Paper Citation Record · LEDGER

MPM: Mutual Pair Merging for Efficient Vision Transformers

As of 9 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2604.05718.

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

pith.paper-citation-record.v1
2604.05718 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T19:22:31.335412Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

39 of 39 outbound references displayed

verified exact1
verified fuzzy36
unresolved1
parse uncertain1
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6fa920ec-9477-42ed-952d-bd0a83c9717d · outbound

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

MPM: Mutual Pair Merging for Efficient Vision Transformers Token cropr: Faster vits for quite a few tasks

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:25.202465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 02c0aaaf-23d6-40db-81a4-726c3e0c9335 · outbound

This paper cites Token merging: Your vit but faster.

MPM: Mutual Pair Merging for Efficient Vision Transformers Token merging: Your vit but faster

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:25.195120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation caed3035-6d8f-4af7-a97e-f7e476ae1e9b · outbound

This paper cites Vision transformer adapter for dense predictions.

MPM: Mutual Pair Merging for Efficient Vision Transformers Vision transformer adapter for dense predictions

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:25.210193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 072c1706-ca38-4bf3-85c8-60de95af8ead · outbound

This paper cites Schwing, Alexan- der Kirillov, and Rohit Girdhar.

MPM: Mutual Pair Merging for Efficient Vision Transformers Schwing, Alexan- der Kirillov, and Rohit Girdhar

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:25.198616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 43ae2f76-acc0-48c0-9cfc-71301ca98cf5 · outbound

This paper cites 1, 2, 7, 8.

MPM: Mutual Pair Merging for Efficient Vision Transformers 1, 2, 7, 8

Reference 5

Resolution: parse uncertain; raw_fallback, observed 2026-05-16T05:37:25.206217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3a216b39-ff84-4e1c-9b82-b5066dcb9dcd · outbound

This paper cites Flashattention-2: Faster attention with better paral- lelism and work partitioning.

MPM: Mutual Pair Merging for Efficient Vision Transformers Flashattention-2: Faster attention with better paral- lelism and work partitioning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:25.220584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 01f7cf07-61a2-4553-a6b7-6769144b709a · outbound

This paper cites Fu, Stefano Ermon, Atri Rudra, and Christopher R´e.

MPM: Mutual Pair Merging for Efficient Vision Transformers Fu, Stefano Ermon, Atri Rudra, and Christopher R´e

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:25.213855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8b6a5413-8416-4b3d-9fa6-df2446c689ba · outbound

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

MPM: Mutual Pair Merging for Efficient Vision Transformers An image is worth 16x16 words: Transformers for image recognition at scale

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.791485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a4a7177d-2706-4907-8292-f2e003bfc59a · outbound

This paper cites Multiscale vision transformers.

MPM: Mutual Pair Merging for Efficient Vision Transformers Multiscale vision transformers

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.750268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c90e54dd-10da-49c2-8aee-65679c1a1271 · outbound

This paper cites EV A: exploring the limits of masked visual representation learning at scale.

MPM: Mutual Pair Merging for Efficient Vision Transformers EV A: exploring the limits of masked visual representation learning at scale

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.823500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0c63f0c3-7592-41d4-9c72-7f278ccc1fd9 · outbound

This paper cites Adaptive token sampling for efficient vision transformers.

MPM: Mutual Pair Merging for Efficient Vision Transformers Adaptive token sampling for efficient vision transformers

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.799332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 058150ba-ff26-4f85-98a0-0ac19cfe3080 · outbound

This paper cites Tay- lor, and Thomas B.

MPM: Mutual Pair Merging for Efficient Vision Transformers Tay- lor, and Thomas B

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.806898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 38dabb03-8826-4522-8116-39bc22f14534 · outbound

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

MPM: Mutual Pair Merging for Efficient Vision Transformers Token fusion: Bridging the gap between token pruning and token merging

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.795342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6931de52-37f4-4674-a06b-dc47316dd666 · outbound

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

MPM: Mutual Pair Merging for Efficient Vision Transformers Spvit: Enabling faster vision transformers via latency-aware soft token pruning

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.803305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c1aee6d8-be27-4a9f-9af9-466acd30574e · outbound

This paper cites Learning to merge to- kens via decoupled embedding for efficient vision transform- ers.

MPM: Mutual Pair Merging for Efficient Vision Transformers Learning to merge to- kens via decoupled embedding for efficient vision transform- ers

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.814832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5f2bcf02-845d-486e-b778-a2eed40ea902 · outbound

This paper cites Expediting large-scale vision transformer for dense prediction without fine-tuning.

MPM: Mutual Pair Merging for Efficient Vision Transformers Expediting large-scale vision transformer for dense prediction without fine-tuning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:25.185077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 491a05dc-61bf-4561-8844-ac440092a054 · outbound

This paper cites Evit: Expediting vision transformers via token reorganizations.

MPM: Mutual Pair Merging for Efficient Vision Transformers Evit: Expediting vision transformers via token reorganizations

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:25.176971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e26ca4c4-2e3f-4374-a5cb-b96942a2631e · outbound

This paper cites Adaptive sparse vit: Towards learnable adaptive token pruning by fully exploiting self-attention.

MPM: Mutual Pair Merging for Efficient Vision Transformers Adaptive sparse vit: Towards learnable adaptive token pruning by fully exploiting self-attention

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.787632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2320bb68-1507-4e61-8f29-faa7df4525d9 · outbound

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

MPM: Mutual Pair Merging for Efficient Vision Transformers Swin transformer: Hierarchical vision transformer using shifted windows

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.728597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 821f12c1-a7ac-4c01-a84a-e7bea43a4fb5 · outbound

This paper cites Content- aware token sharing for efficient semantic segmentation with vision transformers.

MPM: Mutual Pair Merging for Efficient Vision Transformers Content- aware token sharing for efficient semantic segmentation with vision transformers

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:25.217144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 417517f5-09b1-466e-a2c8-b6b8d61df781 · outbound

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

MPM: Mutual Pair Merging for Efficient Vision Transformers Token pooling in vision transformers for image classification

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.775632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dd2d1b0a-0aa1-4a2c-b884-b35b08712aba · outbound

This paper cites ALGM: adaptive local-then-global token merg- ing for efficient semantic segmentation with plain vision trans- formers.

MPM: Mutual Pair Merging for Efficient Vision Transformers ALGM: adaptive local-then-global token merg- ing for efficient semantic segmentation with plain vision trans- formers

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.771677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4d3d162a-3067-44f3-aa1f-fe879018ba1d · outbound

This paper cites Dynamicvit: Efficient vision trans- formers with dynamic token sparsification.

MPM: Mutual Pair Merging for Efficient Vision Transformers Dynamicvit: Efficient vision trans- formers with dynamic token sparsification

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.779818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation aa05c928-19e2-4cf5-89ad-df37e440dd50 · outbound

This paper cites Hiera: A hier- archical vision transformer without the bells-and-whistles.

MPM: Mutual Pair Merging for Efficient Vision Transformers Hiera: A hier- archical vision transformer without the bells-and-whistles

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.819163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e7733b8f-ab35-472e-b4df-a666b5485f13 · outbound

This paper cites an unresolved cited work.

MPM: Mutual Pair Merging for Efficient Vision Transformers Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-05-16T05:32:24.783802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 39769017-af61-4bfc-8503-3de25ab8ce32 · outbound

This paper cites Flashattention-3: Fast and accurate attention with asynchrony and low-precision.

MPM: Mutual Pair Merging for Efficient Vision Transformers Flashattention-3: Fast and accurate attention with asynchrony and low-precision

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.759045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1f6ae0e3-9915-4a28-bfef-30ba7b76949c · outbound

This paper cites Segmenter: Transformer for semantic segmentation.

MPM: Mutual Pair Merging for Efficient Vision Transformers Segmenter: Transformer for semantic segmentation

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:25.173721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ccacf9b4-2062-49c9-99c5-e1288efb615f · outbound

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

MPM: Mutual Pair Merging for Efficient Vision Transformers Training data-efficient image transformers & distillation through at- tention

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.754490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 406ce45b-bc89-4971-a540-e33c1a33df4b · outbound

This paper cites Gomez, Lukasz Kaiser, and Illia Polosukhin.

MPM: Mutual Pair Merging for Efficient Vision Transformers Gomez, Lukasz Kaiser, and Illia Polosukhin

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:25.191811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b4eef831-c912-4d3e-ad32-6eb3e53c9525 · outbound

This paper cites Pyra- mid vision transformer: A versatile backbone for dense predic- tion without convolutions.

MPM: Mutual Pair Merging for Efficient Vision Transformers Pyra- mid vision transformer: A versatile backbone for dense predic- tion without convolutions

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.767765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c579ccfc-cae9-4aa3-9be6-ca00fc3813c1 · outbound

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

MPM: Mutual Pair Merging for Efficient Vision Transformers PVT v2: Improved baselines with pyramid vision transformer

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.763262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 26a06763-d81d-4171-8e3b-fbc2ea158585 · outbound

This paper cites Dtmformer: Dynamic token merging for boosting transformer-based medical image seg- mentation.

MPM: Mutual Pair Merging for Efficient Vision Transformers Dtmformer: Dynamic token merging for boosting transformer-based medical image seg- mentation

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:25.188735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4b47a9aa-e219-43d3-876d-13a4de100c7b · outbound

This paper cites PPT: Token Pruning and Pooling for Efficient Vision Transformers.

MPM: Mutual Pair Merging for Efficient Vision Transformers PPT: Token Pruning and Pooling for Efficient Vision Transformers

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:05:47.985985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bc2c3069-bff8-42b1-b352-067a28db6c62 · outbound

This paper cites Unified perceptual parsing for scene understanding.

MPM: Mutual Pair Merging for Efficient Vision Transformers Unified perceptual parsing for scene understanding

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.810969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 537d0504-9ce9-4e9e-9866-6d2fe3bdd01c · outbound

This paper cites ´Alvarez, and Ping Luo.

MPM: Mutual Pair Merging for Efficient Vision Transformers ´Alvarez, and Ping Luo

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.740691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2b8e1192-c2f9-4809-8184-eaf8f155bd23 · outbound

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

MPM: Mutual Pair Merging for Efficient Vision Transformers Evo-vit: Slow-fast token evolution for dynamic vision transformer

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.745477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 35d7fcad-3bce-4fd3-8aa5-8f6ef6a38afe · outbound

This paper cites ´Alvarez, Arun Mallya, Jan Kautz, and Pavlo Molchanov.

MPM: Mutual Pair Merging for Efficient Vision Transformers ´Alvarez, Arun Mallya, Jan Kautz, and Pavlo Molchanov

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.736287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c655f3f5-72b9-4dde-94f1-d662c847bd9a · outbound

This paper cites Segvit: Semantic segmentation with plain vision transformers.

MPM: Mutual Pair Merging for Efficient Vision Transformers Segvit: Semantic segmentation with plain vision transformers

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:25.181166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ecfb700a-08a4-4b6f-9438-8b2d375068a4 · outbound

This paper cites Scene parsing through ADE20K dataset.

MPM: Mutual Pair Merging for Efficient Vision Transformers Scene parsing through ADE20K dataset

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:32:24.732396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

No inbound Pith citation observations are available.