Paper Citation Record · LEDGER

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI

As of 9 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2507.09702.

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

pith.paper-citation-record.v1
2507.09702 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T17:53:29.400938Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

38 of 38 outbound references displayed

verified exact0
verified fuzzy17
unresolved21
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c917aeac-93ad-4cc3-8220-234813b55a6a · outbound

This paper cites EVit: Expediting vision transformers via token reorganizations,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI EVit: Expediting vision transformers via token reorganizations,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:25.907116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66bc784b-c34d-41e9-8b31-ea949e7eea59 · outbound

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

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Dynamicvit: Efficient vision transformers with dynamic token sparsification,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:25.950294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf39ae82-2bb0-47d5-9324-f160b4a46846 · outbound

This paper cites Token cropr: Faster vits for quite a few tasks,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Token cropr: Faster vits for quite a few tasks,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:32.957144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 303c52b5-4eef-4059-b823-60ce23020226 · outbound

This paper cites Adaptive token sampling for efficient vision trans- formers,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Adaptive token sampling for efficient vision trans- formers,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:32.771402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 91b631ec-01d9-4f2e-b7fd-9e1e91f2438e · outbound

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

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Spvit: Enabling faster vision transformers via latency-aware soft token pruning,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:32.616947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2a1f77be-8f9c-4eb7-8135-db7994d8ada5 · outbound

This paper cites Token merging: Your ViT but faster,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Token merging: Your ViT but faster,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:26.194931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c0617de-37b9-4f7b-87d7-a01874c97176 · outbound

This paper cites Not all tokens are equal: Human-centric visual analysis via token cluster- ing transformer,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Not all tokens are equal: Human-centric visual analysis via token cluster- ing transformer,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:26.373778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a37da3f-b963-42e0-b554-17b19b5b2fbb · outbound

This paper cites Ac- celerating transformers with spectrum-preserving token merging,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Ac- celerating transformers with spectrum-preserving token merging,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:32.234718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2f567a39-8f7c-4071-9207-555a1334a347 · outbound

This paper cites Self-slimmed vision transformer,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Self-slimmed vision transformer,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:32.044333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 40b915a7-a7b8-4159-afdf-3b1e53e50ced · outbound

This paper cites Multi-scale hybrid vision transformer and sinkhorn tokenizer for sewer defect classification,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Multi-scale hybrid vision transformer and sinkhorn tokenizer for sewer defect classification,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:31.800702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 06250222-426a-428f-9eb6-6a309faf1aba · outbound

This paper cites Learning to Merge Tokens in Vision Transformers.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Learning to Merge Tokens in Vision Transformers

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:26.621820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76227289-c98c-4736-b3ae-01dfea308443 · outbound

This paper cites Learning to merge tokens via decoupled embedding for efficient vision transformers,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Learning to merge tokens via decoupled embedding for efficient vision transformers,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:31.614091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 90f019a3-07c6-4d21-ada9-a614fedeea49 · outbound

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

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Token fusion: Bridging the gap between token pruning and token merging,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:26.795238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb0a5cf6-021a-402f-9fb3-8a6a7a2dd66b · outbound

This paper cites Diffrate: Differentiable compression rate for efficient vision transformers,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Diffrate: Differentiable compression rate for efficient vision transformers,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:31.428546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9567c294-0725-45f8-a984-c2be9d4f9260 · outbound

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

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI An image is worth 16x16 words: Transformers for image recognition at scale,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:26.884853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91990994-306b-4e64-b933-e5790e1cb3bb · outbound

This paper cites End-to-end object detection with transformers,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI End-to-end object detection with transformers,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:31.156986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7e75d30c-a07d-4964-97c9-d5db8ac0c261 · outbound

This paper cites Vivit: A video vision transformer,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Vivit: A video vision transformer,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:27.015898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b86b3981-37e0-453f-9f19-f8ca4603207e · outbound

This paper cites Learn- ing transferable visual models from natural language supervision,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Learn- ing transferable visual models from natural language supervision,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:30.861889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3f7bcd5f-7488-4d85-84c6-c33b1b7f1a5a · outbound

This paper cites Autoformer: Searching transformers for visual recognition,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Autoformer: Searching transformers for visual recognition,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:27.144976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fecc1481-479b-4b93-9219-34517ec79ea8 · outbound

This paper cites Elasticvit: Conflict-aware supernet training for deploying fast vi- sion transformer on diverse mobile devices,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Elasticvit: Conflict-aware supernet training for deploying fast vi- sion transformer on diverse mobile devices,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:30.682547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6c57c364-ddee-4dfe-9c33-e32ef61a0829 · outbound

This paper cites Revisit multimodal meta-learning through the lens of multi-task learning,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Revisit multimodal meta-learning through the lens of multi-task learning,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:27.321679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05247dab-19c9-49db-a882-e9291e14c59d · outbound

This paper cites Vct: A video compression transformer,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Vct: A video compression transformer,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:27.406658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28b16230-1395-4927-a880-ad616e314363 · outbound

This paper cites Highly parallel rate-distortion optimized intra-mode decision on multicore graphics processors,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Highly parallel rate-distortion optimized intra-mode decision on multicore graphics processors,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:27.533921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c55b6a2-edef-4805-ac11-6f67401c5568 · outbound

This paper cites On-device scalable image-based localization via prioritized cascade 5 search and fast one-many ransac,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI On-device scalable image-based localization via prioritized cascade 5 search and fast one-many ransac,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:30.470844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1e3af81f-46f6-4f84-bf14-2b32bb6ec881 · outbound

This paper cites On Accelerating Edge AI: Optimizing Resource-Constrained Environments.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI On Accelerating Edge AI: Optimizing Resource-Constrained Environments

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:27.672710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 641e6118-09b8-41e6-8cdc-811107b6a0f5 · outbound

This paper cites A Survey on Efficient Inference for Large Language Models.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI A Survey on Efficient Inference for Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:27.843310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 774558c3-3b82-4344-bf88-e578ddd294d2 · outbound

This paper cites RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:27.970825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e54d633-1641-4df0-a91f-929796d6b195 · outbound

This paper cites Nvit: Vision transformer compression and parameter redistribution,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Nvit: Vision transformer compression and parameter redistribution,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:28.086534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9be91c68-efb8-4f45-b462-6efde717b120 · outbound

This paper cites Width & depth pruning for vision transformers,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Width & depth pruning for vision transformers,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:28.128321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7f218e3-45ec-4f69-96b0-00ae361c1662 · outbound

This paper cites Revisiting label smoothing and knowledge distillation compatibility: What was missing?.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Revisiting label smoothing and knowledge distillation compatibility: What was missing?

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:30.295861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a6046838-30fb-488b-8e8c-cf710c122d23 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Distilling the Knowledge in a Neural Network

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:28.417264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32f8f9c4-6c85-4b5e-a48b-3821f59517cb · outbound

This paper cites Searching the search space of vision transformer,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Searching the search space of vision transformer,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:28.554175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c97944a2-5ac3-4dfc-9aca-8c246711a92a · outbound

This paper cites Nasvit: Neural architecture search for efficient vision transformers with gradient conflict-aware supernet training,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Nasvit: Neural architecture search for efficient vision transformers with gradient conflict-aware supernet training,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:28.753738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbf2d92d-b3e7-484e-afba-6f4621fdc9ef · outbound

This paper cites Vitas: Vision transformer architecture search,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Vitas: Vision transformer architecture search,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:28.896734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63adba2c-ac20-4529-9d81-c02e587840b2 · outbound

This paper cites Which tokens to use? investigating token reduction in vision transformers,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Which tokens to use? investigating token reduction in vision transformers,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:30.117351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b7d28318-bd84-4719-b765-41d3dd0a1e50 · outbound

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

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Spvit: Enabling faster vision transformers via latency-aware soft token pruning,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:29.957935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b6929117-3273-4c44-88dc-c55c69a2bc84 · outbound

This paper cites Token pooling in vision transformers for image classification,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Token pooling in vision transformers for image classification,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:32.421317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 843c6e41-c705-4e23-8564-1d22cf2c679a · outbound

This paper cites Not all tokens are equal: Human-centric visual analysis via token cluster- ing transformer,.

Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI Not all tokens are equal: Human-centric visual analysis via token cluster- ing transformer,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:53:29.691991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

No inbound Pith citation observations are available.