Search papers, labs, and topics across Lattice.
4
0
8
1
Making interactive video world models real-time just got easier: minWM offers a full-stack, open-source pipeline to convert existing diffusion models into controllable, low-latency generators.
Douyin Music users are spending almost 50% more days actively engaging with the app thanks to a new LLM that understands vague, conversational music requests.
Polarization cues, often overlooked, unlock significantly more robust monocular depth estimation, especially in scenes with challenging reflective or transparent surfaces.
Ditching pixel-space translation unlocks a unified model (LatentUM) that reasons across modalities with SOTA results, opening doors to more efficient and aligned visual AI.
