Pith. sign in

Paper Citation Record · LEDGER

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing

As of 14 August 2026, this Paper Citation Record lists 94 of 94 outbound references and 0 inbound Pith citation observations for arXiv:2502.00594.

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

pith.paper-citation-record.v1
2502.00594 v1

Coverage vector

measured 94 of 94 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T18:28:48.679484Z

measured 94 of 94 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

94 of 94 outbound references displayed

  • verified exact2
  • verified fuzzy35
  • unresolved56
  • parse uncertain1
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5bbf912a-01ae-4e9d-bd57-95fc243458a6 · outbound

This paper cites Hiervl: Learning hierarchical video- language embeddings.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Hiervl: Learning hierarchical video- language embeddings

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.027458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.027458Z digest=sha256:7c970332aab62e03af74124bda41e528f81b3fa6b3bbc0f77a0e2a1e036b202a

Observation 9949af15-89e3-4f4a-b3af-6d505aaabfab · outbound

This paper cites BEiT: BERT Pre-Training of Image Transformers.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing BEiT: BERT Pre-Training of Image Transformers

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.077510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.077510Z digest=sha256:cb8c4a80ac2b79375bfd3900a698cb86969e49be1105adbfc4d2da6212a3284e

Observation f3c30f5f-6149-4898-bfc4-b0c156b7a00d · outbound

This paper cites Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.206021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.206021Z digest=sha256:1e8207df23ecf20782855a1972cb9ea88d5e194be70cca8327ab7d6b61eb0163

Observation 97edd187-1858-446e-9b68-f4f24fc8d4f8 · outbound

This paper cites Hypermae: Modulating implicit neural representations for mae training.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Hypermae: Modulating implicit neural representations for mae training

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.211633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.211633Z digest=sha256:3cfd0eb968b22c3513cd2814a59df0a4e5b00cfd45c326d8bc630150623221d9

Observation ca69a3bd-37c7-4b68-9b87-5d6042ae02dd · outbound

This paper cites Prefix sums and their applications.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Prefix sums and their applications

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.216579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.216579Z digest=sha256:755b7b27c3f72408e819198eb363218d94345a09dea851149251b670fea82a47

Observation 54ff10f1-55c4-4078-84ea-6e34e694eb1f · outbound

This paper cites Token Merging: Your ViT But Faster.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Token Merging: Your ViT But Faster

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.221551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.221551Z digest=sha256:045a7cb88f15f5f759ae58336dace6c6386801751e6053a4c51390a14b95bb55

Observation efa9f274-ff20-437b-8586-5f06a6265aff · outbound

This paper cites High-performance large-scale image recognition without normalization.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing High-performance large-scale image recognition without normalization

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.227627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.227627Z digest=sha256:a04b72f534b1aa762086f6e63b2ae05a7bc2b69ba83ca53e456e8689fff9fff5

Observation 1d1a7761-c3ff-4c41-8174-c5885e3f8f46 · outbound

This paper cites Jump cell painting dataset: morphological im- pact of 136,000 chemical and genetic perturbations.BioRxiv, pages 2023–03, 2023.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Jump cell painting dataset: morphological im- pact of 136,000 chemical and genetic perturbations.BioRxiv, pages 2023–03, 2023

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.232305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.232305Z digest=sha256:ba15db1a4112f6cababc6802c1bb7548e1a5da2852bb24756b9190e950d6a3e9

Observation 12b4d707-183f-45f4-8c74-18a95e8010e6 · outbound

This paper cites Towards a general-purpose foundation model for computational pathology.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Towards a general-purpose foundation model for computational pathology

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.236234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.236234Z digest=sha256:54b6ce220ce1c635b0fe9632ca000676f35c8afdbad74a9d8b7f9f2428e28eb0

Observation f2d18df4-8a15-4d62-8759-a14a1e8fac3f · outbound

This paper cites Openmmlab semantic seg- mentation toolbox and benchmark, 2020.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Openmmlab semantic seg- mentation toolbox and benchmark, 2020

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.240362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.240362Z digest=sha256:4758fbc3c39f05114943906ca9ec48addecd24ec07b7130ed91e78b9b2540733

Observation 3d490cf1-c8f7-47eb-90a5-b3c89bde4360 · outbound

This paper cites Randaugment: Practical automated data augmen- tation with a reduced search space.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Randaugment: Practical automated data augmen- tation with a reduced search space

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.244496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.244496Z digest=sha256:e0fd3c383650bb975e4cff2a93e16ab8c21ca6f0ae8327b2ae48d7c3f4f1adca

Observation d0efb87a-c2bb-4a91-998d-2266d105f783 · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.248751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.248751Z digest=sha256:539f273b02135a9bd610c3e4e3ee0f09d02cd17db7a6ad494e060dfe2f5505b9

Observation 172ea684-c459-409f-b2d5-d3328d2b95e3 · outbound

This paper cites Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.253626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.253626Z digest=sha256:686a2786fb3148ca385879c9e644b5a1a62d36944820e8dceba231c37d155c62

Observation e7b47e4f-9d2c-4748-959a-22054eaad46b · outbound

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

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Flashattention: Fast and memory-efficient exact at- tention with io-awareness

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.258168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.258168Z digest=sha256:0832d7ff18a212ea3a920323bcb7118e8e2d893c10552e03d7a5b5c91fe51782

Observation 48660da0-bd72-47a3-84cb-2b8a395f45e5 · outbound

This paper cites Vpn++: Rethinking video-pose embeddings for understand- ing activities of daily living.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Vpn++: Rethinking video-pose embeddings for understand- ing activities of daily living

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.262466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.262466Z digest=sha256:bf4783c8edfbc9bc33d1750b161858a536548f6e3e2decd5eb6d93e429925c32

Observation 17fe9fe6-b38e-44e3-80d9-36814e67a872 · outbound

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

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Imagenet: A large-scale hierarchical image database

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.266716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.266716Z digest=sha256:dc81dfe35d45a0b2fd5b256d6c75d4b4b86c5acfae9e7be5053401b53af850c2

Observation 70ee05b0-8083-43ca-9169-8ed344a96e05 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.270938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.270938Z digest=sha256:d2a8c47675711472233d713deda4e638fbe1f874eb8fe90c32aedb004e1b83dd

Observation 9c06baab-2d78-4e7f-bd16-95b9cdfbed3c · outbound

This paper cites Learned representation-guided diffusion models for large-image generation.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Learned representation-guided diffusion models for large-image generation

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.275280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.275280Z digest=sha256:10db46ecdd7568acbc7cd3689a59334dd571831d8333155f8be1bf31dd029a95

Observation b063ed24-cb3b-4042-bbb5-adc8cbbbc8de · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.279120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.279120Z digest=sha256:4f888a0e9d0059e07c3dcfa9bd2ed6d26387c712af8f8621ca9d903340a0d1e7

Observation 92f2adb6-0584-4bc7-992e-f56b1a030687 · outbound

This paper cites Efficiently Modeling Long Sequences with Structured State Spaces.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Efficiently Modeling Long Sequences with Structured State Spaces

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.284095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.284095Z digest=sha256:880f94d618f8e8de9eee1b6b6568c787b967224343e66e8fba4f02834fd349fc

Observation 252e95e9-9f57-4325-942f-f948285a6cf3 · outbound

This paper cites Combining recurrent, convolutional, and continuous-time models with linear state space layers.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Combining recurrent, convolutional, and continuous-time models with linear state space layers

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.288506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.288506Z digest=sha256:b11cfcb4ddfe76417653f4ce282755c6c0e9950897b0374d9ef6a55828f8b883

Observation e8d547f6-8544-434a-bc7f-4b19283ac95a · outbound

This paper cites MambaVision: A Hybrid Mamba-Transformer Vision Backbone.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing MambaVision: A Hybrid Mamba-Transformer Vision Backbone

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.292793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.292793Z digest=sha256:3294a5dd8b7bd41d9a4ad6c94d4515ef739a68d70b3b1506cf96a14bd469bab3

Observation cf9d9376-a084-4029-ba2b-c7041c8873c6 · outbound

This paper cites Mask r-cnn.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Mask r-cnn

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.320508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.320508Z digest=sha256:01309cb077707924433f9f9a65caa73c49eb6932d71192e8587abc05d56bc6bd

Observation 2e6616fc-4a8e-4411-acb1-f2c9ead3feb3 · outbound

This paper cites Masked autoencoders are scalable vision learners.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Masked autoencoders are scalable vision learners

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.755200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:47.357924Z digest=sha256:b2fbbfed81471b1cd8660debd7e4cb98a5595314bdb346b5fc15217ffe58c887

Observation dc1375a1-1019-4157-b9d7-7d69177970f7 · outbound

This paper cites Token Dropping for Efficient BERT Pretraining.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Token Dropping for Efficient BERT Pretraining

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.481444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.481444Z digest=sha256:d3a93752653f77aa251f6ba08072b1da01ba3a518e6b4902deef0ab3a93aa35c

Observation e4b05f06-9583-4134-a255-f0ec0367cd15 · outbound

This paper cites Deep networks with stochastic depth.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Deep networks with stochastic depth

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.742341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:47.604768Z digest=sha256:f5ec1d6c7b69fe0e373022957257a6211e277d1ee5a553c83fa43850b594d2ea

Observation 8fbfdd15-08c5-46b7-b7c2-432a62d6e3a7 · outbound

This paper cites LocalMamba: Visual State Space Model with Windowed Selective Scan.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing LocalMamba: Visual State Space Model with Windowed Selective Scan

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.687930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.687930Z digest=sha256:9c84ae86f8519756f1762f4cdf90230bc3c391176d3865dea644b516e083eb90

Observation 55be8f63-ba7c-474e-93a3-01840838a081 · outbound

This paper cites Attention-based deep multiple instance learning.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Attention-based deep multiple instance learning

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.727992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:47.770585Z digest=sha256:f0d29eec6a11542daee841f1ef52887ccc7eb230ef7d850bbfcc3c5cd69700d2

Observation 90af7577-2010-4dae-b329-7255e9435e9c · outbound

This paper cites Object- centric diffusion for efficient video editing.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Object- centric diffusion for efficient video editing

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.713373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:47.845460Z digest=sha256:a29cf7e7a5df79d3a6fe06cfb50db6050ffa7798eaa2dd903e8b690679e166e1

Observation 0ca161cb-2a31-4368-b9ce-fc702d91c444 · outbound

This paper cites Si-mil: Taming deep mil for self-interpretability in gigapixel histopathology.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Si-mil: Taming deep mil for self-interpretability in gigapixel histopathology

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.699665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:47.850118Z digest=sha256:44d76dcd8de49fc9715c5ea7c9e7e544c8399e89e4be07eb45b26555c5c7d983

Observation eb207fd1-522b-433d-a3c4-4da3bb37feb3 · outbound

This paper cites Vision transformers inference acceleration based on adaptive layer normalization.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Vision transformers inference acceleration based on adaptive layer normalization

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.685429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:47.854197Z digest=sha256:472314579c13febb55b602d1c71426ff680b0ca12fb5282e41e4dbaaeac700e6

Observation 52b4b24a-9282-4863-8fa7-31496ac14be5 · outbound

This paper cites ViTally Consistent: Scaling Biological Representation Learning for Cell Microscopy.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing ViTally Consistent: Scaling Biological Representation Learning for Cell Microscopy

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.858959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.858959Z digest=sha256:5ffbc8a9184a2d40c06e96904188a0f7f29b9c85d0b1b5e652eabd44d91ca24d

Observation bb4e11b9-62b6-41ff-923d-59c9faa70eaf · outbound

This paper cites Videomamba: State space model for efficient video understanding.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Videomamba: State space model for efficient video understanding

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.671858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:47.863752Z digest=sha256:97be76dc48c429b7bab696d3bc29c0b0a694e22be21720a829a9d2fcf96e9e44

Observation 30e19c5a-3904-4601-9d9e-797afdcd7e50 · outbound

This paper cites Exploring plain vision transformer backbones for object de- tection.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Exploring plain vision transformer backbones for object de- tection

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.658326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:47.868392Z digest=sha256:09e47894046afbf69438594f80301779c992d80c6e2d916450520acec08f8da7

Observation e85b7bc2-e70f-4390-900b-f2e2245e06e0 · outbound

This paper cites Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.872619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.872619Z digest=sha256:c7e4a53fb73906830274ea96d2b777b84c3be2461ece1907f74cc12e137e149a

Observation ee700de7-5fba-4293-9e27-74809cc3c35b · outbound

This paper cites Jamba: A Hybrid Transformer-Mamba Language Model.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Jamba: A Hybrid Transformer-Mamba Language Model

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.876559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.876559Z digest=sha256:610e516a8d395eda34fbcea838a7e5829c7e7544dde11a26233d4679f2626658

Observation d19f7cfd-63ad-491c-8bf9-137d9672bfce · outbound

This paper cites Microsoft coco: Common objects in context.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Microsoft coco: Common objects in context

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.880926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.880926Z digest=sha256:e8053456b9318501e990fa147222c29dce0bae334274b2c39aa99e42b3dd923d

Observation 04f8b42e-6bcc-496c-ab62-829b83a80fa2 · outbound

This paper cites MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.885072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.885072Z digest=sha256:d3c3539fb231dc2cdc8644328bb1cfe2597d8bcaea7cfbb72e94c4b68dc628af

Observation c6c6fce7-36c3-4bf9-a647-0536860090b1 · outbound

This paper cites Vmamba: Visual state space model, 2024.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Vmamba: Visual state space model, 2024

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.635675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:47.889120Z digest=sha256:1d5249ba1828df4731779e57e47385c1faa5b5476ad4a5c05f0d8941a88fd7a1

Observation 17a66bfa-ac0e-4496-b97d-42150f36b6b1 · outbound

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

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Swin transformer: Hierarchical vision transformer using shifted windows

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.621712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:47.893304Z digest=sha256:ecc7c476f7025fde909f107af3c38d10631f5a8de4466aeabecf6312d98853e2

Observation d50d473c-ba14-4b20-9645-d6b1ab339f06 · outbound

This paper cites A convnet for the 2020s.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing A convnet for the 2020s

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.897538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.897538Z digest=sha256:1be0e717fb29bc03b14687e37ab2998142acdcb91b1d4461af8c4970f006ad3e

Observation e754c47b-9635-44b9-b063-72f22461b372 · outbound

This paper cites Decoupled Weight Decay Regularization.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Decoupled Weight Decay Regularization

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.902445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.902445Z digest=sha256:ab08070feb8389f81e2c258e8d70e2c2e52de900d11c24fa85f85b2a5e52182f

Observation fcaadab1-e1bc-4f30-9712-e984aaa06989 · outbound

This paper cites SGDR: Stochastic Gradient Descent with Warm Restarts.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing SGDR: Stochastic Gradient Descent with Warm Restarts

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.906753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.906753Z digest=sha256:6dffb781eec5cbc2fad92c2f91b0fc5736e4148569658c53c92f707e2baeed32

Observation ce124bbb-00ac-4f99-b4bf-7bc51b946de2 · outbound

This paper cites Vim4path: Self-supervised vi- sion mamba for histopathology images.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Vim4path: Self-supervised vi- sion mamba for histopathology images

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.600004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:47.912064Z digest=sha256:73c7eb8c7a96bbab398b14c94fc330096f93db13ecfac7e37277f8043c87a152

Observation 2c515de7-6d4b-4e9e-9a9f-aae9157eb3e0 · outbound

This paper cites An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels

Reference 45

Resolution
verified exact
local_arxiv, observed 2026-08-09T18:28:48.927713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:47.916243Z digest=sha256:4108b7fd1368c869f0322cadabdb7afcca0de78afea532958eb2c7febb3cbe8f

Observation 7674ff40-4336-4b96-b777-0747e089fdad · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing DINOv2: Learning Robust Visual Features without Supervision

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.920635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.920635Z digest=sha256:2692410a4d9b9cb8c737bc3010be9eb2e747be0c048fb1c9c9500c133fc2b66c

Observation 7d0a776c-ba42-44fe-8301-06be5fcc2179 · outbound

This paper cites EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:47.924619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:47.924619Z digest=sha256:3799bb0ef5bb9430ef38d56845de7bc95ccec81e7f8fcf43050fdf565636e981

Observation 60f0f329-f820-4457-a0e5-1a6e6f75fbde · outbound

This paper cites Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers

Reference 48

Resolution
verified exact
local_arxiv, observed 2026-08-09T18:28:48.882474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:47.967988Z digest=sha256:089c307f339982c8381c4c2220a7abeee1377787fff48a991e7a116965deb196

Observation a70e1692-5ba0-477e-b8d7-3bc54dbbdb4c · outbound

This paper cites Per- ceptual grouping in contrastive vision-language models.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Per- ceptual grouping in contrastive vision-language models

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.586010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.088516Z digest=sha256:3cc5bfa6f1e1340a791521cde7399ff8e15273866ab1390f0d5c2452e0d006a6

Observation e7a8dcf1-097f-4d6f-8684-b5ec1cb6717c · outbound

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

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Dynamicvit: Efficient vision transformers with dynamic token sparsification

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.163481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.163481Z digest=sha256:b1b92ef0ba4aa79bf57a462891d054b33b49239a32895f317017d295c99672fc

Observation 9c461ef3-cc6e-4b92-8c8a-3db74e1e26ab · outbound

This paper cites Autoregressive Pretraining with Mamba in Vision.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Autoregressive Pretraining with Mamba in Vision

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.358953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.358953Z digest=sha256:c9401d59da4edc732676c1e02431e9e4e3362715daf04bc71a83c869aefc5fcd

Observation 1912697c-1ac6-4bc8-98ed-0c468cee33b2 · outbound

This paper cites Learning to Merge Tokens in Vision Transformers.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Learning to Merge Tokens in Vision Transformers

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.402338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.402338Z digest=sha256:f7641b7b51910145443e8f0853e4ea48b2cd965e837632a06b2767e51bdb3bd8

Observation c39a0be2-f050-43b9-b048-64ff5f04c902 · outbound

This paper cites TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.407448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.407448Z digest=sha256:831b9dc584c6ecb42b9046f91005c8ceb7b9403760c8ffce301fd192a77d1920

Observation 125869ff-5f78-417d-9af6-bbc9383231a2 · outbound

This paper cites GroupMamba: Efficient Group-Based Visual State Space Model.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing GroupMamba: Efficient Group-Based Visual State Space Model

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.412132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.412132Z digest=sha256:900fdb1538999e2dcc6ffa53fde827d5f8bde4d347b36b688b37bd63f4d87581

Observation 6f7e0aaa-3890-4453-82e8-089756588429 · outbound

This paper cites Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.416470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.416470Z digest=sha256:1a955ed9ab54e652def1cb6fdce7680e67bc91331ffe05e16389a4b7f9b18aed

Observation ea069a7f-a15e-43ce-abfb-7f3d17f8f959 · outbound

This paper cites Simplified State Space Layers for Sequence Modeling.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Simplified State Space Layers for Sequence Modeling

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.421026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.421026Z digest=sha256:8b8879fb673c0ac832f7585a10ffe76c7a90edf1f6f824da75095bd0271291d7

Observation 20c497cc-ecff-45ad-8e6c-d991d351b855 · outbound

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

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Training data-efficient image transformers & distillation through at- tention

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.565122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.425538Z digest=sha256:c96399946cca3d9e14cd8086c48afdc149497459903925f1a40fb3240cc069fd

Observation f0c6ea6a-bdb4-423d-a2db-e4c906d18f08 · outbound

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

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Training data-efficient image transformers & distillation through at- tention

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.552685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.429965Z digest=sha256:dd32735c05801d2032eb54bc76f2baffc68f714358f40b373b676c237c100daa

Observation 991bd086-c06d-4792-8654-b728adc15798 · outbound

This paper cites Attention is all you need.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Attention is all you need

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.434842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.434842Z digest=sha256:c71d4dfd28d7db334d48b31e5a4388fc3c908b78cd5472420bfd7e09fdc3b44b

Observation 0ad339ca-3122-4447-8af3-47c93253a370 · outbound

This paper cites Mamba-R: Vision Mamba ALSO Needs Registers.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Mamba-R: Vision Mamba ALSO Needs Registers

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.438869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.438869Z digest=sha256:9390c215a316b5b5b9537d868a81fdeeff7f263977d0229521838773b5b5d87a

Observation 2875a687-c8b4-475a-a1d0-892dae9ef6b2 · outbound

This paper cites Unified perceptual parsing for scene understand- ing.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Unified perceptual parsing for scene understand- ing

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.489438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.489438Z digest=sha256:d5a0facd8af807dff86306bb60719084ebfd0b69328ca1b868dedb2ab76090ee

Observation 5e042235-bfed-423c-8b9e-1ff59bf6d8c8 · outbound

This paper cites A whole-slide foundation model for digital pathology from real-world data.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing A whole-slide foundation model for digital pathology from real-world data

Reference 63

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.523234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.537921Z digest=sha256:56775e6e96ebad38bf1bce6111a0068a7f8736d8179b6b6fc2231985803bfa83

Observation 097394c1-05c2-46b5-b550-ebb2bcf64845 · outbound

This paper cites PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.541812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.541812Z digest=sha256:535131aa75cc407f3839258103e8e47e465120e62fc9ea6bdf2ed330a05987b4

Observation d3a3a8bc-6e17-443d-9c8a-d14953886b67 · outbound

This paper cites Cutmix: Regu- larization strategy to train strong classifiers with localizable features.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Cutmix: Regu- larization strategy to train strong classifiers with localizable features

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.510913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.545751Z digest=sha256:f49ba51aa322b31230f659577acfcfdb4c41f777745e340276cebcf3b0c1add4

Observation db50be05-09c9-4811-abbe-72743fcfd13d · outbound

This paper cites Exploring Token Pruning in Vision State Space Models.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Exploring Token Pruning in Vision State Space Models

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.549618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.549618Z digest=sha256:efc88c2b172028ae60fb144fefbd00d807489294714e9f80a59d28e69f2403b0

Observation 2a9c3ef6-1368-4ee3-a3e7-26beef0231d8 · outbound

This paper cites Rethinking Token Reduction for State Space Models.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Rethinking Token Reduction for State Space Models

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.553647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.553647Z digest=sha256:d04f22a0f369b9f562568c12883b1dd9732404e105280453c8b7936c8acc53d0

Observation c4ab4d19-b994-4c85-914d-a0b7f7315ca9 · outbound

This paper cites mixup: Beyond Empirical Risk Minimization.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing mixup: Beyond Empirical Risk Minimization

Reference 68

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.557693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.557693Z digest=sha256:ac69df8e987d0c8e43d91e18fa121f84aaf6e55a8949b97824817bf5710759b1

Observation 96bd558b-6d88-40ff-8ea6-66a3befa02c5 · outbound

This paper cites Scene parsing through ade20k dataset.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Scene parsing through ade20k dataset

Reference 69

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.562442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.562442Z digest=sha256:968603211e70ae3dbb43a720aa2c71faa00a3cf0d799e51645c55ee4de8e6f2a

Observation 884c7d76-4d70-46bb-a65f-9ada91e8cea6 · outbound

This paper cites Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Reference 70

Resolution
unresolved
no resolver link, observed 2026-08-09T18:28:48.567077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:28:48.567077Z digest=sha256:fc2f5b8b2ee1027926c2186f6b4cfde4f5c380adef3feb7b4668eae5abf400bd

Observation 72815423-f091-4727-9707-331e6092ac0c · outbound

This paper cites We closely followed the pre- training (Table 9), fine-tuning (Table 10), and linear- probing (Table 11) settings from the Masked Autoen- coders [24] codebase.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing We closely followed the pre- training (Table 9), fine-tuning (Table 10), and linear- probing (Table 11) settings from the Masked Autoen- coders [24] codebase

Reference 71

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.488891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.571996Z digest=sha256:5dbbd60fe5ece77e842afd52fabd3092bd7a6bb9ff306aed4b0ac964428b39af

Observation c1b391d4-647e-48ef-952c-b126e0fae6c3 · outbound

This paper cites 2) We applied a scaling factor of 1 − mask ratio (75% masking by default) during fine-tuning and linear probing when pooling tokens before the SSM block.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing 2) We applied a scaling factor of 1 − mask ratio (75% masking by default) during fine-tuning and linear probing when pooling tokens before the SSM block

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.476026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.576472Z digest=sha256:8c4ee0e41746249addac4a1a661e5cbc1eb1f520815b6103a21ee9457bf6d6b4

Observation 8f2b76bc-12f2-4a91-9726-bed24d7e4d83 · outbound

This paper cites mean pool in Fast- MaskVim.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing mean pool in Fast- MaskVim

Reference 73

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.462686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.580967Z digest=sha256:a43ad0882e5389150e6ef3e9d3a2e64d8e14c57e3377c71847c5ba63e621797b

Observation 3677531d-e374-4dd1-a2af-83dfa366a714 · outbound

This paper cites In Table 13, we compare the performance of fine-tuning pre-trained FastMaskVim using alternate layer learning rate decay instead of per-layer decay as in the MAE codebase.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing In Table 13, we compare the performance of fine-tuning pre-trained FastMaskVim using alternate layer learning rate decay instead of per-layer decay as in the MAE codebase

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.449688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.585616Z digest=sha256:f5501bc8c5a31c94a88321a603cdfb922f34f6de7298ea12ccaa789b5d6da5df

Observation cad2c0ed-963b-4fdd-a011-b288a5b87dea · outbound

This paper cites Apply- ing the scaling factor results in an improvement of 0.3% compared to the default mean pooling in fine-tuning without multiplying by the scaling factor.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Apply- ing the scaling factor results in an improvement of 0.3% compared to the default mean pooling in fine-tuning without multiplying by the scaling factor

Reference 75

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.436446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.590168Z digest=sha256:c4e8da3fefde3015a3500be43afa64330477d62375fd1d4bfede897818c8c0fb

Observation d008e347-c57b-4761-90cf-014178075cef · outbound

This paper cites In Table 15, we compare the linear probing performance of Fast- MaskVim with and without the scaling factor (0.25).

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing In Table 15, we compare the linear probing performance of Fast- MaskVim with and without the scaling factor (0.25)

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.423402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.594871Z digest=sha256:329cf155cb039a99dc0bd2fa61d2bcfbada6cf0aa94528b961da463e07b56c2f

Observation f5ae686b-e2e5-4250-86f0-02299296d374 · outbound

This paper cites an unresolved cited work.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Unresolved cited work

Reference 77

Resolution
parse uncertain
raw_fallback, observed 2026-08-09T18:28:49.410087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.599168Z digest=sha256:f9deafb2f3f8f9d7b849122f5bfa3ba902d1865a935c1f75500b482c1cce1bd3

Observation 0066557f-f833-4bb4-aa90-bd5f325eafc7 · outbound

This paper cites In Table 16, we compare the performance of FastVim-S with a class token versus without a class token (default).

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing In Table 16, we compare the performance of FastVim-S with a class token versus without a class token (default)

Reference 78

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.396909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.603670Z digest=sha256:f26cef96407381408a78035d7153fc15dcf2ad3f43fbc7412d9363148ecf1565

Observation 39f5c2a8-6f78-4cfd-8eca-46fb7e5670d3 · outbound

This paper cites In Table 17, we empir- ically demonstrate the performance of FastVim trained with different combinations of input normalization and post-SSM normalization.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing In Table 17, we empir- ically demonstrate the performance of FastVim trained with different combinations of input normalization and post-SSM normalization

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.383837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.608160Z digest=sha256:918d821112faae7b77ebf4a565b0753d7cdca697358adea8f0ca24d7558e55b2

Observation ea6d773f-6309-4c77-a392-188473668fe5 · outbound

This paper cites In Table 18, we explore whether in Fig.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing In Table 18, we explore whether in Fig

Reference 80

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.371044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.612618Z digest=sha256:13267ded551e48e9b3bb13a1a3794fa05b2258709e3f9c0536089e5aee0ee197

Observation f578d65f-0c8d-4930-a71f-173773202692 · outbound

This paper cites We followed the implementation details primarily from ChannelViT [3].

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing We followed the implementation details primarily from ChannelViT [3]

Reference 81

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.358146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.616956Z digest=sha256:d65c359f2cc111900dac8325d6cf7664052194316f7927fb9fae197722ea258d

Observation 3f58022d-ad0b-4c3c-83e0-9e36a20bc279 · outbound

This paper cites Channel- First with and without sorted HCS.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Channel- First with and without sorted HCS

Reference 82

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.346395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.621528Z digest=sha256:56bb9bc947a137c7397b4c96ac2cbd1784c1cc600d5c3b88a4c918caeddaf687

Observation c8d43edc-e6aa-41b9-9d7a-bf12f540d892 · outbound

This paper cites We then explore the effect of different pooling methods, such as max pooling [49] and attention pooling [28], as detailed in Table 20 on the JUMP-CP dataset.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing We then explore the effect of different pooling methods, such as max pooling [49] and attention pooling [28], as detailed in Table 20 on the JUMP-CP dataset

Reference 83

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.334222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.625803Z digest=sha256:bef145a699161051067bbbf530e494b9c63a4d0f39601c9ab597dd3d6aed91f7

Observation dad8146f-16ab-4f56-bb46-027a6f2d510c · outbound

This paper cites Now, we preliminarily explore pooling along two dimen- Table 20.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Now, we preliminarily explore pooling along two dimen- Table 20

Reference 84

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.322383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.630185Z digest=sha256:696a070def8dfd3a491e64cd47ef75cf170c5eb3495d14de0ce127b1e331b3f7

Observation bee2db5a-7fec-4ea4-a149-9b62938f443a · outbound

This paper cites an unresolved cited work.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Unresolved cited work

Reference 85

Resolution
unresolved
raw_fallback, observed 2026-08-09T18:28:49.309789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.634655Z digest=sha256:6ec370c8c70e0fdde4366001eb690d2ebb5b3e1aae1cddb05ba090e6c83ee433

Observation 8d1121a7-1742-4580-adb0-a6c5775f1b32 · outbound

This paper cites an unresolved cited work.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Unresolved cited work

Reference 86

Resolution
unresolved
raw_fallback, observed 2026-08-09T18:28:49.296577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.639100Z digest=sha256:8d6bd8d58d357bf43760592b8f33a19276926ed502598b5b34bc120563c5206c

Observation 90da51ca-3337-4716-b396-7567125093c1 · outbound

This paper cites an unresolved cited work.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Unresolved cited work

Reference 87

Resolution
unresolved
raw_fallback, observed 2026-08-09T18:28:49.283163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.643509Z digest=sha256:c5bce27a6ce5b22e1d6e36ae7092fabcd27550893db587d19a927cd958b2ab5f

Observation cc8fc2a1-58e6-4821-8667-8a2fd380a361 · outbound

This paper cites an unresolved cited work.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Unresolved cited work

Reference 88

Resolution
unresolved
raw_fallback, observed 2026-08-09T18:28:49.269793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.647976Z digest=sha256:7d8bfec312dd14f545b5053f7bcba7c62afb14db1440310cdaca8fcc89b3bca3

Observation b675a518-fb63-429c-a27c-fe1de2209a42 · outbound

This paper cites an unresolved cited work.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Unresolved cited work

Reference 89

Resolution
unresolved
raw_fallback, observed 2026-08-09T18:28:49.256152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.652421Z digest=sha256:f0048d81f3da2405cd8fc5c43a0a05be4294518b692c5f335989d6e6f32a231e

Observation 68b26e95-cc81-4cbd-b083-05aa12fc2641 · outbound

This paper cites In Table 22, we demonstrate the throughput improvement in FastChannelVim compared to ChannelVim.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing In Table 22, we demonstrate the throughput improvement in FastChannelVim compared to ChannelVim

Reference 90

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.242420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.656847Z digest=sha256:7ae8a04d4df9544779d240a1e935369fe1bdcd17be12719ab00731a9ee51350e

Observation 505fef0c-ccf5-4083-b4f1-83bf717a8875 · outbound

This paper cites Here, we calcu- late the processing time for Forward SSM + Backward SSM in only one block (see Fig.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Here, we calcu- late the processing time for Forward SSM + Backward SSM in only one block (see Fig

Reference 91

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.227388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.661339Z digest=sha256:1d31721f4abbb8aa500695a98acaf5cb4ba2f1067a2d736444c31c8c3f9356cd

Observation b83603b0-749f-4159-8994-013e7e0e667d · outbound

This paper cites We employed the AdamW optimizer with a weight decay of 0.01.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing We employed the AdamW optimizer with a weight decay of 0.01

Reference 92

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.213392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.665879Z digest=sha256:6fc3eb283542b2dd68243f0e6e24628066c61edeb41c0f43f036bba844b11ef6

Observation 23b235ad-6ca2-48f2-bd7d-6068e50fbb1c · outbound

This paper cites We employed the AdamW optimizer with a weight decay of 0.05, with a total batch size of 64.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing We employed the AdamW optimizer with a weight decay of 0.05, with a total batch size of 64

Reference 93

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.199418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.670445Z digest=sha256:21d924a758da142b92c264fd3ca1ff2469b06b8e565c09c359c2e919bf81c1b5

Observation 9e16d200-e858-4ce7-9c97-469ad51776c9 · outbound

This paper cites 2), we apply mean pooling to the tokens before performing the SSM scan.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing 2), we apply mean pooling to the tokens before performing the SSM scan

Reference 94

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.185072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.674860Z digest=sha256:014b1d44892b7b2fee568a4d842a275a1384e9bd53618ec460894f616d972b45

Observation 63e740a5-14e1-4335-82eb-dd8fe6848f19 · outbound

This paper cites Model configurations for FastVim Model Layers Embedding dim.

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing Model configurations for FastVim Model Layers Embedding dim

Reference 95

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:28:49.170789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-08-09T18:28:48.679484Z digest=sha256:40bcc624a9dee9c2c5503d130feb6d85df9b25dda6111dec733849970982c7b5

Pith citing papers

No inbound Pith citation observations are available.