Search papers, labs, and topics across Lattice.
Affiliation:
3
0
3
0
The unexpected effects of visual cues on LVLMs highlight the need to understand the presence of an image and its framing when evaluating the robustness of LVLMs.
Object hallucinations in LVLMs can be effectively detected by analyzing attention drifts and prediction changes, revealing critical insights into model reliability.
Backdoor detection just got a major upgrade鈥擠istScan identifies attacks by analyzing shifts in prediction distributions, achieving a 27.32% accuracy boost over existing methods.
