Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
2
0
3
0
Nonlinear recurrent memories struggle with sequential test-time training, but layerwise delta updates unlock significant gains in language modeling and retrieval.
Achieving comparable text-to-image quality with a linearized model that accelerates inference by up to 1.47 times, all while leveraging pretrained weights.