Search papers, labs, and topics across Lattice.
Sapienza University of Rome
4
0
6
Extra Trees outperforms neural networks in identifying unknown subjects from hand landmarks, revealing a critical challenge in score separation rather than mere discrimination.
Fragmented execution logs can be stitched together into a topological knowledge base that allows multi-agent systems to execute workflows more reliably and with greater semantic awareness.
Even state-of-the-art AI agents are surprisingly vulnerable to incremental attacks that gradually lead them to perform unsafe actions in realistic workplace scenarios.
Frontier model safety crumbles when harmful prompts are rephrased with humanities-style transformations, revealing a profound lack of stylistic robustness.
