orailix / PACTLinks
[CVPR 2025] PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models
☆43Updated 2 months ago
Alternatives and similar repositories for PACT
Users that are interested in PACT 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
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆157Updated 3 months ago
- [ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models☆48Updated 7 months ago
- MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer☆46Updated last year
- [NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.☆53Updated this week
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆122Updated 6 months ago
- [ICLR 2025] LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation☆196Updated 5 months ago
- ☆55Updated 4 months ago
- [EMNLP 2025 main] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆72Updated 3 weeks ago
- [CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models☆45Updated 3 months ago
- Code release for VTW (AAAI 2025 Oral)☆49Updated 2 months ago
- [ICCV 2025] Official implementation of LLaVA-KD: A Framework of Distilling Multimodal Large Language Models☆96Updated 2 months ago
- ☆120Updated 6 months ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆146Updated 2 months ago
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models