Paper Citation Record · LEDGER

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference

As of 17 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2607.16326.

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

pith.paper-citation-record.v1
2607.16326 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T03:42:16.353153Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

30 of 30 outbound references displayed

verified exact0
verified fuzzy0
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 22e10980-24c3-4109-b9ec-fe6d9a67ee10 · outbound

This paper cites A survey of state of the art large vision language models: Benchmark evaluations and challenges,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference A survey of state of the art large vision language models: Benchmark evaluations and challenges,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:13.962870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2e7303d-8d63-4d0b-a2ec-b2d66a03a22c · outbound

This paper cites An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.029230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffc841a0-501a-4e7a-8a12-df7467060223 · outbound

This paper cites [cls] attention is all you need for training-free visual token pruning: Make vlm inference faster,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference [cls] attention is all you need for training-free visual token pruning: Make vlm inference faster,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.088093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb80ec59-6fda-4a39-a281-9eb459c21c3f · outbound

This paper cites Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.167493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcb18766-f096-4f16-9ae0-344f2ddf65fd · outbound

This paper cites Visionzip: Longer is better but not necessary in vision language models,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Visionzip: Longer is better but not necessary in vision language models,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.225585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3f840ac-ea02-43e2-9cf5-8fcc758c8011 · outbound

This paper cites Divprune: Diversity- based visual token pruning for large multimodal models,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Divprune: Diversity- based visual token pruning for large multimodal models,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.268413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2747e3b-6ba8-4f41-84f1-43088a6a4d92 · outbound

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

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Sparsevlm: Visual token sparsification for efficient vision-language model inference,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.328001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation deb8fc81-c2ea-47af-a648-ca7099b13bd2 · outbound

This paper cites Which experimental design is better suited for vqa tasks?: Eye tracking study on cognitive load, performance, and gaze allocations,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Which experimental design is better suited for vqa tasks?: Eye tracking study on cognitive load, performance, and gaze allocations,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.387140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf119c7b-0c1e-4101-8c49-904514bb2413 · outbound

This paper cites Making the invisible visible: Verbal but not visual cues enhance visual detection,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Making the invisible visible: Verbal but not visual cues enhance visual detection,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.451408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84348696-6677-4790-919f-ea30c9956231 · outbound

This paper cites Beyond text-visual attention: Exploiting visual cues for effective token pruning in vlms,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Beyond text-visual attention: Exploiting visual cues for effective token pruning in vlms,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.510468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afcfed36-0ac4-44ac-8e3d-7e56bab9427b · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.568395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a87a12c8-fe66-4e61-b471-5a5b9fb3f6f8 · outbound

This paper cites Improved baselines with visual instruction tuning,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Improved baselines with visual instruction tuning,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.614845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f349ea5-b27c-4a40-aabb-1980a500fb4f · outbound

This paper cites Llava-next: Improved reasoning, ocr, and world knowledge,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Llava-next: Improved reasoning, ocr, and world knowledge,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.672964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b78eb07-ce38-47e4-906f-82d0d86ed7e6 · outbound

This paper cites A-vl: Adaptive attention for large vision-language models,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference A-vl: Adaptive attention for large vision-language models,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.747206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43bb17fe-eb23-4fad-ba9e-8ac6e71a801b · outbound

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

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Llava-prumerge: Adaptive token reduction for efficient large multimodal models,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.810397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6c1fd54-da0e-4dc4-85b6-278d6826381c · outbound

This paper cites Hired: Attention-guided token dropping for efficient inference of high-resolution vision-language models,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Hired: Attention-guided token dropping for efficient inference of high-resolution vision-language models,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.869453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e8570fb-3b5f-477d-a0d0-4f7da959d9b4 · outbound

This paper cites PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.917470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e70aee6f-94b2-4f0e-893a-450614b14839 · outbound

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

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Token merging: Your vit but faster,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.968369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9be3d9bc-25e7-4233-9703-6ef794af667e · outbound

This paper cites Less is more: A simple yet effective token reduction method for efficient multi-modal llms,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Less is more: A simple yet effective token reduction method for efficient multi-modal llms,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.973153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cac17e1-2c7a-41fb-9ea6-fe26463ff5d8 · outbound

This paper cites Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:14.989028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb6895fa-9c7e-47b1-948a-5c12c1dfccec · outbound

This paper cites en core web sm: spacy english small model,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference en core web sm: spacy english small model,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:15.064940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa5edcd7-3e17-4763-95cc-a265e3619c42 · outbound

This paper cites Making the v in vqa matter: Elevating the role of image understanding in visual question answering,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Making the v in vqa matter: Elevating the role of image understanding in visual question answering,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:15.224141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ee3588a-2ed4-48ec-a572-b6008311a5bb · outbound

This paper cites Vizwiz grand challenge: Answering visual questions from blind people,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Vizwiz grand challenge: Answering visual questions from blind people,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:15.385887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b291d16-1ac2-4445-9add-45ac222e2926 · outbound

This paper cites Gqa: A new dataset for real-world visual reasoning and compositional question answering,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Gqa: A new dataset for real-world visual reasoning and compositional question answering,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:15.538454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e23e9de6-19a2-423b-9be8-701099206de4 · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Learn to explain: Multimodal reasoning via thought chains for science question answering,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:15.652552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ac73fdb-ead5-4f4c-a603-1df1de942469 · outbound

This paper cites Towards vqa models that can read,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Towards vqa models that can read,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:15.811440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0dc2b26-e124-494d-8b8a-f0c40c015cc9 · outbound

This paper cites Evaluating object hallucination in large vision-language models,.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Evaluating object hallucination in large vision-language models,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:15.972178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf4a3d85-1401-493d-9782-227dffb6d8ee · outbound

This paper cites MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:16.140370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ccc400f-956c-4576-9587-b505246e1706 · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player?.

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Mmbench: Is your multi-modal model an all-around player?

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:16.307600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6462f743-c873-4b9f-8e30-c2f19f1637fd · outbound

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

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference Mm-vet: evaluating large multimodal models for integrated capabilities,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T03:42:16.353153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.