Search papers, labs, and topics across Lattice.
Rensselaer Polytechnic Institute
2
0
4
Sharing key-value caches in multi-agent LLM systems leaks sensitive agent information, but LCGuard can protect it with representation-level transformations.
LLMs can slash memory use by 4x during reasoning without sacrificing accuracy, simply by "zooming in" on relevant cached information instead of attending to everything.
