Search papers, labs, and topics across Lattice.
4
0
7
1
Heterogeneous agents can achieve "mind reading" capabilities through dense alignment, outperforming traditional methods with significantly lower compute costs.
Reasoning models may boost performance but often sacrifice critical alignment behaviors, revealing a hidden trade-off in AI safety.
A4D redefines robot interaction by enabling planning based on what objects can do, not just how they look, achieving unprecedented accuracy and speed in novel scenarios.
LLMs can now reliably follow complex, hierarchical instructions thanks to a new constrained RL framework that treats system prompts as strict algorithmic boundaries.
