Search papers, labs, and topics across Lattice.
3
0
8
6
Light-WAM achieves high-performance robot manipulation with just 0.44B parameters, revolutionizing the efficiency of World Action Models.
InsightVQA reveals that current models struggle with high-dimensional emotion-cognitive reasoning, exposing critical gaps in visual understanding capabilities.
Forget text prompts: vector prompt interfaces are the key to unlocking scalable and stable LLM customization.
