Search papers, labs, and topics across Lattice.
The University of Osaka;
3
0
7
NA-LoRA reveals that adapting low-rank updates with a focus on gate channel responsiveness can significantly enhance model fine-tuning performance.
Adding just one spatial word can lead MLLMs to consistently choose the wrong answer, revealing a critical vulnerability in their reasoning processes.
LLMs struggle to predict prosecutorial decisions, highlighting a critical blind spot in legal AI's ability to assess criminal liability beyond formally indicted cases.
