Commit Graph

248 Commits

Author SHA1 Message Date
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
f6bc14c81d able to return embed from vit-nd-rotary 2025-09-23 07:21:34 -07:00
lucidrains
845c844b3b add a vit nd with rotary nd, from Jerry Xiong at UIUC 2025-09-21 10:45:42 -07:00
lucidrains
5f2bc0c796 with assistance from claude (yes it did the einops equation building here), generalize to n-dimensions 2025-09-21 06:22:43 -07:00
Baraa sameeh
1123063a5e Make all CCT regularization parameters user-configurable. (#346) 2025-08-17 18:07:25 -07:00
lucidrains
f8bec5ede2 able to project the image embedding before applying time positional embedding for accept video wrapper 2025-08-13 10:15:18 -07:00
lucidrains
297e7d00a2 handle channel first for accept video wrapper 2025-08-03 08:29:40 -07:00
lucidrains
29ac8e143c fix when video time seq len less than max time seq len for video acceptor 2025-07-27 09:00:56 -07:00
lucidrains
e05cd6d8b8 some models only return embeddings with some kwarg on forward 2025-07-27 08:46:43 -07:00
lucidrains
b46233c3d6 need to be able to invoke with eval no grad 2025-07-27 08:25:58 -07:00
lucidrains
68e13a3c7d bit more flexible 2025-07-27 08:14:48 -07:00
lucidrains
b22dc0ecd2 add a wrapper for accepting video and processing the images individually, optionally able to add time positional embeddings - for use in two robotics work 2025-07-27 08:05:48 -07:00
lucidrains
db05a141a6 add the proposed jumbo vit from Fuller et al. of Carleton University 2025-03-05 10:50:34 -08:00
JacobLinCool
ab63fc9cc8 remove duplicated qkv computation in na_vit_nested_tensor_3d.py (#341) 2025-01-19 05:52:46 -08:00
Kale Kundert
b7ed6bad28 add option to set frame padding for 3D CCT (#339) 2025-01-04 07:55:27 -08:00
lucidrains
e7cba9ba6d add a simple vit flavor for a new bytedance paper that proposes to break out of the traditional one residual stream architecture - "hyper-connections" 2024-12-20 17:43:50 -08:00
lucidrains
56373c0cbd make value residual learned 2024-11-24 08:21:28 -08:00
lucidrains
24196a3e8a allow for qk norm to be turned off for na vit nested tensor 2024-11-20 10:59:22 -08:00
lucidrains
d47c57e32f fix tests 2024-11-10 09:43:54 -08:00
lucidrains
0449865786 update minimum version for nested tensor of NaViT 2024-11-10 09:37:48 -08:00
lucidrains
6693d47d0b update comment for navit 3d 2024-11-07 20:02:07 -08:00
Phil Wang
141239ca86 fix value residual 2024-10-31 06:48:24 -07:00
lucidrains
0b5c9b4559 add value residual based simple vit 2024-10-28 09:19:00 -07:00
lucidrains
e300cdd7dc fix multiheaded qk rmsnorm in nViT 2024-10-10 19:15:17 -07:00
Phil Wang
36ddc7a6ba go all the way with the normalized vit, fix some scales 2024-10-10 10:42:37 -07:00
Phil Wang
74b62009f8 go for multi-headed rmsnorm for the qknorm on hypersphere vit 2024-10-10 08:09:58 -07:00
Phil Wang
f50d7d1436 add a hypersphere vit, adapted from https://arxiv.org/abs/2410.01131 2024-10-09 07:32:25 -07:00
lucidrains
82f2fa751d address https://github.com/lucidrains/vit-pytorch/issues/330 2024-10-04 07:01:48 -07:00
lucidrains
fcb9501cdd add register tokens to the nested tensor 3d na vit example for researcher 2024-08-28 12:21:31 -07:00
roydenwa
9d43e4d0bb Add ViViT variant with factorized self-attention (#327)
* Add FactorizedTransformer

* Add variant param and check in fwd method

* Check if variant is implemented

* Describe new ViViT variant
2024-08-21 19:23:38 -07:00
Phil Wang
5e808f48d1 3d version of navit nested tensor 2024-08-21 07:23:21 -07:00
lucidrains
73199ab486 Nested navit (#325)
add a variant of NaViT using nested tensors
2024-08-20 15:12:29 -07:00
Phil Wang
dfc8df6713 add the u-vit implementation with simple vit + register tokens 2024-08-07 08:45:57 -07:00
lucidrains
9992a615d1 attention re-use in lookup vit should use pre-softmax attention matrix 2024-07-19 19:23:38 -07:00
Phil Wang
4b2c00cb63 when cross attending in look vit, make sure context tokens are normalized 2024-07-19 10:23:12 -07:00
Phil Wang
ec6c48b8ff norm not needed when reusing attention in lookvit 2024-07-19 10:00:03 -07:00
Phil Wang
bd72b58355 add lookup vit, cite, document later 2024-07-19 09:48:58 -07:00
lucidrains
e3256d77cd fix t2t vit having two layernorms, and make final layernorm in distillation wrapper configurable, default to False for vit 2024-06-11 15:12:53 -07:00
lucidrains
90be7233a3 rotary needs to be done with full precision to be safe 2024-05-11 08:04:32 -07:00
Phil Wang
bca88e9039 address https://github.com/lucidrains/vit-pytorch/issues/300 2024-05-02 08:46:39 -07:00
Phil Wang
96f66d2754 address https://github.com/lucidrains/vit-pytorch/issues/306 2024-04-18 09:44:29 -07:00