thu-nics / FrameFusion
The official code implementation of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"
☆39Updated last week
Alternatives and similar repositories for FrameFusion:
Users that are interested in FrameFusion are comparing it to the libraries listed below
- Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆93Updated last month
- [NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.☆71Updated 3 months ago
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆50Updated 3 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆70Updated 4 months ago
- 📚 Collection of token reduction for model compression resources.☆51Updated last week
- Code release for VTW (AAAI 2025) Oral☆34Updated 3 months ago
- [NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification☆21Updated 3 weeks ago
- DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆40Updated 2 weeks ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆126Updated 11 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆89Updated last month
- [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…☆92Updated 5 months ago
- This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality"☆46Updated last month
- Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆36Updated 3 weeks ago
- [Arxiv 2025] Efficient Reasoning Models: A Survey☆107Updated this week
- A collection of recent token reduction (token pruning, merging, clustering, etc.) techniques for ML/AI☆39Updated this week
- ☆42Updated 3 months ago
- ☆80Updated last month
- The code repository of "MBQ: Modality-Balanced Quantization for Large Vision-Language Models"☆37Updated last month
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding☆56Updated this week
- ☆160Updated 3 months ago
- The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"☆44Updated 3 months ago
- [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Cont…☆31Updated 4 months ago
- XAttention: Block Sparse Attention with Antidiagonal Scoring☆140Updated 3 weeks ago
- ✈️ Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints☆65Updated 3 weeks ago
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…☆30Updated last week
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆27Updated 3 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆77Updated last month
- [ICLR2025] γ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Models☆36Updated 2 months ago
- official impelmentation of Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input☆64Updated 7 months ago
- p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay☆35Updated 3 months ago