Paper Citation Record · LEDGER

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models

As of 6 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2605.13375.

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

pith.paper-citation-record.v1
2605.13375 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-14T19:15:13.205594Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

42 of 42 outbound references displayed

verified exact16
verified fuzzy25
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c517aff6-f6d2-4768-929b-ed4bf980772d · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.117329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8cff7443-81f2-4ae9-a985-b13d792f7200 · outbound

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

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:17:50.756941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d83dc8ba-3a99-492a-9398-c1c3c92df709 · outbound

This paper cites Improved baselines with visual instruction tuning.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Improved baselines with visual instruction tuning

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.121890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e23d07a7-28ae-4173-a89c-86cf1e426026 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Visual instruction tuning.Advances in neural information processing systems

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.126711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 27be793a-9cc5-4b91-88c6-9813ead50fc1 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:17:50.749786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7e907cc3-cd78-41d9-acc3-44c064633476 · outbound

This paper cites The Llama 3 Herd of Models.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models The Llama 3 Herd of Models

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:17:50.762418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 14720828-cb05-44e2-a3d0-8bf9473d259c · outbound

This paper cites Qwen Technical Report.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Qwen Technical Report

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:17:50.768044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ba6c2b71-a99f-41a4-a12d-708ff2c80317 · outbound

This paper cites Qwen2.5 Technical Report.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Qwen2.5 Technical Report

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:17:50.785305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 62663dba-f79a-442d-b3fa-bbb6a665b7db · outbound

This paper cites Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-14T19:17:50.819402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f37c86b6-fbc2-4b30-a1a2-112474976abd · outbound

This paper cites Internvideo2: Scaling video foundation models for multimodal video understanding.Arxiv e-prints, pages arXiv–2403.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Internvideo2: Scaling video foundation models for multimodal video understanding.Arxiv e-prints, pages arXiv–2403

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:31:33.511181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d98ab346-77fb-4b13-9544-93c49b75b348 · outbound

This paper cites Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-14T19:17:50.811951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 97efd2c1-4cd3-4cf7-98d8-60f29608211d · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.017253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 942b7986-1252-47f9-8b46-db1d21578ef7 · outbound

This paper cites Qwen2.5-vl technical report.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Qwen2.5-vl technical report

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.045910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9e041039-bc6a-4e0d-a90d-44ec21f78f2f · outbound

This paper cites Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-17T07:44:47.683285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 42f656de-bbed-48e0-af1e-38644ace1ebc · outbound

This paper cites In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1207–1216.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1207–1216

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T19:17:50.798831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8a55e99f-20c1-41ae-bdf9-fa694754708a · outbound

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

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Llava-prumerge: Adaptive token reduction for efficient large multimodal models

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-14T19:17:50.792438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cf81fa2d-4e0e-4663-8e9d-6d135465d057 · outbound

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

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.093017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2876ae61-2a2e-4ddd-8fc3-e6edf48d55dc · outbound

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

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Sparsevlm: Visual token sparsification for efficient vision-language model inference

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.087782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fafd32d3-7b06-4cb4-8b3d-f098384652b7 · outbound

This paper cites Token merging: Your vit but faster.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Token merging: Your vit but faster

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.041341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 001e77ed-87ee-41e7-a706-7678085aa48c · outbound

This paper cites Framefusion: Combining similarity and importance for video token reduction on large vision language models.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Framefusion: Combining similarity and importance for video token reduction on large vision language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.032076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 406b3d0f-0746-4229-ac86-6b0547434ea0 · outbound

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

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Dynamicvit: Efficient vision transformers with dynamic token sparsification

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:31:33.520559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b294bdee-7fdc-4773-9b5b-15ac212bfd8e · outbound

This paper cites Smarttrim: Adaptive tokens and attention pruning for efficient vision-language models.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Smarttrim: Adaptive tokens and attention pruning for efficient vision-language models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:31:33.524662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1f8081c2-751a-483a-bc72-76116d8f089b · outbound

This paper cites Visionselector: End-to-end learnable visual token compression for efficient multimodal llms.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Visionselector: End-to-end learnable visual token compression for efficient multimodal llms

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.082831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 16e4cb1c-cbaf-48ed-9bd7-0fa66784b4e2 · outbound

This paper cites Efficient multi-modal large language models via progressive consistency distillation.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Efficient multi-modal large language models via progressive consistency distillation

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.107841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2977d013-112d-4498-b2e5-6dfc73ffaa3d · outbound

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

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models An image is worth 16x16 words: Transformers for image recognition at scale

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.073062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 232a81b5-dff8-4c7f-adb9-9021a270e528 · outbound

This paper cites Instructblip: Towards general-purpose vision-language models with instruction tuning.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Instructblip: Towards general-purpose vision-language models with instruction tuning

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.036573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4e1e9b15-5537-4968-aa6f-ab794d2ab01d · outbound

This paper cites Llava-next: Improved reasoning, ocr, and world knowledge, January 2024.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Llava-next: Improved reasoning, ocr, and world knowledge, January 2024

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.022689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d6234653-aa1e-496f-9d94-a5d7c58ec71b · outbound

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

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models LLaVA-OneVision: Easy Visual Task Transfer

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:17:50.780093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 204b7347-2110-4eb7-bbdc-7a15872115fd · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:17:50.824171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2894c32c-03d0-45ff-8cf1-628b324c22d6 · outbound

This paper cites Qwen2.5-VL Technical Report.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Qwen2.5-VL Technical Report

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:17:50.774101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5e7a0828-266f-44f0-981e-5f06a324a12e · outbound

This paper cites Attention is all you need.Advances in neural information processing systems, 30.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Attention is all you need.Advances in neural information processing systems, 30

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.027652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 01acc121-5f1e-419a-bd97-6bb4d4ed9dca · outbound

This paper cites Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-14T19:17:50.839649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 06aa54cb-1a7a-4416-aa69-5b7e6356ad6d · outbound

This paper cites Film: Visual reasoning with a general conditioning layer.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Film: Visual reasoning with a general conditioning layer

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.112409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 63ef317b-ac85-4a25-ac83-29ad5f54fa58 · outbound

This paper cites Sft or rl? an early investigation into training r1-like reasoning large vision-language models.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Sft or rl? an early investigation into training r1-like reasoning large vision-language models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:31:33.528814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 01623c75-8ef5-4c04-a3f4-4c736f1406e4 · outbound

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

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:17:50.844426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8929df7f-efb7-4e82-98ee-24b299109575 · outbound

This paper cites Evaluating Object Hallucination in Large Vision-Language Models.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Evaluating Object Hallucination in Large Vision-Language Models

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:17:50.804755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cf90a508-84b8-4496-83ce-544465813af4 · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.Advances in Neural Information Processing Systems, 35:2507–2521.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Learn to explain: Multimodal reasoning via thought chains for science question answering.Advances in Neural Information Processing Systems, 35:2507–2521

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.098008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cf64293f-0f2b-4f7b-b18f-67484eccb2ca · outbound

This paper cites Towards vqa models that can read.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Towards vqa models that can read

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.102959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bf289a30-9e9a-4147-a3fe-367855a28437 · outbound

This paper cites A diagram is worth a dozen images.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models A diagram is worth a dozen images

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.065991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2835d0ef-7f8f-4f45-b5f1-9a2361fad672 · outbound

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

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:51:34.077728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cf4eb7f7-0569-4c19-88f2-f3548d869dde · outbound

This paper cites MMBench: Is Your Multi-modal Model an All-around Player?.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models MMBench: Is Your Multi-modal Model an All-around Player?

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:17:50.833919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8b473c9e-256e-4ab2-ad61-0ae7543b54bb · outbound

This paper cites Ocrbench: on the hidden mystery of ocr in large multimodal models.Science China Information Sciences, 67(12):220102.

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models Ocrbench: on the hidden mystery of ocr in large multimodal models.Science China Information Sciences, 67(12):220102

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T19:31:33.515784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

No inbound Pith citation observations are available.