Pith. sign in

Paper Citation Record · LEDGER

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training

As of 15 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 3 inbound Pith citation observations for arXiv:2412.12496.

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

pith.paper-citation-record.v1
2412.12496 v4

Coverage vector

measured 56 of 56 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T14:07:16.342170Z

measured 59 of 59 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T20:01:11.371367Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T03:39:29.534164Z

Reference resolution

56 of 56 outbound references displayed

  • verified exact0
  • verified fuzzy35
  • unresolved21
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ea97f0d3-fbd8-4843-8855-1e83cc220d07 · outbound

This paper cites Mutual information neural estimation.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Mutual information neural estimation

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:18.161642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:15.852227Z digest=sha256:0de4e3dc4531100a6879b68581bc5899efc2692c055c174bb92a0cd6ea845a79

Observation fcbe3cc3-b82a-44ba-9029-03e85abaa93f · outbound

This paper cites Token merging: Your ViT but faster.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Token merging: Your ViT but faster

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:18.141129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:15.860111Z digest=sha256:644b487bdc8476ba196c153028d49bd9acbb20aa652ffcb8a00a592930b4fd4e

Observation 180a5825-7a5b-4f80-b13a-8cd96f9311f4 · outbound

This paper cites Quo vadis, action recognition? a new model and the kinetics dataset.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Quo vadis, action recognition? a new model and the kinetics dataset

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:15.867111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:15.867111Z digest=sha256:d3fff044ab27f9011a0f043dbfea4198171a612ddcc6baf7223c0af125f39eb8

Observation 4ce6b7e8-bb12-411c-96e1-2b7eb836a648 · outbound

This paper cites Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:15.873501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:15.873501Z digest=sha256:20b9b13ffe12a7c564f979deabd22e8deab4c6137a25c526c10574bb6f9f2c24

Observation 6190d11b-cabb-4feb-9819-a0da626a499f · outbound

This paper cites Rsmamba: Remote sens- ing image classification with state space model.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Rsmamba: Remote sens- ing image classification with state space model

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:18.098051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:15.887193Z digest=sha256:9ce08bd657e99e995423c3b17b2e76350942c8731e28035c3bf841f73cad39c6

Observation 3ba5b7e1-3049-4b2e-a1be-ffa07f82e45d · outbound

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

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Diffrate: Differentiable compression rate for efficient vision transformers

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:18.072765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:15.892312Z digest=sha256:15e8a088c1d1e101b7d6bc88ccdfb0744d648ad86df816f18ad37ee822e06b46

Observation 5d3ff850-208f-4453-bf27-4f7938046286 · outbound

This paper cites Transformers are SSMs: General- ized models and efficient algorithms through structured state space duality.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Transformers are SSMs: General- ized models and efficient algorithms through structured state space duality

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:18.043576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:15.900398Z digest=sha256:c71ab4395abce131582d910580037774fa0d10a63c308eb760a592e70222d00a

Observation 943aa2d3-7214-4ac3-a043-574c72b2ea13 · outbound

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

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Imagenet: A large-scale hierarchical image database

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:18.023785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:15.908405Z digest=sha256:6ef08666f2b48ebc09943cab9654311db221dffc59cc0c54daae10804703a481

Observation 5f5888ff-9355-4f76-a979-717a8f25b961 · outbound

This paper cites Fusion-Mamba for Cross-modality Object Detection.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Fusion-Mamba for Cross-modality Object Detection

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:15.914851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:15.914851Z digest=sha256:aef3d35923ea141c58e857f438c5a7f0cbfced3b20939686f00f5fd970ff042e

Observation 424ac404-cdb9-40bd-8869-796a43e19d5b · outbound

This paper cites Adaptive token sampling for efficient vision transformers.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Adaptive token sampling for efficient vision transformers

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.997824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:15.924958Z digest=sha256:eaa46e009a5a032c56facf51bef09eecf58492c2378051366989b133dd65c062

Observation 3cc28072-c382-4ced-a799-3f1de4f2f8d7 · outbound

This paper cites Fu, Tri Dao, Khaled K.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Fu, Tri Dao, Khaled K

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.976227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:15.934719Z digest=sha256:c6bc030d8685fb7c6484a5f7f8af06c400dfb95e0054a94942013222a275ca66

Observation 241c855f-e69b-420f-8f75-81e49addfff0 · outbound

This paper cites Power-bert: Accelerating bert inference via progres- sive word-vector elimination.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Power-bert: Accelerating bert inference via progres- sive word-vector elimination

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.952770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:15.948508Z digest=sha256:463dcf54cf0293bb820cdcad26d5a2e228a7d536b0cfc908ced384a90fc63270

Observation 0e07ca3f-9a07-40d7-89bd-78dcd5791de7 · outbound

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

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:15.958509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:15.958509Z digest=sha256:4da044f9cabc048bc456dadb1bdad0f71c1d4025d38c3da7432be0aa74d789ce

Observation fb7d71e6-d6d8-43de-9af3-7aac47d0b026 · outbound

This paper cites Efficiently mod- eling long sequences with structured state spaces.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Efficiently mod- eling long sequences with structured state spaces

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:15.964016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:15.964016Z digest=sha256:f95212ed48f0d107a82a2196c95c033c93870da06f65b6a94582b8fd20fd9d60

Observation 6a087680-0b2c-4fa0-95e6-c79586832464 · outbound

This paper cites Mambair: A simple baseline for image restoration with state-space model.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Mambair: A simple baseline for image restoration with state-space model

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.908590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:15.969066Z digest=sha256:a742a9f1e90441e2bd601b1f1a0470e23c249e5e1c5aaf46704100763ea7801c

Observation a46c1510-6b46-4a6d-a62e-aa019c314ed6 · outbound

This paper cites Mamba3d: Enhancing local features for 3d point cloud anal- ysis via state space model.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Mamba3d: Enhancing local features for 3d point cloud anal- ysis via state space model

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.885147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:15.975292Z digest=sha256:91a4df8c77da020455f4c95c4d430b2444666815022fdda1250745670444f91d

Observation 39dec487-74c5-4d12-9892-3b6f1386bb6c · outbound

This paper cites MambaVision: A Hybrid Mamba-Transformer Vision Backbone.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training MambaVision: A Hybrid Mamba-Transformer Vision Backbone

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:15.981263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:15.981263Z digest=sha256:d3d95388489017e40ba081e6af83f35a86dbad76d2c12f88baf51d5d036f084c

Observation 1a13c471-8bdf-405f-ac16-ed0cde2bd4f2 · outbound

This paper cites Zigma: A dit-style zigzag mamba diffusion model.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Zigma: A dit-style zigzag mamba diffusion model

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.862849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:15.996094Z digest=sha256:20d2a18a8cd0bd1b1cd6cd4b985a4e706f0ca21e27851ddfc3147d2b312d4345

Observation a044577a-3849-4948-9c67-cbc7eb2baa38 · outbound

This paper cites LocalMamba: Visual State Space Model with Windowed Selective Scan.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training LocalMamba: Visual State Space Model with Windowed Selective Scan

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:16.003428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:16.003428Z digest=sha256:6801abf7cc94a47e40afba7ce55cc3a71594303067258d45a66a73ec86e46c90

Observation 81b39bae-0ac8-433b-9d4a-5d5403d80e27 · outbound

This paper cites Length-adaptive trans- former: Train once with length drop, use anytime with search.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Length-adaptive trans- former: Train once with length drop, use anytime with search

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.835736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.010325Z digest=sha256:5c66175e6682fc3ee56c1453289c6bf13ae13bc3c1915fa1dba0e791c89bb64b

Observation 19af26af-2033-440d-95ac-ec62d559c27a · outbound

This paper cites Learned token pruning for transformers.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Learned token pruning for transformers

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.808987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.016337Z digest=sha256:d8c9784c54b872a8067be73d8f50404f2ddf9a12389020c64d0ed09c4e9a96fe

Observation 1765b264-c2f9-4c56-bed9-4e0b04d2039d · outbound

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

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Spvit: Enabling faster vision transformers via latency-aware soft token pruning

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.781925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.025020Z digest=sha256:0889f634c749991fb463aabe8929e3132cff6c78d50af59b8d5e19eb3df8db75

Observation 62d8e844-10d1-4ce6-baa1-b2aeb419bb58 · outbound

This paper cites Videomamba: State space model for efficient video understanding.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Videomamba: State space model for efficient video understanding

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.741831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.032838Z digest=sha256:e4a6a590c838f870d27e9355d16913cfd6adb8e9914987be45efc8d4790fcdac

Observation 75409847-d557-4e18-a845-744ac4cb2195 · outbound

This paper cites Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:16.041108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:16.041108Z digest=sha256:19e8c55b2d0eba3e631893abc303651e9946e1524077afa9a9b235e3851d7a7a

Observation 7f2bc7b5-d5b4-46ff-94e3-18589862448d · outbound

This paper cites Pointmamba: A simple state space model for point cloud analysis.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Pointmamba: A simple state space model for point cloud analysis

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.708388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.064495Z digest=sha256:90dcb63c1db2450b191c2f24778ea53db49289f593a9f36e9085c8a9e476234b

Observation eb4a8b98-d999-4801-b28d-8e822246830d · outbound

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

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Not all patches are what you need: Expediting vision transformers via token reorganizations

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.673569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.073459Z digest=sha256:4e0403d604c8db4726b10df05da4f2796e79316df10e66d8cbe0975614826b67

Observation d7693d84-949c-47c1-b988-792a8a5f39ef · outbound

This paper cites Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:16.084477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:16.084477Z digest=sha256:31a970451f4c413927399a6e4f7de7eb124dc53d4c923be9fbf807f871c20afa

Observation 72f94ea1-8506-4516-bdc6-01c7f72b5298 · outbound

This paper cites Vmamba: Visual state space model.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Vmamba: Visual state space model

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.641281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.091637Z digest=sha256:4af07c6f9c560c686566fbf668f6fa5bdac3cf89a22844ecf696b29bfe79a219

Observation 827820b8-062f-41b2-8c32-728df373fe09 · outbound

This paper cites Decoupled weight decay regularization.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Decoupled weight decay regularization

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:16.102327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:16.102327Z digest=sha256:db4ec36ab41c85859da1853ba36e29e187cb35f058f6760f7fa253ccf86b6dba

Observation 80b15b35-b0ab-4eda-9e37-93a6d9b43dce · outbound

This paper cites Token pooling in vision transformers.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Token pooling in vision transformers

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.528793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.109348Z digest=sha256:325faa19e0a34e26dde83366541a3260a6249124d95b28911041d4e091ef3154

Observation 77372112-d9e4-4455-8d38-d3f815fb4642 · outbound

This paper cites Long range language modeling via gated state spaces.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Long range language modeling via gated state spaces

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.504580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.116538Z digest=sha256:d235ad51e26d79758c59c35569e1d6c9de7edf6ebe629acea29e2725a6aa765e

Observation 79df1505-5d56-4049-bfa0-293efc1ecaad · outbound

This paper cites Adavit: Adaptive vision transformers for efficient image recognition.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Adavit: Adaptive vision transformers for efficient image recognition

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.465820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.126858Z digest=sha256:9add6f1a0aafc9a1faa3078b336136c6c4c9f13b0eff92c622738910c156f103

Observation d25a2078-984d-4080-b5a8-b3eeaddd2a2d · outbound

This paper cites SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:16.137321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:16.137321Z digest=sha256:f65c8ef9c4c2754ae011a44c2307d0a568d41c50fc6908b64fdee9174d55c0f8

Observation 529ebcb7-eb87-48b1-bc21-dd4c65412677 · outbound

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

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:16.151633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:16.151633Z digest=sha256:d5c48c5d614a9fad3a653aab270881e8bb3b39c39d7fcc5ed22767b401f364c8

Observation ff0c8697-123e-46a2-8e6d-3e0ad95060e7 · outbound

This paper cites An introduction to the infiniband architec- ture.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training An introduction to the infiniband architec- ture

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.441508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.157785Z digest=sha256:77825417ccb843787ec2828f788fdb8d0b36f1f2477e00bf5947030e14e76e9a

Observation 369b4953-0399-4eab-86fa-7accf24fca4f · outbound

This paper cites VL-Mamba: Exploring State Space Models for Multimodal Learning.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training VL-Mamba: Exploring State Space Models for Multimodal Learning

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:16.165092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:16.165092Z digest=sha256:5a94df96bf413dce9244c1245dfd4fd5ebb65151085dd2aea79a19100eb8246b

Observation a57b5355-ed44-42c8-b369-a91bc3003c82 · outbound

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

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Dynamicvit: Efficient vision transformers with dynamic token sparsification

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.397762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.173463Z digest=sha256:8acfd189f5e79a1bff51cc3dbe13c39d607fb1f9acf82b51d3e7bc4694b8012c

Observation ac852e82-60fe-4190-86f6-6feb194eec4e · outbound

This paper cites VM-UNet: Vision Mamba UNet for Medical Image Segmentation.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training VM-UNet: Vision Mamba UNet for Medical Image Segmentation

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:16.188046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:16.188046Z digest=sha256:f064158400a7e331564537dc3eba6a352a80d3841088174a69c937ad6db94c44

Observation 21e975b2-2d83-48bd-a5a6-f5285437376c · outbound

This paper cites Tokenlearner: Adaptive space-time tokenization for videos.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Tokenlearner: Adaptive space-time tokenization for videos

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.355249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.202401Z digest=sha256:b7e69c9b9a05c334945eb100ace003cbb773b3bcf0e09a3c813820365608a026

Observation 5d6d4f5c-4f1d-40f4-a63f-63a1b3b67bbb · outbound

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

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:16.209541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:16.209541Z digest=sha256:8045bb2e59d1489f6fcbb00780e6de36af4137d55674472e43accf4b627a1aa2

Observation 95565a0e-2264-47ba-a004-1d2dd8b09585 · outbound

This paper cites Simplified state space layers for sequence modeling.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Simplified state space layers for sequence modeling

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.308083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.215461Z digest=sha256:6d9a42f4294c6708f732ce0cb946053bc72c886688ab65d471fb28a398a159f9

Observation f0217408-51cf-42c4-b39e-203911660f00 · outbound

This paper cites CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:16.226732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:16.226732Z digest=sha256:737460783e708fc32a859eb2e7721e716b2dee5d82386f8fe5b97e832f43f4bc

Observation b2ad3ad0-6053-418b-9bce-85171e124d68 · outbound

This paper cites Deep learning and the information bottleneck principle.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Deep learning and the information bottleneck principle

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.262382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.236094Z digest=sha256:da19572279996b3a92f069df35c34d19612a17248e57d10dd97f7ee7efe47a23

Observation 834bd0bd-d34c-48ee-ae3c-41436ab54432 · outbound

This paper cites The information bottleneck method.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training The information bottleneck method

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:16.242892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:16.242892Z digest=sha256:dc342feaec04207ebe7fb88161ec6072b211dac02e9e2c8c436f0fee4c791138

Observation 9e392021-6575-4a58-bfc4-6c4e9c3747cf · outbound

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

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Training data-efficient image transformers & distillation through at- tention

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.230745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.250297Z digest=sha256:82db0a8a5008e93faca7389a3e90da0884a7bb7323dc63b5012398bada723532

Observation d526439c-fb22-464f-a192-fbf6eee17338 · outbound

This paper cites Attention is all you need.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Attention is all you need

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.203429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.259279Z digest=sha256:fc78a41968650b989386fc50f666f24a2c21f14200cbbb04acceb9bec1f46572

Observation a25b7e45-dad1-4e39-a13a-f260ef7a081c · outbound

This paper cites Groupvit: Semantic segmentation emerges from text supervision.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Groupvit: Semantic segmentation emerges from text supervision

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.182037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.267703Z digest=sha256:be7f7cbef3e19e3ad87b17bd72861777cd4b34e74d9ebb655ce134b7f677dad7

Observation bd399c02-bc4f-43cd-a293-20bf0fae9417 · outbound

This paper cites PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:16.276421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:16.276421Z digest=sha256:d348bfe030a01b6d4d478877cde56a5bf57e4bee41011d2d7e5da126cda2926d

Observation 78a9bdaf-01cd-4c4e-8dec-36a5ffc99716 · outbound

This paper cites an unresolved cited work.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Unresolved cited work

Reference 49

Resolution
unresolved
raw_fallback, observed 2026-08-11T14:07:17.153488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.283139Z digest=sha256:4cbbe44f02a79b5d85cb96a4f90ddd32d95f73c7d81d33be249ae6319358d4e9

Observation f8d704be-9a13-476f-81b5-35c35840c6c5 · outbound

This paper cites Vivim: a Video Vision Mamba for Medical Video Segmentation.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Vivim: a Video Vision Mamba for Medical Video Segmentation

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:16.290069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:16.290069Z digest=sha256:f755177587acf7dc407f2430285333883e2c7706a71dc81fd2fdcecb81ce533e

Observation 51419cf1-637c-4ab7-8ce6-6a36d5681ade · outbound

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

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training A-vit: Adaptive tokens for efficient vision transformer

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.125221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.298785Z digest=sha256:182e1801ba5ede353d323161388c9355dfbc83efdaa6b90d5a95f019b0782ebd

Observation 0396535f-4d00-417b-84d4-94e3ef153d5b · outbound

This paper cites Exploring token pruning in vision state space models.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Exploring token pruning in vision state space models

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.091277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.309233Z digest=sha256:0c9764f7ca5b9fdbc7ffccbae485f05e3cd7f7829ec957b08dfe34baaac3f6b4

Observation 7608ee85-0648-4fc6-9398-bb480df086f1 · outbound

This paper cites Point Cloud Mamba: Point Cloud Learning via State Space Model.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Point Cloud Mamba: Point Cloud Learning via State Space Model

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-11T14:07:16.317365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T14:07:16.317365Z digest=sha256:20a24a99edc53b0e4a599192f0943b90e9372c8d47d115addb33ea94b9b4565a

Observation 5b9c7ee0-5765-4679-b0ca-f4580825565a · outbound

This paper cites Motion mamba: Efficient and long sequence motion generation.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Motion mamba: Efficient and long sequence motion generation

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.066226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.328584Z digest=sha256:671bafe01f00da308d2594536a1d85f3336e14b53775d9c12e14fc4d7030af5c

Observation afa6c6eb-78c9-4f68-a2b3-33ed0394f71b · outbound

This paper cites Vision mamba: Efficient visual representation learning with bidirectional state space model.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training Vision mamba: Efficient visual representation learning with bidirectional state space model

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.034723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.335100Z digest=sha256:85cb8f33b91ad580fb0d2d364f7cedc75323d7764147985d3fcccab813cd3e25

Observation 8fdd0203-497a-4bda-af05-48af51b65cfa · outbound

This paper cites This change allows us to assess the importance of selecting the top-r operations versus randomly choosing r candidate to- kens.

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training This change allows us to assess the importance of selecting the top-r operations versus randomly choosing r candidate to- kens

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T14:07:17.002649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-11T14:07:16.342170Z digest=sha256:1edfe5ff00bba3da4e238efb8b5e9ace57b1a851bb7ace8468973f41c4b496f0

Pith citing papers

Observation 6d9dd944-ab54-4815-8b6e-9f8fc7d9b6f2 · inbound

Exploring Kolmogorov-Arnold Network Expansions in Vision Transformers for Mitigating Catastrophic Forgetting in Continual Learning cites this paper.

Exploring Kolmogorov-Arnold Network Expansions in Vision Transformers for Mitigating Catastrophic Forgetting in Continual Learning Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-06T20:01:11.371367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:01:11.371367Z digest=sha256:7f9855cddea79571c12356ea89359e3a701fe143f8c986281ff924c94b5d4c0e

Observation ee770119-5eb2-4921-8e8a-d29486685686 · inbound

QuarterMap: Efficient Post-Training Token Pruning for Visual State Space Models cites this paper.

QuarterMap: Efficient Post-Training Token Pruning for Visual State Space Models Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-06T17:59:30.946262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T17:59:30.946262Z digest=sha256:71c4a6bab4d72f7a53dc04aca9987561220b2e41ae91e03af444f6ffdd4d1b23

Observation b4fe3363-0614-42a7-95fc-37008ae591bc · inbound

Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models cites this paper.

Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training

Reference 106

Resolution
verified exact
arxiv_id, observed 2026-07-04T03:39:29.536278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=arxiv_source observed=2026-06-26T17:53:38.503877Z digest=sha256:e0a018d182c83223b219d2c47d489025e137faf437b7fc6033cd5952a75f19b7