Search papers, labs, and topics across Lattice.
4
0
8
CircuitLasso reveals how human-interpretable semantic features propagate through LLMs, achieving high accuracy with drastically lower computational costs.
Sharing key-value caches in multi-agent LLM systems leaks sensitive agent information, but LCGuard can protect it with representation-level transformations.
Steer LLMs like never before with AI Steerability 360, an open-source toolkit that unifies input, structural, state, and output steering methods under a common pipeline.
Agentic systems leak sensitive data in 80% of workflows, even when the final output seems safe, because current privacy evaluations miss intermediate steps.
