Search papers, labs, and topics across Lattice.
3
0
8
Memory isolation fails to protect user data in LLM agents, as demonstrated by the SPORE attack, which achieves an 80% extraction rate even with limited triggers.
Hidden Decoding achieves unprecedented performance improvements in large language models by scaling computation along the sequence length without modifying the Transformer architecture.
Robots can now better navigate using language instructions even when objects block their view, thanks to a new method that reasons about the environment in a bird's-eye view rather than relying on visible pixels.
