Search papers, labs, and topics across Lattice.
7
0
10
57
World models need to forget selectively, discarding outdated instance facts while rigidly retaining fundamental invariants like physics, a nuance standard forgetting metrics miss.
RubSE transforms UI-to-code generation by using structured rubrics to stabilize self-evolution, outperforming traditional methods in both stability and performance.
AV-Flamingo outperforms existing models on complex audio-visual tasks, revealing that size isn't everything when it comes to reasoning capabilities.
Open-source diffusion models can now achieve state-of-the-art illumination control rivaling closed-source alternatives, thanks to a novel training pipeline and dataset.
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.
LALMs can be easily tricked into "hearing" things that aren't there, with success rates as high as 95% on targeted attacks.
Forget HRTFs: a differentiable multi-sphere scattering model inspired by underwater animal acoustics offers a new foundation for spatial audio processing and localization.
