Paper Citation Record · LEDGER

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 27 inbound Pith citation observations for arXiv:2412.01818.

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

pith.paper-citation-record.v1
2412.01818 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 27 of 27 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 27 of 27 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T15:48:05.534196Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T22:17:26.122002Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 4d590f45-b32e-4d8f-9566-7aa62d9e1872 · inbound

Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models cites this paper.

Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-05-23T00:02:17.826191Z

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 a152e2cf-71b3-4838-ae5a-24f22fbedff1 · inbound

AdaTP: Attention-Debiased Token Pruning for Video Large Language Models cites this paper.

AdaTP: Attention-Debiased Token Pruning for Video Large Language Models Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:08:10.568820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfa4e81f-0ea0-49af-aad9-41a331e93e78 · inbound

FlexSelect: Flexible Token Selection for Efficient Long Video Understanding cites this paper.

FlexSelect: Flexible Token Selection for Efficient Long Video Understanding Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T11:59:10.721952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71ec673b-1526-4118-a103-06c1a1fd7bbf · inbound

Do Concept Replacement Techniques Really Erase Unacceptable Concepts? cites this paper.

Do Concept Replacement Techniques Really Erase Unacceptable Concepts? Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:22.689471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1a373ab-ce2e-4b1e-8eac-7867ae7a5305 · inbound

GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language Models cites this paper.

GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language Models Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T00:42:53.731513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de3b0a21-a37f-471b-b485-d88fd6c34fe7 · inbound

Structured Attention Matters to Multimodal LLMs in Document Understanding cites this paper.

Structured Attention Matters to Multimodal LLMs in Document Understanding Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T23:47:39.833498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 027bcc54-980e-4005-976e-4024bede4f92 · inbound

LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs cites this paper.

LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 102

Resolution: unresolved; no resolver link, observed 2026-08-06T22:24:36.069967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9769bad8-5242-44f0-8796-3fb811209059 · inbound

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning cites this paper.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:38.007759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db89bafa-0a57-4cdb-9ed4-0046b86f872e · inbound

AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding cites this paper.

AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 113

Resolution: unresolved; no resolver link, observed 2026-08-06T20:29:56.989156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e34a4b6-98fa-45e8-929f-7b2dce7e4b12 · inbound

Training-free Token Reduction for Vision Mamba cites this paper.

Training-free Token Reduction for Vision Mamba Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T16:16:49.501635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18328f71-a4db-42db-a401-0e22267c7c09 · inbound

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models cites this paper.

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-06T13:18:05.802359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation feaaf656-4822-432f-856a-1c299155dab3 · inbound

A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models cites this paper.

A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T05:37:35.455914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8b6add4-2c32-4340-9e76-eb965d4975ed · inbound

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression cites this paper.

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-05T13:42:28.922349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b8ff788-206e-4cad-bc21-8ee7d2dc6826 · inbound

ID-Selection: Importance-Diversity Based Visual Token Selection for Efficient LVLM Inference cites this paper.

ID-Selection: Importance-Diversity Based Visual Token Selection for Efficient LVLM Inference Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:35:51.376207Z

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 7dfed331-4316-49bf-b658-c03c40981a1b · inbound

Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding cites this paper.

Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 56

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T10:26:01.376382Z

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 934549df-7e05-41c0-912b-9f82bb5c1873 · inbound

Evading Visual Aphasia: Contrastive Adaptive Semantic Token Pruning for Vision-Language Models cites this paper.

Evading Visual Aphasia: Contrastive Adaptive Semantic Token Pruning for Vision-Language Models Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-12T07:36:37.432782Z

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 9f0a851d-c669-4ddd-b934-f862a7070ee4 · inbound

ERASE: Eliminating Redundant Visual Tokens via Adaptive Two-Stage Token Pruning cites this paper.

ERASE: Eliminating Redundant Visual Tokens via Adaptive Two-Stage Token Pruning Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:31:25.369861Z

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 a9079ea7-51fd-418c-a080-ce9acb14dd8c · inbound

LRCP: Low-Rank Compressibility Guided Visual Token Pruning for Efficient LVLMs cites this paper.

LRCP: Low-Rank Compressibility Guided Visual Token Pruning for Efficient LVLMs Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:08:54.487547Z

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 37f6b381-e56a-4e33-a38a-e603e6bee3fa · inbound

Locality Matters for Training-Free Audio Token Compression in Audio-Language Models cites this paper.

Locality Matters for Training-Free Audio Token Compression in Audio-Language Models Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T11:44:38.351501Z

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 470d56ab-54bb-4b1e-87db-372c9e49ec2f · inbound

Look Less, Reason More: Block-wise Attention Skipping for Efficient Multimodal LLMs cites this paper.

Look Less, Reason More: Block-wise Attention Skipping for Efficient Multimodal LLMs Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:17:26.123720Z

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 9afba30e-add1-4789-94e4-34aad4b59574 · inbound

MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs cites this paper.

MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T10:15:44.594522Z

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 31e0ae82-63bd-4e86-aa8f-789c4ea6cec9 · inbound

Structured Redundancy Modeling for Efficient Visual Token Pruning in High-Resolution MLLMs cites this paper.

Structured Redundancy Modeling for Efficient Visual Token Pruning in High-Resolution MLLMs Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T03:50:32.497038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cab3c0a-6146-49ac-bb56-15432c60c487 · inbound

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models cites this paper.

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T01:26:49.636465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ff5e9df-6bdd-44d4-964f-969d81b032dd · inbound

Calibrate Before Reason: Robust Visual Token Reduction against Semantic Drift in VLMs cites this paper.

Calibrate Before Reason: Robust Visual Token Reduction against Semantic Drift in VLMs Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T03:07:43.698719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe0ca0c7-afc8-4328-9ca5-3091f69bb5b4 · inbound

Capturing Token Tendencies for Training-Free Token Pruning in Multimodal Large Language Models cites this paper.

Capturing Token Tendencies for Training-Free Token Pruning in Multimodal Large Language Models Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-31T10:42:21.341740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8e56e5f-2d4b-4c0a-ba66-b94aabab9a82 · inbound

When Do Fewer Visual Tokens Accelerate Multimodal Inference? A Break-Even Study Across Decision Locations and Hardware cites this paper.

When Do Fewer Visual Tokens Accelerate Multimodal Inference? A Break-Even Study Across Decision Locations and Hardware Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T15:19:02.843428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00f90a41-8bbb-41cb-a3f2-5cb76184f4b1 · inbound

EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding cites this paper.

EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-08T15:48:05.534196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.