ChangyuanWang17 / QVLM
[NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.
☆63Updated last month
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" proposed by Pekin…☆75Updated 3 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆47Updated 2 months ago
- The official code of the paper "PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction".☆53Updated last month
- This is the official pytorch implementation for the paper: Towards Accurate Post-training Quantization for Diffusion Models.(CVPR24 Poste…☆34Updated 8 months ago
- MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer☆38Updated 5 months ago
- [NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks☆105Updated 2 months ago
- This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality"☆45Updated last month
- The official code implementation of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"☆27Updated this week
- [ICLR 2025] Mixture Compressor for Mixture-of-Experts LLMs Gains More☆34Updated last week
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆32Updated last month
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆116Updated 9 months ago
- Code release for VTW (AAAI 2025) Oral☆32Updated last month
- [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation☆227Updated 3 weeks ago
- Official repository of DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models☆81Updated 5 months ago
- VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection☆51Updated last month
- ☆35Updated last month
- 📚 Collection of token reduction for model compression resources.☆27Updated this week
- p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay☆30Updated last month
- ☆110Updated 6 months ago
- DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆26Updated last month
- Accepted by CVPR 2024☆31Updated 9 months ago
- PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models☆25Updated 2 months ago
- A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models!☆125Updated last year
- [ECCV 2024] AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation☆33Updated 5 months ago
- [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'☆143Updated last month
- [Preprint] Number it: Temporal Grounding Videos like Flipping Manga☆55Updated 2 months ago
- Official repository of InLine attention (NeurIPS 2024)☆39Updated last month
- official impelmentation of Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input☆63Updated 5 months ago