CircleRadon / TokenPackerLinks
The code for "TokenPacker: Efficient Visual Projector for Multimodal LLM", IJCV2025
☆265Updated 3 months ago
Alternatives and similar repositories for TokenPacker
Users that are interested in TokenPacker are comparing it to the libraries listed below
Sorting:
- [ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization☆579Updated last year
- [ICLR 2025] Mathematical Visual Instruction Tuning for Multi-modal Large Language Models☆148Updated 8 months ago
- An open-source implementation for training LLaVA-NeXT.☆417Updated 10 months ago
- A collection of multimodal reasoning papers, codes, datasets, benchmarks and resources.☆292Updated this week
- 【NeurIPS 2024】Dense Connector for MLLMs☆174Updated 10 months ago
- ✨✨Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy☆296Updated 3 months ago
- [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'☆190Updated last month
- The Next Step Forward in Multimodal LLM Alignment☆176Updated 3 months ago
- [ECCV 2024] Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?☆169Updated 4 months ago
- [ICLR 2025] MLLM for On-Demand Spatial-Temporal Understanding at Arbitrary Resolution☆320Updated last month
- ✨✨ [ICLR 2025] MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?☆130Updated 5 months ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆119Updated 5 months ago
- Chain-of-Spot: Interactive Reasoning Improves Large Vision-language Models☆96Updated last year
- ☆397Updated 8 months ago
- [CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".☆186Updated 2 months ago
- (ECCV 2024) Empowering Multimodal Large Language Model as a Powerful Data Generator☆113Updated 5 months ago
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆142Updated 2 months ago
- [NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.☆306Updated last year
- The official implementation of RAR☆90Updated last year
- Official implementation of "Towards Efficient Visual Adaption via Structural Re-parameterization".☆185Updated last year
- [NeurIPS 2024] MoVA: Adapting Mixture of Vision Experts to Multimodal Context☆165Updated 11 months ago
- EVE Series: Encoder-Free Vision-Language Models from BAAI☆348Updated last month
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding☆97Updated this week
- Official implementation of the Law of Vision Representation in MLLMs☆163Updated 9 months ago
- [CVPR 2025] The code for "VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM"☆258Updated this week
- [ICML 2025 Oral] An official implementation of VideoRoPE & VideoRoPE++☆184Updated last month
- official impelmentation of Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input☆67Updated 11 months ago
- [ICLR 2025] LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation☆192Updated 4 months ago
- [ICML'25] Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".☆148Updated 2 months ago
- (ICCV 2025) Enhance CLIP and MLLM's fine-grained visual representations with generative models.☆70Updated 2 months ago