LLaVA

lastmod 2025-05-14created 2024-07-024 edits

LLaVA: Large Language and Vision Assistant (Visual Instruction Tuning)

See also

• LMM
• FastVLM - Efficient vision encoding for vision language models

Favorite site

• LLaVA: Large Language and Vision Assistant - Visual Instruction Tuning
• haotian-liu/LLaVA: (NeurIPS'23 Oral) Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
• Arxiv Dives - LLaVA 🌋 an open source Large Multimodal Model (LMM)
• (Paper review) LLaVA: Large Language and Vision Assistant (Visual Instruction Tuning)