Paper Citation Record · LEDGER

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning

As of 7 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 4 inbound Pith citation observations for arXiv:2506.21873.

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

pith.paper-citation-record.v1
2506.21873 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T22:22:38.056203Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T04:26:51.521243Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T11:28:04.115693Z

Reference resolution

33 of 33 outbound references displayed

verified exact1
verified fuzzy14
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 87ff0b8a-ca3b-4887-b17f-c9c0cec093d5 · outbound

This paper cites Learning Transferable Visual Models From Natural Language Supervision.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Learning Transferable Visual Models From Natural Language Supervision

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:34.222152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a4d00e1-d3d4-4eff-8769-671d4229e0c0 · outbound

This paper cites Lmms-eval: Accelerating the development of large multimoal models, 2024.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Lmms-eval: Accelerating the development of large multimoal models, 2024

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:22:40.797436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 13662c94-8ae8-41ee-ae62-f8865c5086aa · outbound

This paper cites an unresolved cited work.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:34.453915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed13873d-7303-41c2-887f-f70ad36352f5 · outbound

This paper cites PuMer: Pruning and merging tokens for efficient vision language models.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning PuMer: Pruning and merging tokens for efficient vision language models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:22:40.638759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3f9feba8-b212-40bb-b00d-6e25488e19e9 · outbound

This paper cites Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:34.600551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5af470b7-381b-4a2d-9d38-e97d8fc76450 · outbound

This paper cites Chasing sparsity in vision transform- ers: An end-to-end exploration.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Chasing sparsity in vision transform- ers: An end-to-end exploration

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:22:40.493296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7977b23f-3ab8-4e3b-a190-dbfb2a7e998a · outbound

This paper cites Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:36.892337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc0b8107-ea83-4856-9830-afdc21830e16 · outbound

This paper cites Bert: Pre-training of deep bidirectional trans- formers for language understanding, 2019.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Bert: Pre-training of deep bidirectional trans- formers for language understanding, 2019

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:22:40.317527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9d0203be-a9ae-4267-b819-47f2116e220d · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:37.063835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80d3a7ef-ddd5-48d5-8a6d-db11f437122b · outbound

This paper cites Mme: A compre- hensive evaluation benchmark for multimodal large language models, 2024.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Mme: A compre- hensive evaluation benchmark for multimodal large language models, 2024

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:22:40.112200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6252318a-6096-4ab7-8ba4-8f2660f663eb · outbound

This paper cites Stangl, Anhong Guo, Chi Lin, Kristen Grauman, Jiebo Luo, and Jeffrey P.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Stangl, Anhong Guo, Chi Lin, Kristen Grauman, Jiebo Luo, and Jeffrey P

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:22:39.929819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 96308886-7034-4e99-b06c-ec9193ca46fc · outbound

This paper cites Ferret: Refer and Ground Anything Anywhere at Any Granularity.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Ferret: Refer and Ground Anything Anywhere at Any Granularity

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:37.288321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94758521-e0ad-4fef-9396-4cb57a0b7a2c · outbound

This paper cites Hudson and Christopher D.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Hudson and Christopher D

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:22:39.759716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7ffded63-3567-47ec-910b-4f75f5548ef0 · outbound

This paper cites MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:37.354640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5177977-f620-44b3-af16-da781b15a257 · outbound

This paper cites MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:37.398957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1047d42b-4035-4686-8f2f-34b0c62f05e4 · outbound

This paper cites ReferItGame: Referring to objects in pho- tographs of natural scenes.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning ReferItGame: Referring to objects in pho- tographs of natural scenes

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:22:39.581887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6aaf2107-1780-41a2-9582-3bfcd228cdca · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning LLaVA-OneVision: Easy Visual Task Transfer

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:37.486139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b850b5a-68b8-422d-8942-b13c090b933f · outbound

This paper cites Improved baselines with visual instruction tuning, 2023.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Improved baselines with visual instruction tuning, 2023

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:22:39.392107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 68059e97-b956-4043-b2dd-cd8c386fdc96 · outbound

This paper cites Visual instruction tuning.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Visual instruction tuning

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:22:39.211131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a98f1f51-a427-4ee7-8008-049e208faa8f · outbound

This paper cites Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:22:39.048593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 56f3c6af-f16a-4ade-a470-9398eb3fad83 · outbound

This paper cites Ok-vqa: A visual question answer- ing benchmark requiring external knowledge.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Ok-vqa: A visual question answer- ing benchmark requiring external knowledge

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:22:38.868981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 54baaea2-b91c-4979-b628-4e52c11da981 · outbound

This paper cites Llava-prumerge: Adaptive token reduction for efficient large multimodal models.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Llava-prumerge: Adaptive token reduction for efficient large multimodal models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:37.656404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 503b3c1d-7e40-4cf9-b445-c27e3b6e1c85 · outbound

This paper cites Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:37.694996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8632f363-36a1-41db-8844-8a1c699956a1 · outbound

This paper cites Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:37.715782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f131960-fa44-40a5-9d6e-9b4f5b04fd33 · outbound

This paper cites SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-06T22:22:38.253638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9006af8c-53da-4f81-ac21-12430f38a059 · outbound

This paper cites CogVLM: Visual Expert for Pretrained Language Models.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning CogVLM: Visual Expert for Pretrained Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:37.779534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 740a8bef-e1ff-46b1-89b5-71d8a266bd68 · outbound

This paper cites Sigmoid Loss for Language Image Pre-Training.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Sigmoid Loss for Language Image Pre-Training

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:37.804075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0abc5a8-7da7-4a9b-b116-4f52f17b07b3 · outbound

This paper cites Referring Expression Comprehension: A Survey of Methods and Datasets.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Referring Expression Comprehension: A Survey of Methods and Datasets

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:37.839061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00fd528a-580c-476a-9dff-37e14e2d1699 · outbound

This paper cites Sparsity Meets Similarity: Leveraging Long-Tail Distribution for Dynamic Optimized Token Representation in Multimodal Large Language Models.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Sparsity Meets Similarity: Leveraging Long-Tail Distribution for Dynamic Optimized Token Representation in Multimodal Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:37.891208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f291d98b-bdaa-49bb-bf10-0afed6d4abc4 · outbound

This paper cites Mm-vet: Evaluating large multimodal models for integrated capabilities, 2023.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Mm-vet: Evaluating large multimodal models for integrated capabilities, 2023

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:22:38.683766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a7432697-617b-4d76-9b68-62afca620f25 · outbound

This paper cites EVA: Exploring the Limits of Masked Visual Representation Learning at Scale.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning EVA: Exploring the Limits of Masked Visual Representation Learning at Scale

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T22:22:37.974207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

This paper cites Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs.

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 8406bbc7-9c0c-4615-b864-0bf5b81d436a · outbound

This paper cites Sparsevlm: Visual token sparsification for efficient vision- language model inference.

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning Sparsevlm: Visual token sparsification for efficient vision- language model inference

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:22:38.533842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation 1d10623c-83fb-4f45-95cd-23b3146a6d3d · inbound

Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models cites this paper.

Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-03T11:28:04.117867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dd37fb2c-b09e-4a78-b543-4a85336b2d2f · inbound

Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning cites this paper.

Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T10:15:45.167041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9580cabb-5320-4a7c-ba02-205e08d07265 · inbound

Beyond Accuracy: Auditing Spatial Provenance in Visual Token Pruning for OCR-Critical MLLM Inference cites this paper.

Beyond Accuracy: Auditing Spatial Provenance in Visual Token Pruning for OCR-Critical MLLM Inference Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-04T01:29:54.348125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1208ac5a-4bec-4880-8f3e-70d05e81322a · inbound

Beyond Accuracy: Auditing Spatial Provenance in Visual Token Pruning for OCR-Critical MLLM Inference cites this paper.

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:51.521243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.