Search papers, labs, and topics across Lattice.
5
0
9
0
Today's visually impressive video world models still fail to produce physically plausible robot actions, revealing a critical gap between visual realism and embodiment.
Forget flat, lifeless speech: this model uses self-critique to generate expressive speech rivaling GPT-4o-Audio, even with significantly less training data.
Ditch the critic: This new reinforcement learning approach trains feature extractors for human activity recognition without needing a value function, leading to more stable and generalizable performance across diverse users.
Current LLMs struggle with biologically complex tasks in single-cell biology, particularly those requiring mechanistic or causal understanding, highlighting the need for more biology-aligned foundation models.
Slash spoken dialogue system latency by up to 51% with a new architecture that lets the system "listen-while-thinking" and "speak-while-thinking."
