hasanar1f / HiREDLinks
[AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Vision-Language Models (e.g., LLaVA-Next) under a fixed token budget.
☆39Updated 2 months ago
Alternatives and similar repositories for HiRED
Users that are interested in HiRED are comparing it to the libraries listed below
Sorting:
- Code release for VTW (AAAI 2025) Oral☆43Updated 5 months ago
- ☆48Updated last month
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆109Updated 3 months ago
- [CVPR 2025] PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models☆42Updated last week
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆78Updated 6 months ago
- [CVPR 2025] Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training☆47Updated 2 months ago
- ☆21Updated 3 months ago
- [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Cont…☆42Updated 6 months ago
- ☆42Updated 7 months ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆30Updated 5 months ago
- Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆54Updated last month
- [ICLR2025] γ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Models☆36Updated 4 months ago
- [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding☆50Updated 6 months ago
- Official Repository: A Comprehensive Benchmark for Logical Reasoning in MLLMs☆37Updated last week
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆133Updated last year
- NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation☆67Updated 2 weeks ago
- ☆78Updated 5 months ago
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding☆73Updated 2 months ago
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆62Updated 5 months ago
- [NeurIPS'24] Official PyTorch Implementation of Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment☆56Updated 8 months ago
- ☆44Updated 5 months ago
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆123Updated 2 weeks ago
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆51Updated last week
- 🚀 Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models☆23Updated last week
- ☆14Updated last month
- ☆86Updated 3 months ago
- Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"☆29Updated last month
- This is the official repo for ByteVideoLLM/Dynamic-VLM☆20Updated 6 months ago
- DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding☆61Updated 2 weeks ago
- The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"☆46Updated 5 months ago