MingyuJ666 / Rope_with_LLMLinks
[ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concentrated in low-frequency dimensions across different attention heads exclusively in attention queries (Q) and keys (K) while absent in values (V).
☆80Updated 4 months ago
Alternatives and similar repositories for Rope_with_LLM
Users that are interested in Rope_with_LLM are comparing it to the libraries listed below
Sorting:
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆87Updated 9 months ago
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆97Updated 8 months ago
- A Sober Look at Language Model Reasoning☆87Updated last month
- ☆181Updated 6 months ago
- 🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training☆88Updated 11 months ago
- ☆55Updated 4 months ago
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆188Updated 4 months ago
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆189Updated this week
- ☆67Updated 7 months ago
- [ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"☆83Updated 10 months ago
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!☆69Updated 7 months ago
- Code for "CREAM: Consistency Regularized Self-Rewarding Language Models", ICLR 2025.☆27Updated 8 months ago
- [NeurIPS 2025] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains☆59Updated 3 months ago
- ☆135Updated 2 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆46Updated last year
- The official repository of NeurIPS'25 paper "Ada-R1: From Long-Cot to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization"☆20Updated last week
- One-shot Entropy Minimization☆187Updated 5 months ago
- ☆131Updated 8 months ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆69Updated 4 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆258Updated 6 months ago
- Official PyTorch implementation of the paper "Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Princ…☆34Updated 3 months ago
- Official Repository of LatentSeek☆67Updated 5 months ago
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆61Updated 5 months ago
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models☆143Updated 4 months ago
- [TMLR 2025] Efficient Reasoning Models: A Survey☆276Updated 2 weeks ago
- ☆163Updated last month
- [NeurIPS 2025] The implementation of paper "On Reasoning Strength Planning in Large Reasoning Models"☆25Updated 4 months ago
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆135Updated 4 months ago
- ☆339Updated 3 months ago
- This is the repository of DEER, a Dynamic Early Exit in Reasoning method for Large Reasoning Language Models.☆176Updated 4 months ago