Search papers, labs, and topics across Lattice.
5
88
10
29
Multimodal models can now achieve state-of-the-art performance in real-world tasks like document understanding and audio-video comprehension with significantly reduced inference latency thanks to novel token-reduction techniques.
Audio-language models can now reason about 30-minute-long audio clips with timestamp-grounded intermediate steps, unlocking a new level of fine-grained understanding.
A 30B MoE model can now achieve Gold Medal-level performance in IMO, IOI, and ICPC, rivaling frontier models with 20x more parameters.
Forget hand-crafted datasets: a new synthetic data pipeline lets smaller LLMs beat giants at terminal tasks.
A 3B parameter model, Audio Flamingo 2, now rivals larger proprietary models in audio understanding and reasoning, even handling audio segments up to 5 minutes long.
