Debate Over VLM vs MLLM Definitions

Researchers including Jitendra Malik debated on X whether CLIP-style encoders count as VLMs, while others clarified that CLIP-like models are VLMs and LLM-based models such as LLaVA should be called MLLMs.

2026-08-25 ~ 2026-08-26 · 2 related posts

• Community discusses definition differences between VLM and MLLM — TimDarcet · 2026-08-25
• Debate on VLM Definition: Are CLIP Encoders Considered VLMs? — giffmana · 2026-08-26