EMOv2: Pushing 5M Vision Model Frontier | Paper Citation Record

Observation 8e84cf61-7c8c-40c1-a18e-8b065172ec78 · outbound

This paper cites Rethinking vision transformers for mobilenet size and speed,.

EMOv2: Pushing 5M Vision Model Frontier Rethinking vision transformers for mobilenet size and speed,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.654918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73934214-ad02-419b-9ea6-953354eb7b0d · outbound

This paper cites Edgenext: efficiently amalgamated cnn-transformer architecture for mobile vision applications,.

EMOv2: Pushing 5M Vision Model Frontier Edgenext: efficiently amalgamated cnn-transformer architecture for mobile vision applications,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.661571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 411ff54c-7915-4fda-8451-f04aa6e20fc8 · outbound

This paper cites TinySAM: Pushing the Envelope for Efficient Segment Anything Model.

EMOv2: Pushing 5M Vision Model Frontier TinySAM: Pushing the Envelope for Efficient Segment Anything Model

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.666958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e58ad30-8e85-455e-8d61-0653dc7ac474 · outbound

This paper cites EdgeSAM: Prompt-In-the-Loop Distillation for SAM.

EMOv2: Pushing 5M Vision Model Frontier EdgeSAM: Prompt-In-the-Loop Distillation for SAM

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.673378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4626c645-2d66-4f12-8eb1-3f575496e272 · outbound

This paper cites RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything.

EMOv2: Pushing 5M Vision Model Frontier RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-11T19:33:09.930388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f4a81fa6-25d5-402f-a38b-0421641e9c6a · outbound

This paper cites Semantic flow for fast and accurate scene parsing,.

EMOv2: Pushing 5M Vision Model Frontier Semantic flow for fast and accurate scene parsing,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.684783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be0314c3-7ad2-4c6c-bef4-ff62ad9c4b8f · outbound

This paper cites RTMO: Towards high-performance one-stage real-time multi-person pose estimation,.

EMOv2: Pushing 5M Vision Model Frontier RTMO: Towards high-performance one-stage real-time multi-person pose estimation,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.691436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7ad3ff9-e6ec-404f-a405-d69773bf8967 · outbound

This paper cites MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.

EMOv2: Pushing 5M Vision Model Frontier MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.696530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3b56807-9f23-4947-a900-903807f3d1ea · outbound

This paper cites Mobilenetv2: Inverted residuals and linear bottlenecks,.

EMOv2: Pushing 5M Vision Model Frontier Mobilenetv2: Inverted residuals and linear bottlenecks,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.701456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ffe787f-beb9-42a5-a433-f44eaf2ffbdf · outbound

This paper cites Searching for mobilenetv3,.

EMOv2: Pushing 5M Vision Model Frontier Searching for mobilenetv3,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.706363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c715fc29-f051-455c-a572-bde4120ccf4c · outbound

This paper cites Ghostnet: More features from cheap operations,.

EMOv2: Pushing 5M Vision Model Frontier Ghostnet: More features from cheap operations,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.711971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ac428f7-739d-4c7f-8c21-da27321d5c9d · outbound

This paper cites Efficientnet: Rethinking model scaling for convolu- tional neural networks,.

EMOv2: Pushing 5M Vision Model Frontier Efficientnet: Rethinking model scaling for convolu- tional neural networks,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.717647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abbfe0d3-ec84-4b43-bed4-8b2cb3d7107b · outbound

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

EMOv2: Pushing 5M Vision Model Frontier Rethinking mobile block for efficient attention- based models,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.723263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ab1bf7e-2601-4303-8c09-96d2f1a3c2f2 · outbound

This paper cites Separable self-attention for mobile vision transformers,.

EMOv2: Pushing 5M Vision Model Frontier Separable self-attention for mobile vision transformers,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.727666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0990dfa0-8335-417b-9287-aff0f9e29755 · outbound

This paper cites The need for speed in ai,.

EMOv2: Pushing 5M Vision Model Frontier The need for speed in ai,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.731853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36848301-9378-4db7-abfe-9730811e6041 · outbound

This paper cites Morgan Kaufmann, 1994.

EMOv2: Pushing 5M Vision Model Frontier Morgan Kaufmann, 1994

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.736200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70f6f7a5-ae5c-43b7-9ad6-fb4e2ae1207a · outbound

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

EMOv2: Pushing 5M Vision Model Frontier Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.741940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e00b2a56-e6d6-4f7d-aa3b-3f0cdebdf639 · outbound

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

EMOv2: Pushing 5M Vision Model Frontier An image is worth 16x16 words: Transformers for image recognition at scale,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.747913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3158886e-6a80-4b9c-b34d-ba2450d64983 · outbound

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

EMOv2: Pushing 5M Vision Model Frontier Pyramid vision transformer: A versatile backbone for dense prediction without convolutions,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.752576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4a2ca76-9dc6-49f7-b599-2c84ec0deab5 · outbound

This paper cites Pvt v2: Improved baselines with pyramid vision transformer,.

EMOv2: Pushing 5M Vision Model Frontier Pvt v2: Improved baselines with pyramid vision transformer,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.757577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8be071b-6bba-4e0e-a390-252fdd28640a · outbound

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

EMOv2: Pushing 5M Vision Model Frontier Swin transformer: Hierarchical vision transformer using shifted windows,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.761844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acd20323-67f1-4521-8e2b-b175589b0b70 · outbound

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

EMOv2: Pushing 5M Vision Model Frontier Swin transformer v2: Scaling up capacity and resolution,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.766281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f755c53c-fc13-49d4-8fa3-ed7c03243643 · outbound

This paper cites Analogous to evolutionary algorithm: Designing a unified sequence model,.

EMOv2: Pushing 5M Vision Model Frontier Analogous to evolutionary algorithm: Designing a unified sequence model,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.770568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff6ec03f-1536-42c6-9abe-77e2a5d307c0 · outbound

This paper cites Eatformer: improving vision transformer inspired by evolutionary algorithm,.

EMOv2: Pushing 5M Vision Model Frontier Eatformer: improving vision transformer inspired by evolutionary algorithm,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.774881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f65a7298-ff7b-40a5-8b96-24dabe04e7b0 · outbound

This paper cites Transformer-based visual segmentation: A survey,.

EMOv2: Pushing 5M Vision Model Frontier Transformer-based visual segmentation: A survey,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.779095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d98f55a-1abc-47b8-be2e-842544e36605 · outbound

This paper cites Involution: Inverting the inherence of convolution for visual recognition,.

EMOv2: Pushing 5M Vision Model Frontier Involution: Inverting the inherence of convolution for visual recognition,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.784290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd42233a-f80b-49f1-b593-17445f5468d1 · outbound

This paper cites Reformer: The efficient transformer,.

EMOv2: Pushing 5M Vision Model Frontier Reformer: The efficient transformer,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.789159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34e7f7c7-731d-4326-ba20-9dff7667a4df · outbound

This paper cites Rethinking attention with performers,.

EMOv2: Pushing 5M Vision Model Frontier Rethinking attention with performers,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.793762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27bd2904-f201-4682-921f-3896a3aad547 · outbound

This paper cites Cvt: Introducing convolutions to vision transformers,.

EMOv2: Pushing 5M Vision Model Frontier Cvt: Introducing convolutions to vision transformers,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.799084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5eb6ccc-8c74-492c-b035-4c28345ed52e · outbound

This paper cites Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios.

EMOv2: Pushing 5M Vision Model Frontier Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.804743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afe24a19-3941-4870-95cd-d62da4f76f0f · outbound

This paper cites Delight: Deep and light-weight transformer,.

EMOv2: Pushing 5M Vision Model Frontier Delight: Deep and light-weight transformer,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.810047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 992e5d3b-2184-4fd1-94de-0a93dfc5beb2 · outbound

This paper cites MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features.

EMOv2: Pushing 5M Vision Model Frontier MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.814498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e520eb0b-6d36-4c8f-86c3-bcb393c5ea46 · outbound

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

EMOv2: Pushing 5M Vision Model Frontier Mobile-former: Bridging mobilenet and transformer,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.820780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03f0c357-36fa-4f03-ada7-af4d35b2fa63 · outbound

This paper cites Efficientformer: Vision transformers at mobilenet speed,.

EMOv2: Pushing 5M Vision Model Frontier Efficientformer: Vision transformers at mobilenet speed,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.827247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58c51e32-7a46-4087-80c5-8b3e216cc763 · outbound

This paper cites Attention is all you need,.

EMOv2: Pushing 5M Vision Model Frontier Attention is all you need,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.833265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 392d599a-51f6-4ae9-b3fa-f39d0fa02526 · outbound

This paper cites Focal loss for dense object detection,.

EMOv2: Pushing 5M Vision Model Frontier Focal loss for dense object detection,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.839656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55a4544f-fa93-43c1-8266-15eec9444fc9 · outbound

This paper cites SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size.

EMOv2: Pushing 5M Vision Model Frontier SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.845432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a1d4f5b-bc96-480f-aa03-d4e603c7c3ad · outbound

This paper cites Rethinking the inception architecture for computer vision,.

EMOv2: Pushing 5M Vision Model Frontier Rethinking the inception architecture for computer vision,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.851325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 486bcff3-5a35-4f06-9161-707ae2c96535 · outbound

This paper cites Sfnet: Faster, accurate, and domain agnostic semantic segmentation via semantic flow,.

EMOv2: Pushing 5M Vision Model Frontier Sfnet: Faster, accurate, and domain agnostic semantic segmentation via semantic flow,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.858186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ff64f92-79ed-4bd1-8890-cc59de2db743 · outbound

This paper cites RepViT: Revisiting Mobile CNN From ViT Perspective.

EMOv2: Pushing 5M Vision Model Frontier RepViT: Revisiting Mobile CNN From ViT Perspective

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.863249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a640a60-d755-402b-9f9c-619af5ab2cac · outbound

This paper cites GhostNetV3: Exploring the Training Strategies for Compact Models.

EMOv2: Pushing 5M Vision Model Frontier GhostNetV3: Exploring the Training Strategies for Compact Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.868843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e6f82c6-2a2c-41ae-ad0e-3b70f686dfae · outbound

This paper cites MobileNetV4 -- Universal Models for the Mobile Ecosystem.

EMOv2: Pushing 5M Vision Model Frontier MobileNetV4 -- Universal Models for the Mobile Ecosystem

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.873961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c377e4c1-abe1-44de-8b56-044a72afed09 · outbound

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

EMOv2: Pushing 5M Vision Model Frontier Training data-efficient image transformers & distillation through attention,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.879036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1955f161-b3e5-4173-9c88-c9e2ac5f9627 · outbound

This paper cites Deep residual learning for image recognition,.

EMOv2: Pushing 5M Vision Model Frontier Deep residual learning for image recognition,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.883318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32ea3e88-d033-46fa-975a-85b102a9e5fb · outbound

This paper cites Visual Attention Methods in Deep Learning: An In-Depth Survey.

EMOv2: Pushing 5M Vision Model Frontier Visual Attention Methods in Deep Learning: An In-Depth Survey

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.887397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 743ef52e-aec7-42fd-ac69-d156a532d765 · outbound

This paper cites Recent Advances in Vision Transformer: A Survey and Outlook of Recent Work.

EMOv2: Pushing 5M Vision Model Frontier Recent Advances in Vision Transformer: A Survey and Outlook of Recent Work

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.892005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbc42525-401c-4862-83c6-7dea658736a9 · outbound

This paper cites Incorporating convolution designs into visual transformers,.

EMOv2: Pushing 5M Vision Model Frontier Incorporating convolution designs into visual transformers,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.896971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f21b8c0-dc0a-4499-9607-3048338d7061 · outbound

This paper cites Conditional positional encodings for vision transformers,.

EMOv2: Pushing 5M Vision Model Frontier Conditional positional encodings for vision transformers,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.901253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0aaec46-3205-4273-81c5-603398431aca · outbound

This paper cites Uniformer: Unified transformer for efficient spatial-temporal representation learning,.

EMOv2: Pushing 5M Vision Model Frontier Uniformer: Unified transformer for efficient spatial-temporal representation learning,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.905345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efbbadd6-3bd9-46c9-8526-31080f65c0c0 · outbound

This paper cites Moganet: Multi-order gated aggregation network,.

EMOv2: Pushing 5M Vision Model Frontier Moganet: Multi-order gated aggregation network,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:11.116756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1397ff16-5ff2-4ee2-a7c3-2b64b661da38 · outbound

This paper cites Shvit: Single-head vision transformer with memory efficient macro design,.

EMOv2: Pushing 5M Vision Model Frontier Shvit: Single-head vision transformer with memory efficient macro design,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:11.096081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 47747279-bde4-4292-a45e-1dcd761b2e6d · outbound

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

EMOv2: Pushing 5M Vision Model Frontier Metaformer is actually what you need for vision,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:11.076066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 43aac6a7-d236-42b7-b7e6-7525849696e0 · outbound

This paper cites LightViT: Towards Light-Weight Convolution-Free Vision Transformers.

EMOv2: Pushing 5M Vision Model Frontier LightViT: Towards Light-Weight Convolution-Free Vision Transformers

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.925512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27f40d56-3242-48a8-8afc-9e3be376ecb0 · outbound

This paper cites Rest: An efficient transformer for visual recognition,.

EMOv2: Pushing 5M Vision Model Frontier Rest: An efficient transformer for visual recognition,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:11.048115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c917cc1b-f326-4ddd-928b-77f635b36e8b · outbound

This paper cites Edgevits: Competing light-weight cnns on mobile devices with vision transformers,.

EMOv2: Pushing 5M Vision Model Frontier Edgevits: Competing light-weight cnns on mobile devices with vision transformers,

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:11.025015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e2d96dbe-2661-4e47-baf4-d231bb7d05f0 · outbound

This paper cites Res2net: A new multi-scale backbone architecture,.

EMOv2: Pushing 5M Vision Model Frontier Res2net: A new multi-scale backbone architecture,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:11.005459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a1f46c91-27f5-495c-99de-d53d18a39504 · outbound

This paper cites Xcit: Cross- covariance image transformers,.

EMOv2: Pushing 5M Vision Model Frontier Xcit: Cross- covariance image transformers,

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.986956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a92d1563-4dab-4dfd-97dd-790e49f0ba0c · outbound

This paper cites ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention.

EMOv2: Pushing 5M Vision Model Frontier ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention

Reference 58

Resolution: verified exact; local_arxiv, observed 2026-08-11T19:33:09.678654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a4a37822-38fa-4b5a-acb1-e31952461ee9 · outbound

This paper cites PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning.

EMOv2: Pushing 5M Vision Model Frontier PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.955174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a479897f-bf53-4400-a6e2-ada955ad23ca · outbound

This paper cites Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures.

EMOv2: Pushing 5M Vision Model Frontier Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.960085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17fad12d-aff0-499a-b5e7-59f97270620c · outbound

This paper cites Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model.

EMOv2: Pushing 5M Vision Model Frontier Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.964841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 846bddbb-113b-45fe-8c27-736174fb5682 · outbound

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

EMOv2: Pushing 5M Vision Model Frontier Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.969473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17db84ff-8a86-4532-9a30-958bf9e1c72a · outbound

This paper cites RWKV: Reinventing RNNs for the Transformer Era.

EMOv2: Pushing 5M Vision Model Frontier RWKV: Reinventing RNNs for the Transformer Era

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.974566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cecb269c-59f2-46ad-b5ee-234fec159eaa · outbound

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

EMOv2: Pushing 5M Vision Model Frontier Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.979919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f113bcfd-9f82-42a5-a765-b1fedf2ac45c · outbound

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

EMOv2: Pushing 5M Vision Model Frontier EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.985119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca7ddef0-e575-4101-a4b6-35eb9fb6ce84 · outbound

This paper cites MobileMamba: Lightweight Multi-Receptive Visual Mamba Network.

EMOv2: Pushing 5M Vision Model Frontier MobileMamba: Lightweight Multi-Receptive Visual Mamba Network

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:08.990933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5be2b96-5ac2-42ea-bd25-a18e90e94b8a · outbound

This paper cites Scalable diffusion models with transformers,.

EMOv2: Pushing 5M Vision Model Frontier Scalable diffusion models with transformers,

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.969001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dd7ee496-e397-4116-8610-07581aeae030 · outbound

This paper cites Focal attention for long-range interactions in vision transformers,.

EMOv2: Pushing 5M Vision Model Frontier Focal attention for long-range interactions in vision transformers,

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.950398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e62db3f7-e045-4f42-b810-cd7277157d9b · outbound

This paper cites Cswin transformer: A general vision transformer backbone with cross-shaped windows,.

EMOv2: Pushing 5M Vision Model Frontier Cswin transformer: A general vision transformer backbone with cross-shaped windows,

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.928923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7ad91af7-83be-49a6-9a73-bc19de038b30 · outbound

This paper cites Inception transformer,.

EMOv2: Pushing 5M Vision Model Frontier Inception transformer,

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.902466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 58e8c158-a0f4-46c0-b058-998897949334 · outbound

This paper cites Pay attention to mlps,.

EMOv2: Pushing 5M Vision Model Frontier Pay attention to mlps,

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.879202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f5339a8e-65cc-45fd-bba3-85cb20cbf269 · outbound

This paper cites Mlp-mixer: An all-mlp architecture for vision,.

EMOv2: Pushing 5M Vision Model Frontier Mlp-mixer: An all-mlp architecture for vision,

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.856023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation edde3b16-5899-4a8c-b443-f4f29f6b4e98 · outbound

This paper cites Resmlp: Feed- forward networks for image classification with data-efficient training,.

EMOv2: Pushing 5M Vision Model Frontier Resmlp: Feed- forward networks for image classification with data-efficient training,

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.839369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fe8409ad-4abb-4bb7-9f3f-eab73da92ada · outbound

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

EMOv2: Pushing 5M Vision Model Frontier Shufflenet v2: Practical guidelines for efficient cnn architecture design,

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.807090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3b036c57-67c3-49b0-88df-ee8f5064aa7b · outbound

This paper cites Moat: Alternating mobile convolution and attention brings strong vision models,.

EMOv2: Pushing 5M Vision Model Frontier Moat: Alternating mobile convolution and attention brings strong vision models,

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.780993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f207e548-e190-410e-88ce-ff782ccfacbf · outbound

This paper cites Batch normalization: Accelerating deep network training by reducing internal covariate shift,.

EMOv2: Pushing 5M Vision Model Frontier Batch normalization: Accelerating deep network training by reducing internal covariate shift,

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.751839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d97791ea-07fd-46d4-ad78-f68d35816897 · outbound

This paper cites Gaussian Error Linear Units (GELUs).

EMOv2: Pushing 5M Vision Model Frontier Gaussian Error Linear Units (GELUs)

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:09.047105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 894c76f9-82e0-46f1-bab7-574b3f42d27c · outbound

This paper cites Layer Normalization.

EMOv2: Pushing 5M Vision Model Frontier Layer Normalization

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:09.052064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8a62178-94ae-470f-9605-8e38e2c5a708 · outbound

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

EMOv2: Pushing 5M Vision Model Frontier Imagenet: A large-scale hierarchical image database,

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.731458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 57fc92c9-d1a3-4d3d-aad8-2b07d4b3bfb5 · outbound

This paper cites Decoupled weight decay regularization,.

EMOv2: Pushing 5M Vision Model Frontier Decoupled weight decay regularization,

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.708528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ad719448-0ba3-43b0-a4e6-4fc178cfbcaf · outbound

This paper cites SGDR: Stochastic gradient descent with warm restarts,.

EMOv2: Pushing 5M Vision Model Frontier SGDR: Stochastic gradient descent with warm restarts,

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.684108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8684aa9d-264d-40d0-bd48-c941080f277d · outbound

This paper cites Rethinking the inception architecture for computer vision,.

EMOv2: Pushing 5M Vision Model Frontier Rethinking the inception architecture for computer vision,

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.657560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation baa63e5f-30b8-4daa-9ff7-d511a5d314f1 · outbound

This paper cites Deep networks with stochastic depth,.

EMOv2: Pushing 5M Vision Model Frontier Deep networks with stochastic depth,

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.623924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 042320f6-541c-466e-b4d8-dd8411d8701e · outbound

This paper cites Randaugment: Practical automated data augmentation with a reduced search space,.

EMOv2: Pushing 5M Vision Model Frontier Randaugment: Practical automated data augmentation with a reduced search space,

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.590744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b8afa672-506a-4e7b-b2cb-f96e1bfa5a93 · outbound

This paper cites Going deeper with image transformers,.

EMOv2: Pushing 5M Vision Model Frontier Going deeper with image transformers,

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.568617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c9e714b6-8083-4929-bc1e-23725ee1c6e0 · outbound

This paper cites Dropout: a simple way to prevent neural networks from overfitting,.

EMOv2: Pushing 5M Vision Model Frontier Dropout: a simple way to prevent neural networks from overfitting,

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.541249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 18d1dcc5-5954-40cf-945f-0ea0af80b9df · outbound

This paper cites mixup: Beyond empirical risk minimization,.

EMOv2: Pushing 5M Vision Model Frontier mixup: Beyond empirical risk minimization,

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.515981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 33bf2199-9b74-4fc9-bfee-73954325550b · outbound

This paper cites Cutmix: Regularization strategy to train strong classifiers with localizable features,.

EMOv2: Pushing 5M Vision Model Frontier Cutmix: Regularization strategy to train strong classifiers with localizable features,

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.493164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 30b561b1-19a5-4bd4-932c-afd800402dda · outbound

This paper cites Random erasing data augmentation,.

EMOv2: Pushing 5M Vision Model Frontier Random erasing data augmentation,

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.471017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3119840b-3a8f-4a63-9f7b-63eaaee56d96 · outbound

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

EMOv2: Pushing 5M Vision Model Frontier All tokens matter: Token labeling for training better vision transformers,

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.442430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 01d4d43a-718c-47c0-b2b4-9a604226b8d6 · outbound

This paper cites Pytorch image models,.

EMOv2: Pushing 5M Vision Model Frontier Pytorch image models,

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:09.116189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43f888f2-8d32-43d2-a133-5c8e753c3104 · outbound

This paper cites Tresnet: High performance gpu-dedicated architecture,.

EMOv2: Pushing 5M Vision Model Frontier Tresnet: High performance gpu-dedicated architecture,

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.399510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e360292b-ab38-4b64-92ab-7c9887d2741d · outbound

This paper cites Run, don’t walk: chasing higher flops for faster neural networks,.

EMOv2: Pushing 5M Vision Model Frontier Run, don’t walk: chasing higher flops for faster neural networks,

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.376257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation db85b25a-659b-4da1-8527-28afa9548087 · outbound

This paper cites MoCoViT: Mobile Convolutional Vision Transformer.

EMOv2: Pushing 5M Vision Model Frontier MoCoViT: Mobile Convolutional Vision Transformer

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:09.129596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daac5484-93a7-4379-86b7-776dbb425025 · outbound

This paper cites Efficientvit: Memory efficient vision transformer with cascaded group attention,.

EMOv2: Pushing 5M Vision Model Frontier Efficientvit: Memory efficient vision transformer with cascaded group attention,

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.354143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 24faf258-60a5-4ef8-927a-48bd188e380d · outbound

This paper cites Mpvit: Multi-path vision transformer for dense prediction,.

EMOv2: Pushing 5M Vision Model Frontier Mpvit: Multi-path vision transformer for dense prediction,

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.317228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 063dfb65-5f9b-401b-9606-be7d48e94af5 · outbound

This paper cites Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model.

EMOv2: Pushing 5M Vision Model Frontier Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:09.144083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4e01e62-c4f0-4e4d-b604-710d53478543 · outbound

This paper cites MambaOut: Do We Really Need Mamba for Vision?.

EMOv2: Pushing 5M Vision Model Frontier MambaOut: Do We Really Need Mamba for Vision?

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-11T19:33:09.149397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61065d6f-849c-4e43-9cbf-9c3fc1bc013b · outbound

This paper cites Microsoft coco: Common objects in context,.

EMOv2: Pushing 5M Vision Model Frontier Microsoft coco: Common objects in context,

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.294337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0131d5fc-e6ef-4ee5-94de-c487610a00b3 · outbound

This paper cites Mask r-cnn,.

EMOv2: Pushing 5M Vision Model Frontier Mask r-cnn,

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:33:10.277774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers