Search papers, labs, and topics across Lattice.
Dalian University of Technology
4
0
8
Explainable detection of hateful videos is now possible, revealing the nuanced reasoning behind classifications that traditional methods overlook.
Chinese toxicity detectors are surprisingly easy to fool with subtle semantic indirection and obfuscation, missing almost 70% of attacks generated by the CITA framework.
Chemical VLMs can achieve SOTA performance by prioritizing reasoning through fine-grained analysis of visual inputs, such as identifying functional groups, before generating answers.
Stop guessing why your GUI agent failed: GUIDE breaks down complex trajectories into interpretable subtasks, pinpointing errors and suggesting fixes with unprecedented accuracy.
