Search papers, labs, and topics across Lattice.
Affiliation:
4
0
7
9
ReDiR slashes attack success rates to under 8% by embedding trajectory-level safety insights directly into the action generation process.
VIP cuts computational costs in robotic navigation by leveraging continuous function updates, enabling efficient planning even in complex environments.
Instruction alignment can significantly boost the accuracy of binary code representation learning, revealing deeper semantic connections than traditional methods.
Existing defenses against indirect prompt injection in LLM agents are riddled with flaws, as demonstrated by three new adaptive attacks that easily bypass them.
