[EMNLP 2025] LightThinker: Thinking Step-by-Step Compression
☆165Jun 22, 2026Updated 3 weeks ago
Alternatives and similar repositories for LightThinker
Users that are interested in LightThinker are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆27Aug 8, 2025Updated 11 months ago
- [ICML 2026] Heima☆75May 20, 2026Updated 2 months ago
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆92May 30, 2025Updated last year
- Aligning Agentic World Models via Knowledgeable Experience Learning☆37May 15, 2026Updated 2 months ago
- Official repository for "CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation"☆102Dec 15, 2025Updated 7 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [WSDM 2026] LookAhead Tuning: Safer Language Models via Partial Answer Previews☆17Dec 14, 2025Updated 7 months ago
- KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality☆48May 19, 2026Updated 2 months ago
- The official repository of NeurIPS'25 paper "Ada-R1: From Long-Cot to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization"☆24May 6, 2026Updated 2 months ago
- ☆151Sep 12, 2025Updated 10 months ago
- [ICLR/AAAI/KDD2026] Open-Source LLM-Based Data Analysis Agents☆121Jul 10, 2026Updated last week
- Official github repo for "Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute"☆17Jun 30, 2025Updated last year
- ☆46Sep 27, 2025Updated 9 months ago
- Code for paper: Optimizing Length Compression in Large Reasoning Models☆29Oct 20, 2025Updated 9 months ago
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆224Nov 30, 2025Updated 7 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Official implementation of Latent-SFT: teaching LLMs to reason with vocabulary-space latent chains.☆55May 18, 2026Updated 2 months ago
- Official Repository of LatentSeek☆85Jun 6, 2025Updated last year
- Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"☆344Jun 12, 2026Updated last month
- [TMLR 2025] Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models☆782Feb 28, 2026Updated 4 months ago
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆99Feb 21, 2025Updated last year
- ☆20Mar 18, 2026Updated 4 months ago
- [ACL 2026 Main] Official Repo for Paper "Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Ali…☆17Jul 1, 2026Updated 2 weeks ago
- ☆65Mar 30, 2026Updated 3 months ago
- [NeurIPS 2025] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains☆97Jun 29, 2026Updated 3 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆47Nov 1, 2025Updated 8 months ago
- REverse-Engineered Reasoning for Open-Ended Generation☆98Sep 10, 2025Updated 10 months ago
- ☆186Dec 5, 2025Updated 7 months ago
- Paper list for Efficient Reasoning.☆901May 29, 2026Updated last month
- RL with Experience Replay☆59Jul 27, 2025Updated 11 months ago
- [ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation☆1,022Updated this week
- Official code repository for Sketch-of-Thought (SoT)☆138May 8, 2025Updated last year
- Code for "Retaining Key Information under High Compression Rates: Query-Guided Compressor for LLMs" (ACL 2024)☆20Jun 12, 2024Updated 2 years ago
- ☆72May 8, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Parallel Continuous Chain-of-Thought with Jacobi Iteration. Accepted to EMNLP 2025.☆23Mar 29, 2026Updated 3 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆103Oct 15, 2025Updated 9 months ago
- [WWW 2026 Oral] MoE-CL:Self-Evolving LLMs via Continual Instruction Tuning☆21Dec 1, 2025Updated 7 months ago
- Official code for Guiding Language Model Math Reasoning with Planning Tokens☆19Feb 29, 2024Updated 2 years ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆263May 14, 2025Updated last year
- Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models☆55Sep 19, 2025Updated 10 months ago
- ☆21May 22, 2026Updated last month