Search papers, labs, and topics across Lattice.
4
0
7
Forget representational differences - the secret to better feed-forward 3D scene modeling lies in tackling five core design problems.
Adversarially finetuning CLIP using a pretraining-inspired recipe with web data and feature regularization yields significantly better zero-shot robustness across diverse datasets than standard adversarial training.
Counterintuitively, VLMs can achieve higher VQA accuracy by intentionally degrading visual inputs, suggesting that high-resolution details can act as noise that hinders reasoning.
Reconstructing 3D scenes from images obscured by smoke and extreme darkness is now significantly more achievable, thanks to insights gleaned from the NTIRE 2026 challenge.
