Paper Citation Record · LEDGER

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention

As of 5 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 4 inbound Pith citation observations for arXiv:2602.07574.

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

pith.paper-citation-record.v1
2602.07574 v2

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T03:36:43.892124Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T18:16:46.738649Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-04T08:19:44.559138Z

Reference resolution

36 of 36 outbound references displayed

verified exact0
verified fuzzy0
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c941f91f-458d-424b-bfee-57c79342a20f · outbound

This paper cites GPT-4 Technical Report.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.786045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66d283e1-b9c9-4aac-a3a6-5ebdbb55a070 · outbound

This paper cites From llms to lrms: Rethinking pruning for reasoning-centric models.arXiv preprint arXiv:2601.18091,.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention From llms to lrms: Rethinking pruning for reasoning-centric models.arXiv preprint arXiv:2601.18091,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.797433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e581471b-eaaa-4f14-bc2b-e3565ed59700 · outbound

This paper cites Visipruner: Decoding discontinuous cross-modal dynamics for efficient multimodal llms.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Visipruner: Decoding discontinuous cross-modal dynamics for efficient multimodal llms

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.800697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba9bde6f-dc17-470b-b9ca-27ae5a9e6181 · outbound

This paper cites The framework tax: Disparities between inference effi- ciency in NLP research and deployment.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention The framework tax: Disparities between inference effi- ciency in NLP research and deployment

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.803774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a00e5172-ce7a-4dab-a7b9-6aceeea84fb6 · outbound

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

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.806789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 725bcd9b-1c9d-45b9-85f1-f21bfefa4233 · outbound

This paper cites Filter, correlate, com- press: Training-free token reduction for mllm accelera- tion.arXiv preprint arXiv:2411.17686,.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Filter, correlate, com- press: Training-free token reduction for mllm accelera- tion.arXiv preprint arXiv:2411.17686,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.813342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6ac5bc9-df02-4fb8-b581-a2bcfa666296 · outbound

This paper cites Training-free token pruning via zeroth-order gradient estimation in vision-language models.arXiv preprint arXiv:2509.24837,.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Training-free token pruning via zeroth-order gradient estimation in vision-language models.arXiv preprint arXiv:2509.24837,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.819419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2698dd5f-f538-4696-9fc2-925bfeb145e0 · outbound

This paper cites Crafting papers on machine learning.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Crafting papers on machine learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.822334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe6a8878-5f93-4c2b-a242-d594f641f58d · outbound

This paper cites an unresolved cited work.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.885996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f79e5802-4c2a-456f-93e8-e2229b6e0f5a · outbound

This paper cites an unresolved cited work.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.831132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 344c15a1-56d7-4455-85a7-9c432869e3f9 · outbound

This paper cites The few govern the many: Unveiling few-layer dominance for time series models.arXiv preprint arXiv:2511.07237,.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention The few govern the many: Unveiling few-layer dominance for time series models.arXiv preprint arXiv:2511.07237,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.833966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6a59e34-f22e-4c8d-9df7-618e24ce7a7d · outbound

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

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.836659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f6e8c13-3300-4526-90f7-e31565de98f1 · outbound

This paper cites WeLM: A Well-Read Pre-trained Language Model for Chinese.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention WeLM: A Well-Read Pre-trained Language Model for Chinese

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.839708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fd97f3b-7b79-4986-bc5d-e941bd1876c4 · outbound

This paper cites Unraveling the Mystery of Scaling Laws: Part I.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Unraveling the Mystery of Scaling Laws: Part I

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.842782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e46ced7-cd4e-4db9-b348-b7ac0ab0b99d · outbound

This paper cites an unresolved cited work.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.845796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 422fd897-39a2-45c6-b90b-6c39a3d0f062 · outbound

This paper cites TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.848589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d4548d6-a087-41d5-86cf-b33d5ca5d617 · outbound

This paper cites Flowcut: Rethinking redundancy via information flow for efficient vision-language models.arXiv preprint arXiv:2505.19536,.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Flowcut: Rethinking redundancy via information flow for efficient vision-language models.arXiv preprint arXiv:2505.19536,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.851615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77fa743d-5dae-40b2-8c33-67135aaea41d · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention LLaMA: Open and Efficient Foundation Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.854536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4a79494-0980-49de-93da-1059d4310440 · outbound

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

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.857558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a379abfc-05fe-4aee-bb5f-0ce88744d63f · outbound

This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.860430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 018b7785-79ee-4344-a710-5e45add4c883 · outbound

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

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.863246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d0b4ba3-5918-4c10-af00-09dbfa938a6a · outbound

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

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.866305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 068ed5f8-001a-4c3a-b897-6ec3b1f2a7d8 · outbound

This paper cites Shortv: Efficient multi- modal large language models by freezing visual tokens in ineffective layers.arXiv preprint arXiv:2504.00502,.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Shortv: Efficient multi- modal large language models by freezing visual tokens in ineffective layers.arXiv preprint arXiv:2504.00502,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.869360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70140cca-3983-45bf-b5b3-eec4c05b5e23 · outbound

This paper cites and Shukla, D.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention and Shukla, D

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.871953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e035451b-2ac5-4803-9ea6-bea64010fbf2 · outbound

This paper cites Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.874806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe600739-bc70-4b9b-b5f5-0881241d255b · outbound

This paper cites Vscan: Rethinking visual token reduction for efficient large vision-language models.arXiv preprint arXiv:2505.22654, 2025a.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Vscan: Rethinking visual token reduction for efficient large vision-language models.arXiv preprint arXiv:2505.22654, 2025a

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.877803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f8eb748-1179-4bab-a8f9-329a9567700c · outbound

This paper cites SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.880446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d029859-003d-4829-b021-a177564b018d · outbound

This paper cites Don’t just chase” highlighted tokens” in mllms: Revisiting visual holistic context reten- tion.arXiv preprint arXiv:2510.02912,.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Don’t just chase” highlighted tokens” in mllms: Revisiting visual holistic context reten- tion.arXiv preprint arXiv:2510.02912,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.883350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c9823b9-2a33-4884-8775-97d688063185 · outbound

This paper cites an unresolved cited work.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.889099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eba19160-294e-465f-af7b-e273d149be6e · outbound

This paper cites (b) Our method under eager attention, where visual tokens are frozen via explicit masking and participate in attention only as key–value representations.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention (b) Our method under eager attention, where visual tokens are frozen via explicit masking and participate in attention only as key–value representations

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.892124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e48dae1a-7083-4a06-9cc9-8fe29af1ac0b · outbound

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

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention LLaVA-OneVision: Easy Visual Task Transfer

Reference 2000

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.825189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ff8ca33-d940-433b-be82-67ebea37e28f · outbound

This paper cites Informed routing in llms: Smarter token- level computation for faster inference.arXiv preprint arXiv:2510.13831,.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Informed routing in llms: Smarter token- level computation for faster inference.arXiv preprint arXiv:2510.13831,

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.810118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e25429e2-c7ad-4414-a600-650fcb048802 · outbound

This paper cites BLIP-2: Boot- strapping language-image pre-training with frozen image encoders and large language models.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention BLIP-2: Boot- strapping language-image pre-training with frozen image encoders and large language models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.828231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91f02fb3-bf7b-443b-a0cb-d07aa6f705b0 · outbound

This paper cites D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.794122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42a9394c-6e02-47db-8123-83d92b80befd · outbound

This paper cites Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.816273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba07eca3-772f-4565-9d43-a4718bd14d41 · outbound

This paper cites Qwen2.5-VL Technical Report.

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention Qwen2.5-VL Technical Report

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T03:36:43.790329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 36894a2f-169f-4e22-aa11-c9d715c1990f · inbound

SkipOPU: An FPGA-based Overlay Processor for Large Language Models with Dynamically Allocated Computation cites this paper.

SkipOPU: An FPGA-based Overlay Processor for Large Language Models with Dynamically Allocated Computation ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T18:16:46.738649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ff9dad2-ab9e-4d4a-9b72-d7405e708a29 · inbound

ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference cites this paper.

ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention

Reference 50

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T03:19:29.982411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5477009a-0d09-4044-911e-9ec5cb869b84 · inbound

From Recognition to Understanding: Unlocking Cognitive Time Series Reasoning with LLMs cites this paper.

From Recognition to Understanding: Unlocking Cognitive Time Series Reasoning with LLMs ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-04T08:19:44.560480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a404a56c-7951-4876-828e-90c1de1ccc84 · inbound

Intrinsic and Triangulation-Agnostic Attention: A Simple and Powerful Approach for Learning on Meshes cites this paper.

Intrinsic and Triangulation-Agnostic Attention: A Simple and Powerful Approach for Learning on Meshes ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-31T05:06:55.036228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.