Search papers, labs, and topics across Lattice.
University of California , Santa Barbara ,, The Chinese University of Hong Kong, Shenzhen
6
0
12
7
Optimizing soft memory directly for user behavior, not text reconstruction, unlocks state-of-the-art long-context personalization.
This work introduces HarnessVLN, a zero-shot, training-free framework that unifies instruction-following and object-goal navigation through a shared Agent Harness, and demonstrates its applicability to both navigation tasks in real-world environments.
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.
