 7 months ago
- ☆20May 14, 2025Updated 10 months ago
- Official Implementation of the paper "Jointly Reinforcing Diversity and Quality in Language Model Generations"☆57Dec 26, 2025Updated 2 months ago
- Vision-Language based Visual Object Tracking☆28Oct 10, 2025Updated 5 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆262May 14, 2025Updated 10 months ago
- This project implements a Reinforcement Learning (RL) enhanced Retrieval-Augmented Generation (RAG) system that optimizes document retrie…☆23Apr 27, 2025Updated 10 months ago
- [NeurIPS 2025] The implementation of paper "On Reasoning Strength Planning in Large Reasoning Models"☆31Jul 6, 2025Updated 8 months ago
- ☆21Mar 5, 2026Updated 2 weeks ago
- ☆27Nov 25, 2025Updated 3 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆92Feb 14, 2025Updated last year
- Reflect-RL: Two-Player Online RL Fine-Tuning for LMs☆18Jul 19, 2025Updated 8 months ago
- ☆47Nov 25, 2024Updated last year
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆264May 5, 2025Updated 10 months ago
- (ACL 2025 oral) SCOPE: Optimizing KV Cache Compression in Long-context Generation☆34May 28, 2025Updated 9 months ago
- The official repository of paper "Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models''☆112Aug 15, 2025Updated 7 months ago