[EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs
☆202Nov 30, 2025Updated 3 months ago
Alternatives and similar repositories for TokenSkip
Users that are interested in TokenSkip are comparing it to the libraries listed below
Sorting:
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆92Feb 14, 2025Updated last year
- Paper list for Efficient Reasoning.☆828Updated this week
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆62Feb 21, 2025Updated last year
- Codes for Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback (ACL 2024 Findings)☆16Jul 2, 2024Updated last year
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆287Feb 21, 2026Updated last week
- The official repository of NeurIPS'25 paper "Ada-R1: From Long-Cot to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization"☆21Nov 9, 2025Updated 3 months ago
- Official Implementation for the paper "Integrative Decoding: Improving Factuality via Implicit Self-consistency"☆32Apr 12, 2025Updated 10 months ago
- [ICLR 2025] Language Imbalance Driven Rewarding for Multilingual Self-improving☆24Aug 25, 2025Updated 6 months ago
- ☆74Apr 13, 2025Updated 10 months ago
- PyTorch implementation of experiments in the paper Aligning Language Models with Human Preferences via a Bayesian Approach☆32Nov 6, 2023Updated 2 years ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆100Oct 15, 2025Updated 4 months ago
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!☆72Apr 1, 2025Updated 11 months ago
- Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue (ACL 2024)☆25Oct 18, 2025Updated 4 months ago
- Code for the paper "Self-Detoxifying Language Models via Toxification Reversal" (EMNLP 2023)☆18Oct 17, 2023Updated 2 years ago
- Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains…☆258Aug 13, 2025Updated 6 months ago
- [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression☆133Apr 12, 2025Updated 10 months ago
- ☆145Sep 12, 2025Updated 5 months ago
- Codes for our paper "Enhancing Continual Relation Extraction via Classifier Decomposition" (Findings of ACL2023)☆10Nov 29, 2023Updated 2 years ago
- Target-constrained Bidirectional Planning for Generation of Target-oriented Proactive Dialogue (TOIS)☆13Oct 18, 2025Updated 4 months ago
- Code and data for "Medical Dialogue Generation via Dual Flow Modeling" (ACL 2023 Findings)☆13Nov 22, 2023Updated 2 years ago
- PyTorch implementation of CARE☆16Oct 6, 2023Updated 2 years ago
- ☆48Nov 25, 2024Updated last year
- Dialogue Planning via Brownian Bridge Stochastic Process for Goal-directed Proactive Dialogue (ACL Findings 2023)☆21Nov 10, 2025Updated 3 months ago
- ☆33Nov 18, 2025Updated 3 months ago
- Official code for paper "SPA-RL: Reinforcing LLM Agent via Stepwise Progress Attribution"☆67Sep 13, 2025Updated 5 months ago
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆97Feb 21, 2025Updated last year
- [TMLR 2025] Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models☆743Updated this week
- This repository provides the data and the codes used in the AAAI'24 paper, COOPER: Coordinating Specialized Agents towards a Complex Dial…☆27Mar 1, 2024Updated 2 years ago
- (ACL2025 Findings) Official code for the paper "STeCa: Step-level Trajectory Calibration for LLM Agent Learning"☆25Feb 12, 2026Updated 2 weeks ago
- Code for the paper "RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoning" (EMNLP'23 Findings).☆28Jun 12, 2025Updated 8 months ago
- ☆22Oct 22, 2024Updated last year
- Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation (EMNLP 2023)☆31Oct 18, 2025Updated 4 months ago
- (ICLR 2025 Spotlight) DEEM: Official implementation of Diffusion models serve as the eyes of large language models for image perception.☆48Jul 1, 2025Updated 8 months ago
- ☆20Nov 3, 2024Updated last year
- [ACL 2025 Findings] Official implementation of the paper "Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning".☆20Feb 26, 2025Updated last year
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆262May 14, 2025Updated 9 months ago
- LongAttn ：Selecting Long-context Training Data via Token-level Attention☆15Jul 16, 2025Updated 7 months ago
- AI model designed to test the effectiveness in handling external ethical attacks.☆11Feb 9, 2026Updated 2 weeks ago
- ☆19Mar 10, 2025Updated 11 months ago