GATECH-EIC / ACTLinks
[ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration
☆40Updated last year
Alternatives and similar repositories for ACT
Users that are interested in ACT are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆96Updated last week
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆76Updated 5 months ago
- Github repository for "Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging" (ICML 2025)☆63Updated last month
- [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…☆97Updated 8 months ago
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆76Updated last year
- NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation☆78Updated last month
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆76Updated 8 months ago
- ☆147Updated last month
- ☆90Updated 2 months ago
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆68Updated last year
- This repo contains evaluation code for the paper "MileBench: Benchmarking MLLMs in Long Context"☆35Updated last year
- ☆46Updated 3 months ago
- ☆15Updated 2 months ago
- Code for Heima☆49Updated 2 months ago
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models☆116Updated this week
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆59Updated 4 months ago
- 🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training☆86Updated 7 months ago
- CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for task-aware parameter-efficient fine-tuning(NeurIPS 2024)☆46Updated 6 months ago
- Recent Advances on MLLM's Reasoning Ability☆24Updated 3 months ago
- ☆113Updated 4 months ago
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆31Updated last month
- Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."☆42Updated 8 months ago
- [Arxiv Paper 2504.09130]: VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search☆20Updated 2 months ago
- Code release for VTW (AAAI 2025) Oral☆44Updated 5 months ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆61Updated 6 months ago
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆74Updated 3 weeks ago
- ☆30Updated last year
- V1: Toward Multimodal Reasoning by Designing Auxiliary Task☆34Updated 3 months ago
- code for "Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization"☆55Updated 10 months ago
- [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Cont…☆46Updated 7 months ago