ChangyuanWang17 / QVLM
[NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.
☆67Updated 2 months ago
Alternatives and similar repositories for QVLM:
Users that are interested in QVLM are comparing it to the libraries listed below
- Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆80Updated 3 weeks ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆59Updated 3 months ago
- The official code implementation of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"☆37Updated last month
- This is the official pytorch implementation for the paper: Towards Accurate Post-training Quantization for Diffusion Models.(CVPR24 Poste…☆34Updated 9 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆81Updated 3 weeks ago
- DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆38Updated last week
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆44Updated 2 months ago
- This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality"☆46Updated this week
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆121Updated 10 months ago
- [CVPR 2025] Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training☆22Updated 2 weeks ago
- ☆53Updated this week
- 📚 Collection of token reduction for model compression resources.☆47Updated last month
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding☆39Updated last week
- [NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks☆109Updated 4 months ago
- Code release for VTW (AAAI 2025) Oral☆33Updated 2 months ago
- [CVPR 2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".☆138Updated 3 weeks ago
- [ICLR 2025] Reconstructive Visual Instruction Tuning☆73Updated 3 weeks ago
- MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer☆41Updated 6 months ago
- ☆25Updated 5 months ago
- Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆22Updated this week
- [ICLR 2025] Mixture Compressor for Mixture-of-Experts LLMs Gains More☆35Updated last month
- [CVPR 2025] PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models☆34Updated last month
- ☆111Updated 7 months ago
- ☆40Updated 2 months ago
- official impelmentation of Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input☆63Updated 6 months ago
- [ICLR 2025] LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation☆116Updated 2 months ago
- [ECCV 2024] AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation☆33Updated 6 months ago
- ☆70Updated 4 months ago
- [ECCV 2024] ControlCap: Controllable Region-level Captioning☆73Updated 5 months ago
- p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay☆32Updated 2 months ago