AIoT-MLSys-Lab / MEDALinks
[NAACL 2025🔥] MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference
☆14Updated 5 months ago
Alternatives and similar repositories for MEDA
Users that are interested in MEDA are comparing it to the libraries listed below
Sorting:
- Code release for VTW (AAAI 2025 Oral)☆61Updated 2 weeks ago
- [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Cont…☆62Updated 2 months ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆36Updated 10 months ago
- [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…☆104Updated last year
- ☆60Updated 6 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆97Updated 4 months ago
- ☆28Updated 5 months ago
- [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆90Updated last month
- Code for paper: Unraveling the Shift of Visual Information Flow in MLLMs: From Phased Interaction to Efficient Inference☆13Updated 5 months ago
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆75Updated 3 weeks ago
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆194Updated 5 months ago
- ☆51Updated last week
- [NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.☆67Updated 2 months ago
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆87Updated last month
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆154Updated last month
- Cross-Self KV Cache Pruning for Efficient Vision-Language Inference☆10Updated 11 months ago
- [ICML 2025] Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in…☆168Updated last month
- [AAAI 2026] Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models☆34Updated 2 weeks ago
- ✨✨[AAAI 2026] This is the official implementation of our paper "QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Vi…☆73Updated 6 months ago
- ☆109Updated 2 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆134Updated 8 months ago
- PyTorch Implementation of "Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Larg…☆31Updated 6 months ago
- The official implement of "Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings"☆13Updated 11 months ago
- A Self-Training Framework for Vision-Language Reasoning☆86Updated 10 months ago
- The official repository for the paper "ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning"☆96Updated this week
- [NeurIPS 2025] MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning☆87Updated 2 months ago
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…☆42Updated 7 months ago
- [EMNLP 2025 Main] Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models☆38Updated last week
- [NeurIPS 2025] NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation☆97Updated 2 months ago
- Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"☆96Updated 2 months ago