Search papers, labs, and topics across Lattice.
University of Science and Technology
3
0
7
Code agents are only eliminating 50% of code smells, revealing critical gaps in their understanding of maintainability and cross-file dependencies.
LLMs can generate better features from tabular data when deployed as a multi-agent system with explicit memory of past procedures, feedback, and concepts.
Existing defenses against talking-head manipulation are easily bypassed: SyncBreaker shows how to effectively degrade lip sync and facial dynamics by jointly perturbing audio and video.
