Search papers, labs, and topics across Lattice.
4
0
10
3
G-MARK reveals that grounding multi-agent reasoning in provenance-aware knowledge graphs can drastically enhance occlusion reasoning and decision-making in cooperative driving.
Continual adaptation to evolving prompt injection attacks can enhance LLM defenses by up to 6.3 times, addressing a critical vulnerability in AI systems.
LLMs can parrot CAN bus data, but CAN-QA reveals they fail at the temporal reasoning and multi-condition inference needed for real-world vehicle security forensics.
Forget backpropagation: a forward-pass KL divergence metric pinpoints which parts of your SSM-Transformer hybrid model are most vulnerable to quantization, enabling efficient mixed-precision deployment on edge devices.
