Danielement321 / HiPruneLinks
Implementation for HiPrune, a training-free visual token pruning method for VLM acceleration.
☆40Updated 2 months ago
Alternatives and similar repositories for HiPrune
Users that are interested in HiPrune are comparing it to the libraries listed below
Sorting:
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆137Updated 10 months ago
- [ICCV 2025] Official implementation of LLaVA-KD: A Framework of Distilling Multimodal Large Language Models☆120Updated 2 months ago
- [CVPR 2025] Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training☆98Updated 5 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆101Updated 6 months ago
- ☆132Updated 9 months ago
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding☆157Updated 3 weeks ago
- ☆62Updated 8 months ago
- [EMNLP 2025 Main] Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models☆49Updated this week
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆95Updated last month
- [EMNLP 2025 main 🔥] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆97Updated 2 months ago
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference" and "Sp…☆217Updated 2 weeks ago
- [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"☆50Updated 3 months ago
- MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer☆49Updated last year
- [CVPR 2025 Oral] VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection☆131Updated 5 months ago
- [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…☆44Updated 8 months ago
- [ICLR'25] Reconstructive Visual Instruction Tuning☆133Updated 9 months ago
- [ICCV 2025] Official code for paper: Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs☆56Updated 6 months ago
- TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning☆110Updated 2 weeks ago
- [ICCV 2025] p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay☆43Updated 6 months ago
- Code and dataset link for "DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World"☆120Updated 3 months ago
- ☆101Updated 4 months ago
- [ECCV 2024] Elysium: Exploring Object-level Perception in Videos via MLLM☆86Updated last year
- [ICLR 2025] LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation☆218Updated 9 months ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆36Updated last year
- [NeurIPS 2024] Visual Perception by Large Language Model’s Weights☆55Updated 9 months ago
- ☆74Updated 7 months ago
- [ICCV 2025] Dynamic-VLM☆28Updated last year
- Official code for NeurIPS 2025 paper "GRIT: Teaching MLLMs to Think with Images"☆172Updated this week
- Pruning the VLLMs☆105Updated last year
- ✨✨ [ICLR 2025] MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?☆150Updated 2 months ago