Search papers, labs, and topics across Lattice.
Lancaster University,School of Computing and Communications,UK
4
0
6
9
Hallucinations in LVLMs can be effectively mitigated without training by leveraging per-instance subspaces that adaptively suppress specific hallucination modes.
Introspective attention modulation can significantly enhance the safety of T2I models without sacrificing quality, outperforming existing methods like concept erasure.
Training-free motion generation can now flexibly handle both continuous and discontinuous constraints without requiring differentiability, revolutionizing how we approach human motion synthesis.
MLLMs can be effectively guided to enhance diagnostic accuracy in breast ultrasound by leveraging expert feedback, reducing hallucinations and improving interpretability.
