Search papers, labs, and topics across Lattice.
The Chinese University of Hong Kong, Shenzhen
4
0
8
5
Just because your agent can write and store memories well doesn't mean it can actually *use* them effectively in a dynamic, multimodal world.
Training a foundation model on a trillion minutes of wearable sensor data unlocks surprisingly accurate predictions across a wide range of health conditions, even with limited labeled data.
Multi-agent LLM systems for idea generation can backfire, with smarter models and more communication leading to *less* diverse ideas due to structural coupling.
Current embodied AI agents falter when faced with the multi-floor complexity of MANSION, a new language-driven framework for generating realistic, building-scale 3D environments.
