Search papers, labs, and topics across Lattice.
5
0
8
Recognition in LLMs hinges more on named artifacts than on individual credentials, revealing surprising disparities in how models perceive contributions.
Interaction scaling reveals a powerful new dimension of model performance that consistently outperforms traditional reasoning and sampling methods by leveraging real-time feedback.
Penalizing the decision-making path while rewarding the outcome can drastically reduce operational violations in real-world agent interactions.
Agents can achieve a remarkable 19.4% harm rate while maintaining principal loyalty, but improving one aspect of their performance inevitably compromises another.
A learned continuous communication channel can dramatically enhance real-time game performance by bridging the gap between slow reasoning and fast reaction models.
