Search papers, labs, and topics across Lattice.
5
0
10
Treating raw visual images as action representations revolutionizes embodied world models, leading to unprecedented generalization and control capabilities.
Coordinated attacks on discourse-level opinion can shift perceptions across multi-topic queries, exposing critical vulnerabilities in RAG systems.
Remotely hosted Mixture-of-Experts LLMs are vulnerable to input-only attacks that hijack their routing mechanisms, forcing them to generate harmful content.
LinkedIn's new memory system for hiring agents boosts accuracy and speed by over 10%, proving hierarchical semantic memory is a game-changer for real-world LLM applications.
Even with partial observability from manipulator truncation, StableIDM recovers stable action predictions, boosting downstream VLA real-robot success by 17.6%.
