Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
2
7.40% of LLM-generated query concepts are found to be answer-side intrusions, challenging the validity of current information retrieval evaluations.
VLMs often rely on misleading visual cues instead of true chronological understanding, revealing critical flaws in their reasoning capabilities.
Multimodal graph unlearning doesn't have to destroy utility: carefully protecting high-dimensional input projections during the unlearning process preserves performance while still enabling effective forgetting.
