Search papers, labs, and topics across Lattice.
Erlangen, Germany
3
0
6
Halving multi-hop accuracy loss while maintaining single-hop recall, Kamera redefines how multimodal agents can efficiently reuse cached information without retraining.
Routing queries across GPUs can be cheaper than moving the cache, challenging conventional wisdom in LLM architecture design.
Scaling clinical LLMs doesn't guarantee safety: high-risk errors persist even with advanced RAG and max-context prompting, highlighting the critical role of evidence quality and deployment strategy.
