[ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference" and "SparseVLM+: Visual Token Sparsification with Improved Text-Visual Attention Pattern"
☆241Dec 22, 2025Updated 2 months ago
Alternatives and similar repositories for SparseVLMs
Users that are interested in SparseVLMs are comparing it to the libraries listed below
Sorting:
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆141Mar 6, 2025Updated 11 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆106Jun 29, 2025Updated 8 months ago
- A paper list of some recent works about Token Compress for Vit and VLM☆835Updated this week
- [ECCV 2024 Oral] Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Langua…☆553Jan 4, 2025Updated last year
- [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"☆55Oct 9, 2025Updated 4 months ago
- [NeurIPS'24] Official implementation of paper "Unveiling the Tapestry of Consistency in Large Vision-Language Models".☆38Oct 23, 2024Updated last year
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…☆44Apr 18, 2025Updated 10 months ago
- Official repository for VisionZip (CVPR 2025)☆407Jul 21, 2025Updated 7 months ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆37Jan 8, 2025Updated last year
- [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆106Oct 12, 2025Updated 4 months ago
- Code release for VTW (AAAI 2025 Oral)☆64Nov 4, 2025Updated 3 months ago
- [NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.☆87Sep 20, 2025Updated 5 months ago
- [ICCV 2025] Official code for paper: Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs☆68Jul 1, 2025Updated 7 months ago
- ☆66Jan 23, 2026Updated last month
- [CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".☆203Jun 18, 2025Updated 8 months ago
- [ACL 2025] PruneVid: Visual Token Pruning for Efficient Video Large Language Models☆67May 15, 2025Updated 9 months ago
- [CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models☆65Dec 1, 2025Updated 2 months ago
- [AAAI 2026] Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models☆38Jan 27, 2026Updated last month
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆164Sep 27, 2025Updated 5 months ago
- [NeurIPS 2025] Official repository for “FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models”☆28Dec 9, 2025Updated 2 months ago
- [CVPR 2025] Official implementation of paper "MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders".☆48Jun 7, 2025Updated 8 months ago
- iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models☆21Jan 29, 2025Updated last year
- [ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"☆69Jan 13, 2026Updated last month
- [ICLR2025] γ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Models☆42Oct 28, 2025Updated 4 months ago
- [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…☆104Nov 9, 2024Updated last year
- [ICCV 2025] SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs☆82Jan 17, 2026Updated last month
- MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer☆50Sep 6, 2024Updated last year
- [CVPR'24] Official implementation of paper "FreeKD: Knowledge Distillation via Semantic Frequency Prompt".☆50Apr 20, 2024Updated last year
- [ICCV 2025] p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay☆43Jun 26, 2025Updated 8 months ago
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆101Nov 22, 2025Updated 3 months ago
- [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Cont…☆70Sep 18, 2025Updated 5 months ago
- [CVPR 2025] PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models☆51Jun 12, 2025Updated 8 months ago
- [CVPR 2025] PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models☆56Jan 30, 2026Updated last month
- The code for "TokenPacker: Efficient Visual Projector for Multimodal LLM", IJCV2025☆277May 26, 2025Updated 9 months ago
- ☆29Feb 27, 2025Updated last year
- [ACM MM 2025] TimeChat-online: 80% Visual Tokens are Naturally Redundant in Streaming Videos☆115Dec 12, 2025Updated 2 months ago
- Code for paper: Unraveling the Shift of Visual Information Flow in MLLMs: From Phased Interaction to Efficient Inference☆13Jun 7, 2025Updated 8 months ago
- ☆14Apr 25, 2025Updated 10 months ago
- Official implementation of paper ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding☆39Mar 16, 2025Updated 11 months ago