Search papers, labs, and topics across Lattice.
University of Science and Technology of China
3
0
8
Achieve over 90% accuracy in attributing generated videos to their source model with as few as 20 samples, all without training or modifying the videos themselves.
Stop letting foreground attention shifts sabotage your VLM prompt tuning: FVG-PT adaptively guides attention to boost performance.
LLMs can handle basic route planning, but fall apart when user preferences enter the mix, as shown by a new benchmark based on real-world queries.
