Search papers, labs, and topics across Lattice.
The University of Texas Rio Grande
4
0
8
Robot swarms can achieve significantly faster and more complete resource collection by using a simple visitation grid to guide exploration, even with limited onboard resources.
LLMs waste compute on tokens that have already "figured it out" – DASH selectively skips these tokens during prefill, speeding things up without retraining or sacrificing accuracy.
VLA models can ace the task but still trigger unsafe outcomes, exposing a critical gap between action execution and semantic understanding.
Autonomous agents are alarmingly easy to trick into harmful behavior, even when using aligned models: Claude Code achieves a 73.63% success rate on the AgentHazard benchmark.
