Adlith / MoE-JetpackLinks
[NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
☆130Updated 10 months ago
Alternatives and similar repositories for MoE-Jetpack
Users that are interested in MoE-Jetpack are comparing it to the libraries listed below
Sorting:
- [ICCV 2025] Official implementation of LLaVA-KD: A Framework of Distilling Multimodal Large Language Models☆98Updated 3 months ago
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆163Updated 4 months ago
- [ICLR'25] Reconstructive Visual Instruction Tuning☆118Updated 5 months ago
- ☆122Updated 6 months ago
- [CVPR 2025] Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training☆87Updated 2 months ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆149Updated last week
- [EMNLP 2025 main] Code for "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"☆74Updated last month
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆130Updated 7 months ago
- Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.☆91Updated 3 months ago
- [NeurIPS 2024] Classification Done Right for Vision-Language Pre-Training☆216Updated 6 months ago
- ☆119Updated last year
- The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"☆48Updated 9 months ago
- Official code implementation of Perception R1: Pioneering Perception Policy with Reinforcement Learning☆261Updated 2 months ago
- [CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".☆189Updated 3 months ago
- Pruning the VLLMs☆104Updated 9 months ago
- [NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.☆83Updated 9 months ago
- ☆118Updated last year
- ✨✨ [ICLR 2025] MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?☆133Updated 7 months ago
- ☆55Updated 5 months ago
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆71Updated 8 months ago
- [ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"☆60Updated last month
- The first decoder-only multimodal state space model☆97Updated 4 months ago
- [ICLR 2025] LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation☆200Updated 6 months ago
- Code and dataset link for "DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World"☆109Updated this week
- Official code for NeurIPS 2025 paper "GRIT: Teaching MLLMs to Think with Images"☆143Updated 2 months ago
- Official implementation of the Law of Vision Representation in MLLMs☆166Updated 10 months ago
- MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer☆46Updated last year
- Official repo of Griffon series including v1(ECCV 2024), v2(ICCV 2025), G, and R, and also the RL tool Vision-R1.☆236Updated last month
- [NeurIPS 2024] MoVA: Adapting Mixture of Vision Experts to Multimodal Context☆166Updated last year
- DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception☆155Updated 10 months ago