ChangyuanWang17 / QVLMLinks
[NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.
☆89Updated 10 months ago
Alternatives and similar repositories for QVLM
Users that are interested in QVLM are comparing it to the libraries listed below
Sorting:
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆187Updated 5 months ago
- [ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"☆64Updated last week
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆95Updated 4 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆133Updated 8 months ago
- [NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks☆132Updated 11 months ago
- [NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.☆65Updated last month
- [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆86Updated 3 weeks ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆153Updated last month
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆83Updated last month
- 📚 Collection of token-level model compression resources.☆176Updated 2 months ago
- [NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification☆29Updated 7 months ago
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆75Updated 2 weeks ago
- ☆59Updated 6 months ago
- [CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models☆52Updated 5 months ago
- MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer☆48Updated last year
- The code repository of "MBQ: Modality-Balanced Quantization for Large Vision-Language Models"☆66Updated 7 months ago
- 🚀 Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models☆37Updated 2 weeks ago
- [NeurIPS'25] HoliTom: Holistic Token Merging for Fast Video Large Language Models☆55Updated last month
- The first decoder-only multimodal state space model☆96Updated 5 months ago
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…☆41Updated 6 months ago
- [ICLR 2025] Mixture Compressor for Mixture-of-Experts LLMs Gains More☆61Updated 8 months ago
- Survey: https://arxiv.org/pdf/2507.20198☆190Updated 2 weeks ago
- [ICLR'25] Reconstructive Visual Instruction Tuning☆124Updated 7 months ago
- [CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".☆193Updated 4 months ago
- The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"☆50Updated 10 months ago
- [CVPR 2025] PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models☆49Updated last month
- [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation☆402Updated 6 months ago
- ☆125Updated 7 months ago
- Implementation for HiPrune, a training-free visual token pruning method for VLM acceleration.☆36Updated last week
- Official repository for VisionZip (CVPR 2025)☆368Updated 3 months ago