Alternatives and similar repositories for LLaVA-Mini

Users that are interested in LLaVA-Mini are comparing it to the libraries listed below

• PKU-YuanGroup / Chat-UniVi
  [CVPR 2024 Highlight🔥] Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
  ☆940Updated last year
• UX-Decoder / LLaVA-Grounding
  ☆420Updated last year
• Vision-CAIR / LongVU
  [ICML 2025] Official PyTorch implementation of LongVU
  ☆407Updated 5 months ago
• mbzuai-oryx / LlamaV-o1
  [ACL 2025 🔥] Rethinking Step-by-step Visual Reasoning in LLMs
  ☆307Updated 5 months ago
• apple / ml-slowfast-llava
  SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
  ☆277Updated last year
• SYuan03 / MM-IFEngine
  [ICCV 2025] MM-IFEngine: Towards Multimodal Instruction Following
  ☆109Updated last month
• EvolvingLMMs-Lab / LongVA
  Long Context Transfer from Language to Vision
  ☆394Updated 7 months ago
• yeliudev / VideoMind
  💡 VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning
  ☆270Updated 3 weeks ago
• microsoft / LLM2CLIP
  LLM2CLIP makes SOTA pretrained CLIP model more SOTA ever.
  ☆557Updated 4 months ago
• PhoenixZ810 / OmniAlign-V
  Official Repository of ACL 2025 paper OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference
  ☆142Updated 8 months ago
• dongyh20 / Insight-V
  [CVPR2025 Highlight] Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models
  ☆228Updated 3 months ago
• turningpoint-ai / VisualThinker-R1-Zero
  Explore the Multimodal “Aha Moment” on 2B Model
  ☆613Updated 7 months ago
• tulerfeng / Video-R1
  Video-R1: Reinforcing Video Reasoning in MLLMs [🔥the first paper to explore R1 for video]
  ☆723Updated last month
• SkyworkAI / Vitron
  NeurIPS 2024 Paper: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
  ☆575Updated last year
• zjysteven / lmms-finetune
  A minimal codebase for finetuning large multimodal models, supporting llava-1.5/1.6, llava-interleave, llava-next-video, llava-onevision,…
  ☆350Updated this week
• RLHF-V / RLAIF-V
  [CVPR'25 highlight] RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
  ☆421Updated 5 months ago
• MME-Benchmarks / Video-MME
  ✨✨[CVPR 2025] Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
  ☆674Updated 2 months ago
• EvolvingLMMs-Lab / LLaVA-OneVision-1.5
  Fully Open Framework for Democratized Multimodal Training
  ☆585Updated last week
• Fancy-MLLM / R1-Onevision
  R1-onevision, a visual language model capable of deep CoT reasoning.
  ☆569Updated 6 months ago
• dvlab-research / VisionZip
  Official repository for VisionZip (CVPR 2025)
  ☆366Updated 3 months ago
• IVGSZ / Flash-VStream
  This is the official implementation of ICCV 2025 "Flash-VStream: Efficient Real-Time Understanding for Long Video Streams"
  ☆241Updated 2 weeks ago
• luogen1996 / LLaVA-HR
  [ICLR2025] LLaVA-HR: High-Resolution Large Language-Vision Assistant
  ☆244Updated last year
• VARGPT-family / VARGPT
  VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model
  ☆345Updated 6 months ago
• bytedance / tarsier
  Tarsier -- a family of large-scale video-language models, which is designed to generate high-quality video descriptions , together with g…
  ☆497Updated 2 months ago
• h-zhao1997 / cobra
  [AAAI-25] Cobra: Extending Mamba to Multi-modal Large Language Model for Efficient Inference
  ☆289Updated 9 months ago
• thunlp / LLaVA-UHD
  LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer
  ☆389Updated this week
• FreedomIntelligence / LongLLaVA
  LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture
  ☆211Updated 9 months ago
• XiaomiMiMo / MiMo-VL
  MiMo-VL
  ☆571Updated 2 months ago
• boheumd / MA-LMM
  (2024CVPR) MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
  ☆339Updated last year
• SkyworkAI / MoE-plus-plus
  [ICLR 2025] MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts
  ☆248Updated last year