Alternatives and similar repositories for TokenPacker

Users that are interested in TokenPacker are comparing it to the libraries listed below

• FoundationVision / Groma
  [ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization
  ☆581Updated last year
• xiaoachen98 / Open-LLaVA-NeXT
  An open-source implementation for training LLaVA-NeXT.
  ☆423Updated last year
• ZrrSkywalker / MAVIS
  [ICLR 2025] Mathematical Visual Instruction Tuning for Multi-modal Large Language Models
  ☆152Updated 10 months ago
• VITA-MLLM / Long-VITA
  ✨✨Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy
  ☆302Updated 5 months ago
• Kwai-YuanQi / MM-RLHF
  The Next Step Forward in Multimodal LLM Alignment
  ☆184Updated 6 months ago
• HJYao00 / DenseConnector
  【NeurIPS 2024】Dense Connector for MLLMs
  ☆179Updated last year
• Oryx-mllm / Oryx
  [ICLR 2025] MLLM for On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
  ☆327Updated 3 months ago
• baaivision / EVE
  EVE Series: Encoder-Free Vision-Language Models from BAAI
  ☆353Updated 3 months ago
• Cooperx521 / PyramidDrop
  (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
  ☆132Updated 7 months ago
• 42Shawn / LLaVA-PruMerge
  LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
  ☆152Updated last month
• lwpyh / Awesome-MLLM-Reasoning-Collection
  A collection of multimodal reasoning papers, codes, datasets, benchmarks and resources.
  ☆323Updated this week
• mrwu-mac / ControlMLLM
  [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'
  ☆195Updated 3 months ago
• xmoanvaf / llava-phi
  ☆398Updated 10 months ago
• FoundationVision / OmniTokenizer
  [NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.
  ☆316Updated last year
• Yxxxb / VoCo-LLaMA
  [CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".
  ☆192Updated 4 months ago
• dvlab-research / VisionZip
  Official repository for VisionZip (CVPR 2025)
  ☆366Updated 3 months ago
• dvlab-research / VisionThink
  [NeurIPS 2025] Efficient Reasoning Vision Language Models
  ☆407Updated last month
• ZrrSkywalker / MathVerse
  [ECCV 2024] Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?
  ☆170Updated 6 months ago
• Wiselnn570 / VideoRoPE
  [ICML 2025 Oral] An official implementation of VideoRoPE & VideoRoPE++
  ☆200Updated 3 months ago
• MME-Benchmarks / MME-RealWorld
  ✨✨ [ICLR 2025] MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
  ☆135Updated last week
• LALBJ / PAI
  [ECCV 2024] Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs
  ☆147Updated 11 months ago
• bronyayang / Law_of_Vision_Representation_in_MLLMs
  [COLM'25] Official implementation of the Law of Vision Representation in MLLMs
  ☆168Updated 3 weeks ago
• zhangbaijin / From-Redundancy-to-Relevance
  [NAACL 2025 Oral] 🎉 From redundancy to relevance: Enhancing explainability in multimodal large language models
  ☆120Updated 8 months ago
• Fantasyele / LLaVA-KD
  [ICCV 2025] Official implementation of LLaVA-KD: A Framework of Distilling Multimodal Large Language Models
  ☆103Updated 2 weeks ago
• zhaohengyuan1 / Genixer
  (ECCV 2024) Empowering Multimodal Large Language Model as a Powerful Data Generator
  ☆114Updated 7 months ago
• mashijie1028 / GenHancer
  (ICCV 2025) Enhance CLIP and MLLM's fine-grained visual representations with generative models.
  ☆73Updated 4 months ago
• dongyh20 / Chain-of-Spot
  Chain-of-Spot: Interactive Reasoning Improves Large Vision-language Models
  ☆98Updated last year
• yu-rp / VisualPerceptionToken
  ☆125Updated 7 months ago
• TempleX98 / MoVA
  [NeurIPS 2024] MoVA: Adapting Mixture of Vision Experts to Multimodal Context
  ☆167Updated last year
• invictus717 / MiCo
  [ICCV 2025] Explore the Limits of Omni-modal Pretraining at Scale
  ☆118Updated last year