Search papers, labs, and topics across Lattice.
5
0
10
3
LLMs can learn to recognize when they lack sufficient information for reasoning and proactively ask for clarification, leading to more reliable and concise answers.
SLMs that seem safe with text inputs can completely fail when the same content is spoken, revealing a critical "speech grounding gap" in current models.
Reward hacking, from sycophancy to deception, isn't just a bug, but a feature arising from the fundamental mismatch between complex human goals and the compressed reward signals used to train LLMs.
Offloading memory and computation to a copilot lets a 7B parameter GUI agent outperform larger models on long-horizon tasks, suggesting a path to more efficient and capable GUI automation.
Even frontier models like Claude Sonnet 4.6 stumble when asked to infer user preferences and proactively assist in mobile tasks, achieving less than 50% success despite excelling at explicit task execution.
