State-of-the-art MLLMs achieve PhD-level language reasoning but struggle with visual tasks that 3-year-olds solve effortlessly.
Unipat AI
UnipatAI
AI & ML interests
None yet
Recent Activity
published
a model 4 days ago
UnipatAI/UniScientist-30B-A3B upvoted a paper 6 days ago
MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning updated
a model 7 days ago
UnipatAI/UniScientist-30B-A3B Organizations
None yet