Search papers, labs, and topics across Lattice.
6
0
9
5
Gaze-only models can be significantly improved by injecting lightweight language signals, achieving up to a 2.9 percentage point gain in reading comprehension prediction accuracy.
ProsMAE outperforms traditional methods by leveraging diverse histopathology datasets to significantly improve ISUP grade classification accuracy.
Medical imaging AI can now leverage a self-supervised pre-training method that understands 3D context, boosting reconstruction quality beyond what's possible with 2D-centric approaches.
Fine-tuning only the decoder of a trajectory prediction model pretrained on US data slashes prediction error by 66% when adapting to Korean driving environments.
By cleverly repurposing GAN and diffusion model discriminators, CIPHER achieves state-of-the-art deepfake detection that's robust to unseen generative models, leaving traditional detectors in the dust.
Synthetic MRI data, generated by a segmentation-conditioned diffusion model, can measurably improve the performance of 3D U-Nets for hepatic segmentation.
