18 Commits

Author	SHA1	Message	Date
lucidrains	077d8c188f	fix distill	2025-12-10 15:52:10 -08:00
lucidrains	5888f05300	1.16.4	2025-12-07 04:32:52 -08:00
lucidrains	dd6462d19b	release small navit perf	2025-12-06 04:57:12 -08:00
lucidrains	3cff5e547a	address https://github.com/lucidrains/vit-pytorch/issues/352	2025-12-02 05:21:52 -08:00
lucidrains	fdaf7f92b9	fix positional embed for mean pool case and cleanup	2025-11-27 17:01:47 -08:00
lucidrains	0ebd4edab9	address https://github.com/lucidrains/vit-pytorch/issues/351	2025-11-27 06:07:43 -08:00
lucidrains	aa49c2783a	VAAT should have two ears	2025-11-22 08:32:23 -08:00
lucidrains	6aa0374313	register tokens for the AST in VAAT	2025-11-22 08:12:01 -08:00
lucidrains	b35a97de05	improvise a variant of VAT with audio cortex before fully generalizing it	2025-11-22 07:51:19 -08:00
lucidrains	1374b93145	the paper claims finetuning everything was better, but just allow for freezing the visual cortex, what PI proposes	2025-11-09 10:59:55 -08:00
lucidrains	4386742cd1	an option to return zero for decorr aux loss if insufficient samples	2025-11-09 10:08:06 -08:00
lucidrains	5cf8384c56	add a vit with decorrelation auxiliary losses for mha and feedforwards, right after prenorm - this is in line with a paper from the netherlands, but without extra parameters or their manual sgd update scheme	2025-10-28 12:17:32 -07:00
lucidrains	f7d59cecb5	some register tokens cannot hurt for VAT	2025-10-24 14:00:38 -07:00
lucidrains	a583cb5988	last tweak to vat	2025-10-23 12:21:09 -07:00
lucidrains	25871013f5	forgot task conditioning for vat	2025-10-23 10:55:16 -07:00
lucidrains	e66862bcd5	add VAT from iclr 2026, which claims SOTA on libero using a relatively simple scheme (#350)	2025-10-23 10:23:53 -07:00
lucidrains	39fd9ac8be	for n-dimensional vit, have a method for fetching muon friendly parameters	2025-10-13 12:07:48 -07:00
lucidrains	3becf087bb	have a language model address https://github.com/lucidrains/vit-pytorch/issues/348	2025-09-25 06:21:13 -07:00