Search papers, labs, and topics across Lattice.
♣ Independent Researcher, University of Texas at Dallas, ♠ University of California
3
0
7
Multi-agent LLMs can achieve up to 30% higher accuracy and consume 6.5x fewer tokens by minimizing direct agent communication and instead coordinating via a structured belief state.
Suppressing background noise with heatmap-guided positional embeddings slashes transformer detector parameters by 59% without sacrificing accuracy in small object detection.
Key contribution not extracted.
