ArmenJeddi / saintLinks
a training-free approach to accelerate ViTs and VLMs by pruning redundant tokens based on similarity
☆36Updated 3 months ago
Alternatives and similar repositories for saint
Users that are interested in saint are comparing it to the libraries listed below
Sorting:
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆90Updated 2 months ago
- [CVPR 2025] PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models☆40Updated 2 months ago
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆157Updated 3 months ago
- [ICCV 2025] Official code for paper: Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs☆30Updated 2 months ago
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…☆41Updated 5 months ago
- ☆55Updated 4 months ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆34Updated 8 months ago
- [CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models☆45Updated 3 months ago
- 🚀 Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models☆33Updated last week
- [EMNLP 2025 main] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆72Updated 3 weeks ago
- ☆26Updated 6 months ago
- The official implementation for MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning (CVPR '24)☆65Updated 2 months ago
- CLIP-MoE: Mixture of Experts for CLIP☆46Updated 11 months ago
- [2025] Efficient Vision Language Models: A Survey☆28Updated 2 months ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆146Updated 2 months ago
- [NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.☆81Updated 8 months ago
- 📚 Collection of token-level model compression resources.☆162Updated 2 weeks ago
- Official repository of InLine attention (NeurIPS 2024)☆55Updated 8 months ago
- [ICLR 2025] Mixture Compressor for Mixture-of-Experts LLMs Gains More☆50Updated 7 months ago
- Adapting LLaMA Decoder to Vision Transformer☆30Updated last year
- [ICML'24 Oral] APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference☆45Updated last year
- VeriThinker: Learning to Verify Makes Reasoning Model Efficient☆52Updated 2 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆122Updated 6 months ago
- Code release for VTW (AAAI 2025 Oral)☆49Updated 2 months ago
- This repo contains the source code for VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks (NeurIPS 2024).☆40Updated 11 months ago
- [ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"☆59Updated 3 weeks ago
- [ICML 2024] CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers.☆34Updated 8 months ago
- [ICML 2025 Oral] Mixture of Lookup Experts☆51Updated 4 months ago
- [ICML2025] Official Code of From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection☆22Updated 2 months ago
- The official implementation of the paper "MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding". …☆58Updated 10 months ago