Paper Citation Record · LEDGER

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers

As of 17 August 2026, this Paper Citation Record lists 75 of 75 outbound references and 2 inbound Pith citation observations for arXiv:2505.21847.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.21847 v2

Coverage vector

measured 75 of 75 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:27:53.028375Z

measured 77 of 77 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T00:24:55.763468Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-14T23:23:15.956970Z

Reference resolution

75 of 75 outbound references displayed

verified exact0
verified fuzzy56
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9f72e720-c5fe-41da-a60a-1f84b4dd89f4 · outbound

This paper cites Token merging: Your vit but faster.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Token merging: Your vit but faster

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:03.324248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e39ff7ba-7241-44d0-8076-3477bb150985 · outbound

This paper cites B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:03.163821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 46c3df74-c7e2-429a-9732-855b8aacf71e · outbound

This paper cites Efficientvit: Multi-scale linear attention for high-resolution dense prediction.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Efficientvit: Multi-scale linear attention for high-resolution dense prediction

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:02.958549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9e66d914-440c-49a4-973b-b5d0fc9adb94 · outbound

This paper cites Emerging properties in self-supervised vision transformers.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Emerging properties in self-supervised vision transformers

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:45.217463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 100ccb8b-8646-472b-a642-03c32402a6d8 · outbound

This paper cites MMDetection: Open MMLab Detection Toolbox and Benchmark.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers MMDetection: Open MMLab Detection Toolbox and Benchmark

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:45.287973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72540cce-a55e-48b5-bd4e-1820d0b6c9d7 · outbound

This paper cites Mobile-former: Bridging mobilenet and transformer.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Mobile-former: Bridging mobilenet and transformer

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:02.852775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f21975cf-6cef-4b0b-99db-7fae7383546c · outbound

This paper cites Improved feature distillation via projector ensemble.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Improved feature distillation via projector ensemble

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:02.708513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 885c1f45-f0dc-4280-9185-2a5d07d83883 · outbound

This paper cites Reproducible scaling laws for contrastive language-image learning.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Reproducible scaling laws for contrastive language-image learning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:02.522153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 141a2893-5439-4802-b290-ca7940c93b5d · outbound

This paper cites MMSegmentation : Openmmlab semantic segmentation toolbox and benchmark.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers MMSegmentation : Openmmlab semantic segmentation toolbox and benchmark

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:02.402922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 208860e0-422c-4ad6-8577-283af8f730df · outbound

This paper cites Flashattention: Fast and memory-efficient exact attention with io-awareness.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Flashattention: Fast and memory-efficient exact attention with io-awareness

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:02.231331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7a7d3319-d2a7-4104-923a-d3cd56bea5ae · outbound

This paper cites P., Caron, M., Geirhos, R., Alabdulmohsin, I., et al.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers P., Caron, M., Geirhos, R., Alabdulmohsin, I., et al

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:02.080751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2a879326-452a-46b1-9d0b-5353a0dc34c8 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Imagenet: A large-scale hierarchical image database

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:45.802701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e39f7842-c5c1-47c9-8bd3-60cc395b71d3 · outbound

This paper cites Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:01.897203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6fc45d22-443e-480c-972a-8c2472add66c · outbound

This paper cites Diverse branch block: Building a convolution as an inception-like unit.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Diverse branch block: Building a convolution as an inception-like unit

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:01.764041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c6d97798-378c-41d3-af77-528396fbcab9 · outbound

This paper cites Repvgg: Making vgg-style convnets great again.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Repvgg: Making vgg-style convnets great again

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:01.636099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 586e35d0-a13d-4d6c-a29c-2faa2603e593 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers An image is worth 16x16 words: Transformers for image recognition at scale

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:46.050615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 107d7008-27b5-4789-88dd-31151b5be27d · outbound

This paper cites A., Jafari, F.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers A., Jafari, F

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:01.464000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7e416a1f-1cb1-42d6-bbe5-5f15dfc842d2 · outbound

This paper cites Levit: a vision transformer in convnet's clothing for faster inference.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Levit: a vision transformer in convnet's clothing for faster inference

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:01.280521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 276eee30-f9b5-47d9-8816-6668376fc167 · outbound

This paper cites Slab: Efficient transformers with simplified linear attention and progressive re-parameterized batch normalization.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Slab: Efficient transformers with simplified linear attention and progressive re-parameterized batch normalization

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:01.107677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e41b8e09-14fe-4d83-9d2c-4905aabd6f7b · outbound

This paper cites M., and Salzmann, M.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers M., and Salzmann, M

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:00.956968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 58314a25-db5f-497b-8631-a5f4851ebb12 · outbound

This paper cites Learning efficient vision transformers via fine-grained manifold distillation.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Learning efficient vision transformers via fine-grained manifold distillation

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:00.819100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 001aa655-7d4d-4920-8ff9-396881e675f7 · outbound

This paper cites Mask r-cnn.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Mask r-cnn

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:00.630452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 80b4a332-4a87-44bd-b65b-bff09d8dd2e1 · outbound

This paper cites and Zhou, J.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers and Zhou, J

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:00.516499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8b6147a6-db25-4f52-8ceb-9c1ff9fdd652 · outbound

This paper cites Gaussian Error Linear Units (GELUs).

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Gaussian Error Linear Units (GELUs)

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:46.959811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8be553f8-3dc9-4720-858c-ad1d51358fc3 · outbound

This paper cites and Szegedy, C.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers and Szegedy, C

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:47.077445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5871e259-b89f-4649-a3d0-58f4943f4c90 · outbound

This paper cites All tokens matter: Token labeling for training better vision transformers.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers All tokens matter: Token labeling for training better vision transformers

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:00.302547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 583a81f1-72c5-4dc6-97f8-18d27408e5b2 · outbound

This paper cites Token fusion: Bridging the gap between token pruning and token merging.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Token fusion: Bridging the gap between token pruning and token merging

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:00.211461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 31521059-d2e2-4c46-ada8-d1204e846bf3 · outbound

This paper cites C., Lo, W.-Y., et al.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers C., Lo, W.-Y., et al

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:47.552353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68faef66-af34-4bd9-acdb-f08dd434f0d5 · outbound

This paper cites Spvit: Enabling faster vision transformers via latency-aware soft token pruning.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Spvit: Enabling faster vision transformers via latency-aware soft token pruning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:28:00.057259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 84aa4104-373a-44a9-adc9-22026226a860 · outbound

This paper cites Peeling the onion: Hierarchical reduction of data redundancy for efficient vision transformer training.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Peeling the onion: Hierarchical reduction of data redundancy for efficient vision transformer training

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:59.834091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 21e8091d-0c9c-4465-aace-e3674f08da32 · outbound

This paper cites Layer Normalization.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Layer Normalization

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:47.977714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fb3272e-e312-49e2-9f84-cb9a7248ed6e · outbound

This paper cites Efficientformer: Vision transformers at mobilenet speed.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Efficientformer: Vision transformers at mobilenet speed

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:59.694685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ad50d6bf-0615-4e30-b282-3cbb5624d3f5 · outbound

This paper cites Evit: Expediting vision transformers via token reorganizations.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Evit: Expediting vision transformers via token reorganizations

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:59.553606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation adf8f4e0-881b-4bc0-ac86-28cfd651d7ec · outbound

This paper cites an unresolved cited work.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:48.327152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c81e5e95-9bde-4820-95af-385fd44a0a0d · outbound

This paper cites Focal loss for dense object detection.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Focal loss for dense object detection

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:59.338012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 93879e39-691f-432c-a73d-8ec681ce0156 · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Swin transformer: Hierarchical vision transformer using shifted windows

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:48.547213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10865df5-a497-4bb3-91fa-978eeb2854ed · outbound

This paper cites Swin transformer v2: Scaling up capacity and resolution.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Swin transformer v2: Scaling up capacity and resolution

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:59.197755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9c7bac21-6077-4886-ac1e-535ae15e0c25 · outbound

This paper cites and Hutter, F.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers and Hutter, F

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:59.022633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ea23cbc8-37b1-4916-820c-11a6e864b438 · outbound

This paper cites Shufflenet v2: Practical guidelines for efficient cnn architecture design.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Shufflenet v2: Practical guidelines for efficient cnn architecture design

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:58.824559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b6617482-8fdb-4917-a0aa-ba957599c1fa · outbound

This paper cites W., Anwer, R.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers W., Anwer, R

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:58.648782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 67f50afa-18df-4970-ad0d-5896990e517d · outbound

This paper cites R., Ranjan, A., Prabhu, A., Rastegari, M., and Tuzel, O.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers R., Ranjan, A., Prabhu, A., Rastegari, M., and Tuzel, O

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:58.396689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 762ebb6e-a574-4ae1-949a-d2d4967fbdf5 · outbound

This paper cites and Rastegari, M.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers and Rastegari, M

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:58.174781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a08e2317-556b-433d-b4ad-0f93a07ecdb3 · outbound

This paper cites Separable Self-attention for Mobile Vision Transformers.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Separable Self-attention for Mobile Vision Transformers

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:49.390514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3ace4f7-c42a-45be-b18d-3aff0346496e · outbound

This paper cites Adavit: Adaptive vision transformers for efficient image recognition.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Adavit: Adaptive vision transformers for efficient image recognition

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:58.058235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ecb10f29-70bd-434d-b93c-a7a2524a82bc · outbound

This paper cites Language models are unsupervised multitask learners.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Language models are unsupervised multitask learners

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:49.576398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c0918c6-d211-48a6-88f9-1737db1fa045 · outbound

This paper cites W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:49.667378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cef82201-63f8-4b26-a072-5b84f5c0fac0 · outbound

This paper cites Dynamicvit: Efficient vision transformers with dynamic token sparsification.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Dynamicvit: Efficient vision transformers with dynamic token sparsification

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:57.855534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 51aa05e4-0e6f-46bd-9a94-95740ae5c9fe · outbound

This paper cites Tokenlearner: Adaptive space-time tokenization for videos.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Tokenlearner: Adaptive space-time tokenization for videos

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:57.668346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7ce0a290-1548-4e63-8aaf-be3e24e30ec1 · outbound

This paper cites Laion-400m: Open dataset of clip-filtered 400 million image-text pairs.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Laion-400m: Open dataset of clip-filtered 400 million image-text pairs

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:57.517771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 44543590-2e41-4d79-af94-b4121503f056 · outbound

This paper cites an unresolved cited work.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:27:57.313663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 47baca31-c13a-46fd-a72e-77c254869a79 · outbound

This paper cites Boosting vanilla lightweight vision transformers via re-parameterization.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Boosting vanilla lightweight vision transformers via re-parameterization

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:57.100436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c7e0cc52-2aeb-4d18-8508-c54c23b93fd2 · outbound

This paper cites Patch slimming for efficient vision transformers.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Patch slimming for efficient vision transformers

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:56.899339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ac2fefad-a2ef-4db3-9f13-51155ba56c63 · outbound

This paper cites O., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Steiner, A., Keysers, D., Uszkoreit, J., et al.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers O., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Steiner, A., Keysers, D., Uszkoreit, J., et al

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:50.487356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54b9af9f-ecc3-4fdf-b9f3-0de8c149e7bd · outbound

This paper cites Training data-efficient image transformers & distillation through attention.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Training data-efficient image transformers & distillation through attention

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:50.589425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56638012-8504-442d-b086-80653ce9b30a · outbound

This paper cites an unresolved cited work.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:27:56.717237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ed1f0c29-1b8d-42d9-a0dd-ba745c2890ef · outbound

This paper cites an unresolved cited work.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:27:56.579863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fad1a498-d8ac-43bc-a93a-65ece657a40d · outbound

This paper cites an unresolved cited work.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Unresolved cited work

Reference 57

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:27:56.457303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 578024ba-7d68-4a1e-885c-6a10efcfbbe3 · outbound

This paper cites Repvit: Revisiting mobile cnn from vit perspective.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Repvit: Revisiting mobile cnn from vit perspective

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:56.374338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c337ad37-fbbc-487e-9174-ae239a0cbacf · outbound

This paper cites Tinyvit: Fast pretraining distillation for small vision transformers.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Tinyvit: Fast pretraining distillation for small vision transformers

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:56.290161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ad20b943-0dc2-46bc-9cd0-d7b74bd3ba8d · outbound

This paper cites Unified perceptual parsing for scene understanding.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Unified perceptual parsing for scene understanding

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:56.190669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 62a26267-f6b7-4464-bd8d-a0228ad2db9a · outbound

This paper cites Lpvit: Low-power semi-structured pruning for vision transformers.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Lpvit: Low-power semi-structured pruning for vision transformers

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:56.084181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fcba0f38-2ad7-4226-8eaf-b09535648e71 · outbound

This paper cites No token left behind: Efficient vision transformer via dynamic token idling.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers No token left behind: Efficient vision transformer via dynamic token idling

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:55.967534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 992f239b-c57b-4534-a46f-5282e8b0f7bf · outbound

This paper cites Gtp-vit: Efficient vision transformers via graph-based token propagation.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Gtp-vit: Efficient vision transformers via graph-based token propagation

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:55.889411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 20cd2ca3-0c6d-45fa-bd68-31c7d96c778b · outbound

This paper cites Evo-vit: Slow-fast token evolution for dynamic vision transformer.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Evo-vit: Slow-fast token evolution for dynamic vision transformer

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:55.787076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7f95e591-944e-453d-88d7-d918a7186e96 · outbound

This paper cites Leveraging batch normalization for vision transformers.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Leveraging batch normalization for vision transformers

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:55.594717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 142e6176-d48b-4ab0-82de-ae8065d4b708 · outbound

This paper cites Large batch optimization for deep learning: Training bert in 76 minutes.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Large batch optimization for deep learning: Training bert in 76 minutes

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:55.477732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b78f0dae-a69b-4b29-8f3e-b797d3f6343a · outbound

This paper cites Width & depth pruning for vision transformers.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Width & depth pruning for vision transformers

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:55.384890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 305e0de4-e5f0-4e51-a0a7-1ac43ff86ced · outbound

This paper cites and Xiang, W.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers and Xiang, W

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:55.179975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3ac8b611-267f-4a40-a11e-ee862bb4c0c6 · outbound

This paper cites Unified visual transformer compression.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Unified visual transformer compression

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:54.959345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8b4d8ded-bdd4-42b6-9a3e-060e100cecf5 · outbound

This paper cites Metaformer is actually what you need for vision.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Metaformer is actually what you need for vision

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:54.749064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 259ca026-1a4e-436c-bc1d-a65ece044b40 · outbound

This paper cites Dense vision transformer compression with few samples.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Dense vision transformer compression with few samples

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:54.412604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 43b9cfba-efb7-41c5-b52c-8bebd30db120 · outbound

This paper cites Rethinking mobile block for efficient attention-based models.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Rethinking mobile block for efficient attention-based models

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:54.076400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5c58d379-8672-4e26-93fd-3cf9774fa3fa · outbound

This paper cites Scene parsing through ade20k dataset.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Scene parsing through ade20k dataset

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:53.796137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3591acdd-0f44-4d43-8dc3-46089805a773 · outbound

This paper cites Structural reparameterization lightweight network for video action recognition.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Structural reparameterization lightweight network for video action recognition

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:53.577698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9ad4d017-621f-4db3-9757-9c69379ab265 · outbound

This paper cites Self-slimmed vision transformer.

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers Self-slimmed vision transformer

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:27:53.313550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation 7959b44c-82ad-4bc6-9a81-2769acef33da · inbound

TRACE: Thermal Recognition Attentive-Framework for CO2 Emissions from Livestock cites this paper.

TRACE: Thermal Recognition Attentive-Framework for CO2 Emissions from Livestock RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:23:15.961256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8ba57d15-e1cb-49b7-97bb-3520375753b0 · inbound

DeVIT: Low-Power Vision Transformer Acceleration Using Delta Computation cites this paper.

DeVIT: Low-Power Vision Transformer Acceleration Using Delta Computation RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T00:24:55.763468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.