Search papers, labs, and topics across Lattice.
Columbia University
3
0
6
Reasoning LLMs can now produce well-calibrated confidence estimates without labels or repeated sampling, unlocking more reliable real-world deployment.
Unlock adaptable agents that learn selectively from diverse data streams by controlling neural memory with natural language instructions.
LLMs can now adaptively survey the *right* people, not just ask the *right* questions, boosting response prediction by 12% while querying only 10% of the population.
