sail-sg / LightTransLinks
The official implementation of "LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation"
☆22Updated 8 months ago
Alternatives and similar repositories for LightTrans
Users that are interested in LightTrans are comparing it to the libraries listed below
Sorting:
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆88Updated 10 months ago
- A Sober Look at Language Model Reasoning☆92Updated last month
- ☆19Updated 8 months ago
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆85Updated 6 months ago
- ☆60Updated 5 months ago
- ☆143Updated 3 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆46Updated last year
- ☆46Updated 3 months ago
- [COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆50Updated 9 months ago
- Official code for Guiding Language Model Math Reasoning with Planning Tokens☆18Updated last year
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆96Updated 10 months ago
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆197Updated last month
- ☆71Updated 8 months ago
- The official github repo for "Training Optimal Large Diffusion Language Models", the first-ever large-scale diffusion language models sca…☆46Updated 2 months ago
- [NeurIPS 2025] The implementation of paper "On Reasoning Strength Planning in Large Reasoning Models"☆28Updated 6 months ago
- Code for "The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs"☆73Updated 3 months ago
- Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆62Updated 7 months ago
- The loss landscape of Large Language Models resemble basin!☆35Updated 6 months ago
- dParallel: Learnable Parallel Decoding for dLLMs☆53Updated 2 months ago
- ☆23Updated last year
- [AAAI'26 Oral] Official Implementation of STAR-1: Safer Alignment of Reasoning LLMs with 1K Data☆33Updated 9 months ago
- 🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training☆91Updated last year
- V1: Toward Multimodal Reasoning by Designing Auxiliary Task☆36Updated 8 months ago
- Official repository for paper "DeepCritic: Deliberate Critique with Large Language Models"☆40Updated 6 months ago
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆151Updated 6 months ago
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆74Updated 7 months ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆69Updated 5 months ago
- [ICML 2025] Official implementation of the paper "SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling". …☆17Updated last month
- [AI4MATH@ICML2025] Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs☆41Updated 7 months ago
- [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…☆103Updated last year