hasanar1f / HiRED
[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.
☆28Updated 2 months ago
Alternatives and similar repositories for HiRED:
Users that are interested in HiRED are comparing it to the libraries listed below
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆64Updated 3 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆84Updated 3 weeks ago
- [ICLR 2025] The official pytorch implement of "Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Cont…☆26Updated 4 months ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆121Updated 10 months ago
- ☆70Updated 2 months ago
- Code release for VTW (AAAI 2025) Oral☆33Updated 2 months ago
- ☆41Updated 2 months ago
- [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding☆31Updated 3 months ago
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆44Updated 2 months ago
- Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆26Updated this week
- The official GitHub page for ''What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Ins…☆19Updated last year
- [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…☆92Updated 4 months ago
- This is the official repo for ByteVideoLLM/Dynamic-VLM☆20Updated 3 months ago
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation☆47Updated 3 months ago
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆65Updated 10 months ago
- Official implementation for FlexAttention for Efficient High-Resolution Vision-Language Models☆38Updated 2 months ago
- ☆91Updated last year
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆21Updated 2 months ago
- Official implement of MIA-DPO☆54Updated 2 months ago
- Official Codebase for "Generative Multimodal Model Features Are Discriminative Vision-Language Classifiers"☆13Updated last week
- [NeurIPS'24] Official PyTorch Implementation of Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment☆57Updated 6 months ago
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆70Updated 9 months ago
- ☆40Updated 4 months ago
- A Self-Training Framework for Vision-Language Reasoning☆73Updated 2 months ago
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆70Updated 4 months ago
- ☆56Updated last week
- [ICLR2025] γ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Models☆34Updated last month
- Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal …☆46Updated last month
- [ACL 2024] Multi-modal preference alignment remedies regression of visual instruction tuning on language model☆40Updated 4 months ago
- ☆25Updated 10 months ago