[EMNLP 2025] LightThinker: Thinking Step-by-Step Compression
☆166Jun 22, 2026Updated 4 months 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:
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆231Nov 30, 2025Updated 11 months ago
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆96May 30, 2025Updated last year
- [ICML 2026] Heima☆78May 20, 2026Updated 5 months ago
- ☆29Aug 8, 2025Updated last year
- Official repository for "CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation"☆112Dec 15, 2025Updated 11 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 11 months ago
- [EMNLP 2026] Aligning Agentic World Models via Knowledgeable Experience Learning☆46May 15, 2026Updated 6 months ago
- [ACL 2026] KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality☆47May 19, 2026Updated 6 months ago
- [ACL 2025] Knowledge Unlearning for Large Language Models☆49Sep 18, 2025Updated last year
- Code for paper: Optimizing Length Compression in Large Reasoning Models☆29Oct 20, 2025Updated last year
- ☆47Sep 27, 2025Updated last year
- Official github repo for "Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute"☆18Jun 30, 2025Updated last year
- The official repository of NeurIPS'25 paper "Ada-R1: From Long-Cot to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization"☆25May 6, 2026Updated 6 months ago
- Official implementation of Latent-SFT: teaching LLMs to reason with vocabulary-space latent chains.☆62Aug 31, 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.
- Official Repository of LatentSeek☆88Jun 6, 2025Updated last year
- [ICLR/AAAI/KDD/EMNLP2026] Open-Source LLM-Based Data Analysis Agents☆154Sep 29, 2026Updated last month
- ☆20Mar 18, 2026Updated 8 months ago
- [TMLR 2025] Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models☆795Oct 20, 2026Updated 3 weeks ago
- Official implementation of the NeurIPS 2025 paper "Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space"☆356Jun 12, 2026Updated 5 months ago
- RL with Experience Replay☆59Oct 13, 2026Updated last month
- Sys2Bench is a benchmarking suite designed to evaluate reasoning and planning capabilities of large language models across algorithmic, l…☆30Mar 5, 2025Updated last year
- code for paper Accurate KV Cache Quantization with Outlier Tokens Tracing (ACL2025 Main)☆11Jul 4, 2025Updated last year
- [ACL 2026 Main] Official Repo for Paper "Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Ali…☆17Jul 1, 2026Updated 4 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆65Mar 30, 2026Updated 7 months ago
- [NeurIPS 2025] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains☆98Jun 29, 2026Updated 4 months ago
- Code for "Retaining Key Information under High Compression Rates: Query-Guided Compressor for LLMs" (ACL 2024)☆19Jun 12, 2024Updated 2 years ago
- ☆48Nov 1, 2025Updated last year
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆100Feb 21, 2025Updated last year
- ☆20Jun 17, 2024Updated 2 years ago
- REverse-Engineered Reasoning for Open-Ended Generation☆98Sep 10, 2025Updated last year
- [NeurIPS 2024] Agent Planning with World Knowledge Model☆168Dec 17, 2024Updated last year
- ☆10Jan 25, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Training Large Language Model to Reason in a Continuous Latent Space☆1,752Jul 2, 2026Updated 4 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆91Feb 14, 2025Updated last year
- ☆189Dec 5, 2025Updated 11 months ago
- [arXiv 2026] Learning from Rare Success and Rich Feedback via Reflection-Enhanced Self-Distillation☆20May 21, 2026Updated 5 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆265May 14, 2025Updated last year
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆146Dec 17, 2025Updated 11 months ago
- BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection☆19Mar 30, 2026Updated 7 months ago
Are these results useful?