Search papers, labs, and topics across Lattice.
7
0
9
9
Switching music tokenization can halve the Frechet Music Distance, proving that representation trumps model size in text-to-music generation.
IOM enables robots to recall manipulation procedures from a single encounter, slashing operation counts by up to 30% while ensuring task success remains intact.
Lumera achieves state-of-the-art performance in 3D scene reconstruction, revealing critical gaps in light localization and cross-engine generalization.
PairCoder boosts artifact verifiability by up to 3.9 times compared to traditional single-pass inference, revealing the power of collaborative programming in AI-generated outputs.
OVOW achieves unprecedented accuracy and speed in reconstructing 4D scenes from a single video, making it a game-changer for physics simulation in AI.
Existing VLMs misinterpret critical evidence in exploratory manipulation, but a novel distillation approach boosts action recovery accuracy by nearly half.
Language models are increasingly doing their real work in the "invisible" latent space, not the tokens we see.
