Search papers, labs, and topics across Lattice.
National University of Defense Technology
3
0
8
Agent4Drone's innovative approach to structuring multi-UAV behavior leads to a dramatic reduction in task failures, showcasing the potential of LLMs in aerial robotics.
MiniMax-M2 proves that massive parameter counts don't always translate to better agentic performance; strategic activation of a smaller subset can unlock frontier-level intelligence.
LALMs can learn to strategically "think aloud" during spoken interactions, improving accuracy and reducing response latency by externalizing intermediate reasoning steps.
