Search papers, labs, and topics across Lattice.
2
0
5
Multimodal federated learning can finally handle the messy reality of missing data with BLOSSOM's block-wise personalization, boosting performance by up to 37.7% compared to naive aggregation.
VLMs can be easily swayed by subtle, optimized visual prompts, revealing vulnerabilities in their decision-making processes that could be exploited in real-world applications.