HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers | Paper Citation Record

Observation 89f35159-23f7-42ae-bf3b-8f706438b4d1 · outbound

This paper cites 2017 Robotic Instrument Segmentation Challenge.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers 2017 Robotic Instrument Segmentation Challenge

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:23.426911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d25db0cf-c7e0-47eb-8cac-c14828fcb345 · outbound

This paper cites Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer.JAMA, 318(22):2199–2210, 2017.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer.JAMA, 318(22):2199–2210, 2017

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:27.919585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e92f340b-2215-4726-af84-dbf9b68878ef · outbound

This paper cites Longformer: The Long-Document Transformer.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Longformer: The Long-Document Transformer

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:23.476743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05b0eada-8035-47d6-963f-af6af1179fc3 · outbound

This paper cites Efficientvit: Lightweight multi-scale attention for high-resolution dense prediction.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Efficientvit: Lightweight multi-scale attention for high-resolution dense prediction

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:23.515924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1959458f-d32e-4efb-a929-ae4ef071bab7 · outbound

This paper cites Swin-UNet: Unet-like pure transformer for medical image segmenta- tion.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Swin-UNet: Unet-like pure transformer for medical image segmenta- tion

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:27.906691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 732a3df9-a568-49f0-8812-e7d659a01c40 · outbound

This paper cites TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:23.564890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac0a4fc5-f991-4abe-b6ca-6c41a398acc3 · outbound

This paper cites Rethinking Atrous Convolution for Semantic Image Segmentation.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Rethinking Atrous Convolution for Semantic Image Segmentation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:23.588209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d8eb94d-b7ea-4543-b1b1-de0ce0e3acb2 · outbound

This paper cites an unresolved cited work.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-11T00:33:27.899206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d50f9334-ca06-49d8-8200-1ecfaa56cbae · outbound

This paper cites Recursive Generalization Transformer for Image Super-Resolution.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Recursive Generalization Transformer for Image Super-Resolution

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:23.634112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09f27756-8a4f-49ce-a322-670b4a9e1ee1 · outbound

This paper cites Generating Long Sequences with Sparse Transformers.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Generating Long Sequences with Sparse Transformers

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:23.665860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a353df19-b9f8-453e-9eff-a538de9296b5 · outbound

This paper cites Choromanski, Valerii Likhosherstov, David Dohan, Xingyou Song, Georgiana-Andreea Gane, Tamas Sarlos, Peter Hawkins, Jared Q.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Choromanski, Valerii Likhosherstov, David Dohan, Xingyou Song, Georgiana-Andreea Gane, Tamas Sarlos, Peter Hawkins, Jared Q

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:27.884480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation aa2fd4ff-46ee-414d-b956-36b235c9f394 · outbound

This paper cites The cityscapes dataset for semantic urban scene understanding.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers The cityscapes dataset for semantic urban scene understanding

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:27.841576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a44e2a9e-4e66-4dc9-be96-a881aeb45b7c · outbound

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

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Imagenet: A large-scale hierarchical image database

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:23.727442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac4ebd42-624b-41f5-ac4a-4173848143f2 · outbound

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

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:23.736858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70d7537c-98d6-409b-aec3-b14af91f5783 · outbound

This paper cites Segnext: Rethinking convolutional attention design for semantic segmen- tation.Advances in neural information processing systems, 35:1140–1156, 2022.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Segnext: Rethinking convolutional attention design for semantic segmen- tation.Advances in neural information processing systems, 35:1140–1156, 2022

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:27.771086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 69dc6777-d514-4aee-93c7-4731c4aecb6f · outbound

This paper cites Re- conFormer: Accelerated MRI reconstruction using recurrent transformer.IEEE Trans.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Re- conFormer: Accelerated MRI reconstruction using recurrent transformer.IEEE Trans

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:26.579575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d40d8011-7c68-4e12-b17a-38d8e218588f · outbound

This paper cites FasterViT: Fast Vision Transformers with Hierarchical Attention.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers FasterViT: Fast Vision Transformers with Hierarchical Attention

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:23.807785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c82352e0-1d89-4ced-ad06-b9205c8bab5c · outbound

This paper cites Trans- formers are rnns: Fast autoregressive transformers with linear attention.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Trans- formers are rnns: Fast autoregressive transformers with linear attention

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:26.571984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9edf679e-ca4f-4084-9b29-ba5bfff07de4 · outbound

This paper cites Reformer: The Efficient Transformer.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Reformer: The Efficient Transformer

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:23.864382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a28f2204-bb89-41f4-854d-b94d0658ca96 · outbound

This paper cites Langerak, and Arno Klein.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Langerak, and Arno Klein

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:26.562709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 75cd9b47-35cb-4417-8676-4a4ce304c074 · outbound

This paper cites Efficientformer: Vision transformers at mobilenet speed.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Efficientformer: Vision transformers at mobilenet speed

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:26.541821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 76d1a670-c6b9-4337-8fa1-7edbb474bf85 · outbound

This paper cites Not all patches are what you need: Expediting vision transformers via token reorgani- zations.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Not all patches are what you need: Expediting vision transformers via token reorgani- zations

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:26.531885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9d953b55-9651-43ee-9f89-cc80f3b425cd · outbound

This paper cites Tinyserve: Query-aware cache selection for efficient llm serving.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Tinyserve: Query-aware cache selection for efficient llm serving

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:26.507248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 612ab843-403f-4337-b9fb-c28049379792 · outbound

This paper cites PiKV: KV Cache Management System for Mixture of Experts.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers PiKV: KV Cache Management System for Mixture of Experts

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-11T00:33:25.370855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9313d929-4336-4600-ace1-3913ed9502fc · outbound

This paper cites Fast- cache: Fast caching for diffusion transformer through learnable linear approximation.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Fast- cache: Fast caching for diffusion transformer through learnable linear approximation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:24.088427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f81fcd4-ea72-487d-964e-4d08c59f5bca · outbound

This paper cites To keep or not to keep: Learning KV cache retention in disaggregated LLM serving systems.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers To keep or not to keep: Learning KV cache retention in disaggregated LLM serving systems

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:26.488458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a8c9af71-2a91-4510-b6d2-522cd0bafb2e · outbound

This paper cites AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-11T00:33:25.250526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 24d3e294-1f88-48c1-8a3d-9356eb9e26f9 · outbound

This paper cites Mka: Memory-keyed attention for efficient long-context reasoning.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Mka: Memory-keyed attention for efficient long-context reasoning

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:26.426242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1d5ceffc-c3f1-4a12-93dd-39fa419be2f4 · outbound

This paper cites Accelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Caching.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Accelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Caching

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-11T00:33:25.198855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e91c1b11-b66d-49e5-8f0b-fba13f1f3647 · outbound

This paper cites VMamba: Visual State Space Model.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers VMamba: Visual State Space Model

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:24.235308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6818d1f8-7886-4f46-a01c-f82676cd152a · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted win- dows.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Swin transformer: Hierarchical vision transformer using shifted win- dows

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:24.264680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08d083f6-b882-464c-99aa-3f9e821d10fa · outbound

This paper cites A convnet for the 2020s.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers A convnet for the 2020s

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:24.291115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b3681f4-768a-4eff-a38e-7805f832f2c8 · outbound

This paper cites MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:26.382228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f901de8e-292e-4898-9324-4467406690c0 · outbound

This paper cites Adavit: Adaptive vision transformers for efficient image recogni- tion.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Adavit: Adaptive vision transformers for efficient image recogni- tion

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:26.308561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 484a9d59-4de3-41fb-a3fb-e54043cfed2b · outbound

This paper cites Online normalizer calculation for softmax.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Online normalizer calculation for softmax

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:24.366577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9216f8d3-bb74-42ac-b122-98a6f79db7a7 · outbound

This paper cites Random Feature Attention.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Random Feature Attention

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:24.407493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eb55a57-09f8-4c3a-ba3d-be0142f81c63 · outbound

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

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Dynamicvit: Efficient vision transformers with dynamic token sparsification

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:26.159708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a91c10eb-b7ba-486b-bf02-8d166847710d · outbound

This paper cites an unresolved cited work.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-11T00:33:26.103613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1cf25b3c-5f51-4c32-920d-42cd13dc04be · outbound

This paper cites Efficient attention: Attention with linear complexities.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Efficient attention: Attention with linear complexities

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:26.095307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9ee6cdaf-b707-4c53-96e5-d064ea85992d · outbound

This paper cites Ntire 2017 challenge on single image super-resolution: Methods and results.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Ntire 2017 challenge on single image super-resolution: Methods and results

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:26.055128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 74a67419-fd6f-47e1-8723-70647252a277 · outbound

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

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Training data-efficient image transformers & distillation through attention

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:26.031269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6b7a07b3-ecb4-4e0b-a37f-c19626663700 · outbound

This paper cites Med- ical transformer: Gated axial-attention for medical image segmentation.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Med- ical transformer: Gated axial-attention for medical image segmentation

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:25.992578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9273aa99-fe26-4af3-9610-a38c43925136 · outbound

This paper cites HAT: Hardware-aware transformers for efficient natural language process- ing.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers HAT: Hardware-aware transformers for efficient natural language process- ing

Reference 43

Resolution: verified exact; doi, observed 2026-08-11T00:33:24.972418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 900fefaf-19b1-4f41-8f82-0f2e47c1f1a5 · outbound

This paper cites SpAtten: Efficient sparse attention ar- chitecture with cascade token and head pruning.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers SpAtten: Efficient sparse attention ar- chitecture with cascade token and head pruning

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:25.959746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 832e0bbb-235f-40ed-99f6-95c6617d3fca · outbound

This paper cites Linformer: Self-Attention with Linear Complexity.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Linformer: Self-Attention with Linear Complexity

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:24.614529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05dd2c18-75e1-491d-bea4-54283f6fa649 · outbound

This paper cites Pyramid vision transformer: A versatile backbone for dense prediction without convolutions.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Pyramid vision transformer: A versatile backbone for dense prediction without convolutions

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:24.645635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90fc97b9-d64d-428e-810c-98aa245a3acb · outbound

This paper cites Segformer: Simple and efficient design for semantic segmentation with trans- formers.Advances in neural information processing systems, 34:12077–12090, 2021.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Segformer: Simple and efficient design for semantic segmentation with trans- formers.Advances in neural information processing systems, 34:12077–12090, 2021

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:25.915274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7fcf4dc4-0b88-4222-9d9f-acd7cb7cb3a1 · outbound

This paper cites Nyströmformer: A nyström-based algorithm for approximat- ing self-attention.Proceedings of the AAAI conference on artificial intelligence, 35 (16):14138–14148, 2021.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Nyströmformer: A nyström-based algorithm for approximat- ing self-attention.Proceedings of the AAAI conference on artificial intelligence, 35 (16):14138–14148, 2021

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:25.852502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c9a5b3f2-4068-4c5b-8efa-f114238b4ba3 · outbound

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

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Evo-vit: Slow-fast token evolution for dynamic vision transformer

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:25.798336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b24f8e56-3d78-4239-aaba-74bb01e8c37a · outbound

This paper cites A-vit: Adaptive tokens for efficient vision transformer.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers A-vit: Adaptive tokens for efficient vision transformer

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:25.724579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 488f1994-7aa7-4478-8204-4689cf6590f4 · outbound

This paper cites Coprimeeeg: Crt-guided dual-branch reconstruction from co-prime sub-nyquist eeg.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Coprimeeeg: Crt-guided dual-branch reconstruction from co-prime sub-nyquist eeg

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:25.648303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7fd04453-0109-4f79-aafe-759597061a67 · outbound

This paper cites Big bird: Transformers for longer sequences.Advances in neural information process- ing systems, 33:17283–17297, 2020.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Big bird: Transformers for longer sequences.Advances in neural information process- ing systems, 33:17283–17297, 2020

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:25.585576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8aa06234-651b-457d-bf11-5f6fd5ce144a · outbound

This paper cites Restormer: Efficient transformer for high-resolution image restoration.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Restormer: Efficient transformer for high-resolution image restoration

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:24.828336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db41cb7a-74e5-4231-8173-84028473a424 · outbound

This paper cites Pyramid scene parsing network.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Pyramid scene parsing network

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:24.850748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4851a68-2360-493f-9ea6-8ec02be81674 · outbound

This paper cites PSANet: Point-wise spatial attention network for scene parsing.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers PSANet: Point-wise spatial attention network for scene parsing

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:25.509925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 705c0464-7b82-4334-9bce-fb43511d2ab1 · outbound

This paper cites Scene parsing through ade20k dataset.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Scene parsing through ade20k dataset

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:25.482325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 115300b9-5169-499e-9cc4-65634dfde920 · outbound

This paper cites Biformer: Vision transformer with bi-level routing attention.Proceedings of the IEEE/CVF con- ference on computer vision and pattern recognition, pages 10323–10333, 2023.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers Biformer: Vision transformer with bi-level routing attention.Proceedings of the IEEE/CVF con- ference on computer vision and pattern recognition, pages 10323–10333, 2023

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T00:33:25.473705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b4abb9bf-f6d5-4ba3-b185-a71010cd11c0 · outbound

This paper cites URLhttps://doi.org/10.

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers URLhttps://doi.org/10

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-11T00:33:24.599288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers