Search papers, labs, and topics across Lattice.
Tsinghua University Sun Yat-sen University Central South University University of Illinois at Chicago
Tsinghua AI3
0
6
LLMs are evolving from reactive chatbots to proactive digital colleagues, fundamentally changing how AI can assist in complex tasks.
Forget bolting vision onto language models – truly powerful multimodal AI demands rethinking architectures from the ground up.
MLLMs can ace the test, but still fail to *see*—they often succeed at complex reasoning with symbols while failing at basic symbol recognition, revealing a reliance on linguistic priors over true visual perception.
