Search papers, labs, and topics across Lattice.
4
0
6
Retaining critical information in robot locomotion can yield a 15% performance boost while simplifying the model's architecture.
SLIDER achieves superior target search efficiency while slashing memory usage and decision latency, redefining aerial exploration capabilities.
LLM judges in multi-stakeholder settings suffer from "weighting noise" that gets *worse* as you add more stakeholders, but fixing weights upfront can stabilize the process.
Frontier LLMs still struggle with preference coverage and group fairness when planning travel for multiple users, revealing a critical gap in real-world agent capabilities.
