Search papers, labs, and topics across Lattice.
3
0
5
State-of-the-art semi-supervised domain generalization (SSDG) methods crumble when faced with the real-world challenge of long-tailed class distributions, but IMaX offers a simple, effective fix.
Slapping a learnable Gaussian kernel onto ViT self-attention boosts segmentation performance by over 6% on ADE20K, proving that locality still matters for vision.
Forget prompt engineering – ORION unlocks surprisingly large gains in VLM performance by simply fine-tuning text embeddings to be more orthogonal.