Paper Citation Record · LEDGER

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers

As of 9 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 1 inbound Pith citation observation for arXiv:2509.03379.

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

pith.paper-citation-record.v1
2509.03379 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T11:01:33.575599Z

measured 34 of 34 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T11:01:31.085740Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T11:01:33.666593Z

Reference resolution

33 of 33 outbound references displayed

verified exact0
verified fuzzy30
unresolved2
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b9e16fa5-ca3f-4dee-8ec9-84d995cfa45e · outbound

This paper cites Un- like convolutional networks, ViTs process all input tokens uniformly with identical computational cost, resulting in quadratic complexity relative to token count.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Un- like convolutional networks, ViTs process all input tokens uniformly with identical computational cost, resulting in quadratic complexity relative to token count

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:36.060701Z

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 6d9aaebf-7301-48c4-a87f-e2225da21367 · outbound

This paper cites TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers

Reference 2

Resolution: malformed identifier; local_arxiv, observed 2026-08-05T11:01:33.766233Z

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 1af56d0c-3f7b-496a-a646-62ca51886261 · outbound

This paper cites Settings We evaluate TinyDrop across ImageNet-1K [19] on state-of- the-art architectures, including Vision Transformer [1, 20], BEiTv2 [3], DeiT3 [4] and DeiT [21].

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Settings We evaluate TinyDrop across ImageNet-1K [19] on state-of- the-art architectures, including Vision Transformer [1, 20], BEiTv2 [3], DeiT3 [4] and DeiT [21]

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:36.042528Z

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 102286c7-89bf-4103-a34c-e020550d9b92 · outbound

This paper cites an unresolved cited work.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-05T11:01:36.033169Z

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 a877ee83-1ee0-4a1b-8006-05337c51a03d · outbound

This paper cites Logit standardization in knowl- edge distillation,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Logit standardization in knowl- edge distillation,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.995233Z

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 91c88293-aada-4b35-a5a6-b6a93e76bc77 · outbound

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

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers An image is worth 16x16 words: Transformers for image recognition at scale,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:36.023444Z

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 46776a12-b8d8-4447-ac68-62b8f135166a · outbound

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

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Swin transformer v2: Scaling up capacity and resolution,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:36.014400Z

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 3868b1ea-5102-43d9-85bd-cd722faeaf07 · outbound

This paper cites BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T11:01:31.392569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b41d44d7-5bea-4ff9-b90c-d68d2bc44372 · outbound

This paper cites Deit iii: Revenge of the vit,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Deit iii: Revenge of the vit,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:36.004585Z

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 fb233c0f-b9f4-480e-9b2c-bbb14bdadcec · outbound

This paper cites Zero-tprune: Zero-shot token pruning through leveraging of the attention graph in pre-trained transformers,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Zero-tprune: Zero-shot token pruning through leveraging of the attention graph in pre-trained transformers,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.951841Z

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 566a19e4-20dc-4b41-97fb-af14e93d2d5b · outbound

This paper cites In addition, Papr reports pri- marily on smaller/earlier backbones, with limited accounting of cost when scaling to large frozen ViTs.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers In addition, Papr reports pri- marily on smaller/earlier backbones, with limited accounting of cost when scaling to large frozen ViTs

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:36.052089Z

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 d6617598-f242-4980-a27e-b43b1ebf22c7 · outbound

This paper cites Low-rank approximation for sparse attention in multi-modal llms,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Low-rank approximation for sparse attention in multi-modal llms,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.986744Z

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 380f6841-1388-431e-8ab4-b7c17fa73f8f · outbound

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

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Token merging: Your vit but faster,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.978315Z

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 df7ecc73-c373-4042-8357-8c2d9b214390 · outbound

This paper cites Diffrate: Differentiable com- pression rate for efficient vision transformers,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Diffrate: Differentiable com- pression rate for efficient vision transformers,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.969428Z

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 d2d3f07d-2f80-4298-abfe-93375a295638 · outbound

This paper cites Adaptive token sampling for efficient vision transformers,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Adaptive token sampling for efficient vision transformers,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.960857Z

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 da21b2d4-1cb9-49b1-ac47-3b7f2790e26a · outbound

This paper cites Papr: Training-free one-step patch pruning with lightweight convnets for faster infer- ence,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Papr: Training-free one-step patch pruning with lightweight convnets for faster infer- ence,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.943032Z

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 617ee9ad-bb18-47b8-bfe2-aea864a91af7 · outbound

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

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Rethinking vision transformers for mobilenet size and speed,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.934553Z

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 44ffc52f-0032-45c4-b303-b7ad98aa9dab · outbound

This paper cites Efficientnetv2: Smaller models and faster training,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Efficientnetv2: Smaller models and faster training,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.925930Z

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 841318e6-d3d0-4208-8e93-0b5594d0e958 · outbound

This paper cites Extracting class ac- tivation maps from non-discriminative features as well,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Extracting class ac- tivation maps from non-discriminative features as well,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.917417Z

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 49ae7a41-c633-4418-b655-8482f2fc1ce1 · outbound

This paper cites Tiny models are the computa- tional saver for large models,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Tiny models are the computa- tional saver for large models,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.907939Z

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 d1b959b9-7fe0-478a-90b4-8744ee53d73c · outbound

This paper cites Grad-cam: Visual ex- planations from deep networks via gradient-based local- ization,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Grad-cam: Visual ex- planations from deep networks via gradient-based local- ization,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.898200Z

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 04c17078-a7b5-4cd3-8fdd-8e594c869fad · outbound

This paper cites The impact of posi- tional encoding on length generalization in transform- ers,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers The impact of posi- tional encoding on length generalization in transform- ers,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.889103Z

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 4c8ce726-cffd-4295-b1a7-f9978b422a00 · outbound

This paper cites Rethinking and improving relative po- sition encoding for vision transformer,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Rethinking and improving relative po- sition encoding for vision transformer,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.879521Z

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 6c865bd4-1d6d-4c4d-9520-62ab88855168 · outbound

This paper cites Imagenet large scale visual recognition challenge,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Imagenet large scale visual recognition challenge,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.869930Z

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 bb7d6307-360a-4533-8b16-cf73b5510b70 · outbound

This paper cites How to train your vit? data, augmentation, and regularization in vision trans- formers,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers How to train your vit? data, augmentation, and regularization in vision trans- formers,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.741807Z

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 8d4826b8-7b71-4137-a129-24e62df15e60 · outbound

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

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Training data-efficient image transformers & distillation through attention,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.465648Z

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 0a7e5008-635a-4cea-9e68-05717c22006c · outbound

This paper cites Pytorch image mod- els,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Pytorch image mod- els,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.262118Z

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 a4337302-c209-4a08-93bf-743e2787269c · outbound

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

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Token fusion: Bridging the gap between token pruning and token merging,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:35.090129Z

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 2ac72dac-d14d-4738-934d-4821829cb560 · outbound

This paper cites Cf-vit: A general coarse-to- fine method for vision transformer,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Cf-vit: A general coarse-to- fine method for vision transformer,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:34.948533Z

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 f3d046e2-95bc-4e13-8a36-571e0be04a9e · outbound

This paper cites Dynamic perceiver for efficient vi- sual recognition,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Dynamic perceiver for efficient vi- sual recognition,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:34.712878Z

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 5867d583-96e3-4ded-9527-a3bd6ea5f35c · outbound

This paper cites Msnet: Multi-resolution synergis- tic networks for adaptive inference,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Msnet: Multi-resolution synergis- tic networks for adaptive inference,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:34.472772Z

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 50c1da2c-0daa-4d60-9740-802093bc8cd5 · outbound

This paper cites A panda? no, it’s a sloth: Slow- down attacks on adaptive multi-exit neural network in- ference,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers A panda? no, it’s a sloth: Slow- down attacks on adaptive multi-exit neural network in- ference,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:34.204879Z

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 a39e5890-bf4f-4608-9638-fa322f1d7246 · outbound

This paper cites Not all images are worth 16x16 words: Dynamic transformers for efficient image recog- nition,.

TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers Not all images are worth 16x16 words: Dynamic transformers for efficient image recog- nition,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:01:33.983266Z

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

Observation 6d9aaebf-7301-48c4-a87f-e2225da21367 · inbound