Search papers, labs, and topics across Lattice.
3
0
6
47
This work meta-train speaker-state dynamics through the closed streaming loop, exposing the updater to its own contaminated evidence, and proposes 41k-parameter anchored fast-weights memory, which moves beyond the measured heuristic frontier.
Cocktail-Talker enables spoken dialog systems to navigate the chaos of multi-speaker interactions, achieving selective engagement in noisy environments.
LLMs still fail to grasp research-level mathematics, with top models scoring below random chance when superficial pattern matching is removed, even with access to proof sketches.
