Paper Citation Record · LEDGER

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference

As of 6 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 10 inbound Pith citation observations for arXiv:2511.16449.

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

pith.paper-citation-record.v1
2511.16449 v5

Coverage vector

measured 63 of 63 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T21:14:02.361658Z

measured 73 of 73 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 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T12:54:41.821598Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-04T13:59:52.612293Z

Reference resolution

63 of 63 outbound references displayed

verified exact0
verified fuzzy0
unresolved62
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 523ef674-186c-47a5-b79f-70f216764b6a · outbound

This paper cites Nocaps: Novel object caption- ing at scale.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Nocaps: Novel object caption- ing at scale

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:52.982102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 027dda6f-241f-4936-9e07-ade1bf149914 · outbound

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

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Divprune: Diversity-based visual token pruning for large multimodal models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:53.102464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dde09cef-a399-4f1f-bb1b-f11e9daa696f · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:53.258938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79561e4a-9bf3-4d99-b6cf-8e9212efde30 · outbound

This paper cites $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:53.434223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b967f54-e9e7-43ac-9e0b-0ca2ca51df74 · outbound

This paper cites John Wiley & Sons, 2015.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference John Wiley & Sons, 2015

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:53.606657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d96e85f8-3860-4a2e-a730-164231228012 · outbound

This paper cites Springer, 2002.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Springer, 2002

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:53.806956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a06a6e62-6481-4964-b103-7cdf6b851750 · outbound

This paper cites RT-1: Robotics Transformer for Real-World Control at Scale.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference RT-1: Robotics Transformer for Real-World Control at Scale

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:54.012965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d00ed54c-f655-4514-8d08-15582eceae21 · outbound

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

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:54.233243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f76c21b-a567-4958-a36d-a0d46904e11d · outbound

This paper cites Diffusion policy: Visuomotor policy learning via action dif- fusion.The International Journal of Robotics Research, 44 (10-11):1684–1704, 2025.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Diffusion policy: Visuomotor policy learning via action dif- fusion.The International Journal of Robotics Research, 44 (10-11):1684–1704, 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:54.447436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44927e64-5b6e-4295-9014-9138f7e8fbad · outbound

This paper cites Arima models to forecast next-day elec- tricity prices.IEEE transactions on Power Systems, 18(3): 1114–1121, 2003.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Arima models to forecast next-day elec- tricity prices.IEEE transactions on Power Systems, 18(3): 1114–1121, 2003

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:54.542483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0b9cbd5-33a6-4c81-b5c1-cb020051985e · outbound

This paper cites OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:54.666710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a6f67cf-9d64-49ac-8e0e-dbe3786d2002 · outbound

This paper cites Flashattention: Fast and memory-efficient exact attention with io-awareness.Advances in neural information processing systems, 35:16344–16359, 2022.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Flashattention: Fast and memory-efficient exact attention with io-awareness.Advances in neural information processing systems, 35:16344–16359, 2022

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:54.846056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbb1e2cc-83c9-4ff1-b6e9-49cfd68bec7c · outbound

This paper cites Foundation models in robotics: Applications, challenges, and the future.The International Journal of Robotics Research, 44(5):701–739,.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Foundation models in robotics: Applications, challenges, and the future.The International Journal of Robotics Research, 44(5):701–739,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:54.986243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35f5b705-cad5-49e0-808c-aca6e1c5ae43 · outbound

This paper cites an unresolved cited work.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:55.120484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 905315cf-9604-4888-9ca3-82326d993387 · outbound

This paper cites Exponential smoothing: The state of the art—part ii.International journal of forecasting, 22(4): 637–666, 2006.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Exponential smoothing: The state of the art—part ii.International journal of forecasting, 22(4): 637–666, 2006

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:55.302122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d2b3f30-c72e-40a4-880e-54f0689db79a · outbound

This paper cites Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:55.498913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9ab8769-9c24-43b3-8a5a-613ea645c1a9 · outbound

This paper cites Application of arima model for fore- casting of daily maximum temperature.MAUSAM, 69(2): 291–296, 2018.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Application of arima model for fore- casting of daily maximum temperature.MAUSAM, 69(2): 291–296, 2018

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:55.705077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76bce430-2e08-4cf2-8d40-1d487fc00c44 · outbound

This paper cites A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:55.935229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57e376bb-4e45-42f1-91c8-6cb724594be6 · outbound

This paper cites ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:56.020935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed791c84-ab0b-45c2-b7c2-20b7de49f960 · outbound

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

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:56.169578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 776dd8bb-01a4-4a90-bc50-2924b5caacbb · outbound

This paper cites OTexts, 2018.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference OTexts, 2018

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:56.316181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7934f1b5-4156-4e3e-8d1b-107bd22a6162 · outbound

This paper cites OpenVLA: An Open-Source Vision-Language-Action Model.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference OpenVLA: An Open-Source Vision-Language-Action Model

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:56.462664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5767508-8e7e-4919-a423-a1b18dd412fb · outbound

This paper cites Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:56.747553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd7dfac0-5aee-4ef5-85e6-b94a5a7173eb · outbound

This paper cites CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:56.896555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7816679a-32e7-4762-ba51-ee9b28fac194 · outbound

This paper cites Vision-Language Foundation Models as Effective Robot Imitators.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Vision-Language Foundation Models as Effective Robot Imitators

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:57.062334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ca6b994-fbb6-45b4-aaa2-d6c412525532 · outbound

This paper cites Evaluating Real-World Robot Manipulation Policies in Simulation.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Evaluating Real-World Robot Manipulation Policies in Simulation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:57.157105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bc0f27b-f3b9-4cef-bb6b-dcd2eb6b6674 · outbound

This paper cites Tgif: A new dataset and benchmark on animated gif description.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Tgif: A new dataset and benchmark on animated gif description

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:57.283550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d03a8d31-dd15-43f8-97d6-001a4cede479 · outbound

This paper cites Sp-vla: A joint model scheduling and token prun- ing approach for vla model acceleration.arXiv preprint arXiv:2506.12723, 2025.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Sp-vla: A joint model scheduling and token prun- ing approach for vla model acceleration.arXiv preprint arXiv:2506.12723, 2025

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:57.409447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19356258-b13f-4186-bf1f-4cd782a13b5c · outbound

This paper cites Evo-1: Lightweight vision-language-action model with pre- served semantic alignment, 2025.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Evo-1: Lightweight vision-language-action model with pre- served semantic alignment, 2025

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:57.611003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e1d00c2-cbe7-4225-9c3f-8dbda5f21156 · outbound

This paper cites Boosting multimodal large language models with visual to- kens withdrawal for rapid inference.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Boosting multimodal large language models with visual to- kens withdrawal for rapid inference

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:57.792977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19d3c730-3205-4afa-a043-8e955b0a73d6 · outbound

This paper cites Libero: Benchmarking knowl- edge transfer for lifelong robot learning.Advances in Neural Information Processing Systems, 36:44776–44791, 2023.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Libero: Benchmarking knowl- edge transfer for lifelong robot learning.Advances in Neural Information Processing Systems, 36:44776–44791, 2023

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:58.012908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad7923a5-26ab-47bb-9d10-6b2cef09b2e6 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:58.257420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a8c2edf-12b9-4858-8800-b6a19e29e746 · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player? InEuropean conference on computer vi- sion, pages 216–233.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Mmbench: Is your multi-modal model an all-around player? InEuropean conference on computer vi- sion, pages 216–233

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:58.422734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f55acff6-22a1-47b5-a79f-fac5646390d2 · outbound

This paper cites A Survey on Vision-Language-Action Models for Embodied AI.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference A Survey on Vision-Language-Action Models for Embodied AI

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:58.668633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62b7b23f-dccd-4429-9718-bd66e1e90142 · outbound

This paper cites Efficient Token Compression for Vision Transformer with Spatial Information Preserved.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Efficient Token Compression for Vision Transformer with Spatial Information Preserved

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:58.880803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7542731-dc4f-4724-a060-1dfc10724a08 · outbound

This paper cites Prune and merge: Efficient token compression for vision transformer with spatial infor- mation preserved.IEEE Transactions on Multimedia, 2025.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Prune and merge: Efficient token compression for vision transformer with spatial infor- mation preserved.IEEE Transactions on Multimedia, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:59.045043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06e66336-5d1d-4c61-bb8a-bc2b587f59e6 · outbound

This paper cites A review on discrete diversity and dis- persion maximization from an or perspective.European Journal of Operational Research, 299(3):795–813, 2022.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference A review on discrete diversity and dis- persion maximization from an or perspective.European Journal of Operational Research, 299(3):795–813, 2022

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:59.158654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50416b6c-4386-4944-a84d-a45788eb7c9c · outbound

This paper cites Eog signal modeling using double exponential smoothing for robot arm control system.Kurdistan Journal of Applied Research, 1(3):6–10, 2016.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Eog signal modeling using double exponential smoothing for robot arm control system.Kurdistan Journal of Applied Research, 1(3):6–10, 2016

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:59.269592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0deb0cb-dcbb-4719-bc44-80e53e579d01 · outbound

This paper cites Open x-embodiment: Robotic learning datasets and rt-x models: Open x-embodiment collaboration 0.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Open x-embodiment: Robotic learning datasets and rt-x models: Open x-embodiment collaboration 0

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:59.398579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 869a3651-abe3-40c9-b3d8-12900194fd3d · outbound

This paper cites Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:59.533390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e77ebed-6f69-4937-a551-02152f10e307 · outbound

This paper cites an unresolved cited work.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:59.742159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6e82c46-bdd0-4007-843f-6f64505d4871 · outbound

This paper cites Empirical macroeco- nomic modelling for policy analysis.The Oxford Handbook of Economic Forecasting, 2012.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Empirical macroeco- nomic modelling for policy analysis.The Oxford Handbook of Economic Forecasting, 2012

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:59.863759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5589f6ec-f8f7-4417-9306-7b56d26e492b · outbound

This paper cites Flickr30k entities: Collecting region-to-phrase corre- spondences for richer image-to-sentence models.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Flickr30k entities: Collecting region-to-phrase corre- spondences for richer image-to-sentence models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-03T21:13:59.943585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 880a4a78-742d-4354-9374-e884a44f3bae · outbound

This paper cites A simple and effective algorithm for the maxmin diversity problem.Annals of Operations Research, 186(1):275–293,.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference A simple and effective algorithm for the maxmin diversity problem.Annals of Operations Research, 186(1):275–293,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:00.017215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1717950f-2ac7-4801-8a9d-b8669ac354a6 · outbound

This paper cites Grasp and path relinking for the max–min diversity problem.Computers & Operations Research, 37 (3):498–508, 2010.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Grasp and path relinking for the max–min diversity problem.Computers & Operations Research, 37 (3):498–508, 2010

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:00.262384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 359cc67a-867d-4a60-83e5-d5b1aef7eebf · outbound

This paper cites Llava-prumerge: Adaptive token reduction for efficient large multimodal models.arXiv preprint arXiv:2403.15388,.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Llava-prumerge: Adaptive token reduction for efficient large multimodal models.arXiv preprint arXiv:2403.15388,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:00.438884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67650591-946f-4f66-ba2a-9ccaee522df5 · outbound

This paper cites The empirical case for two systems of reasoning.Psychological bulletin, 119(1):3, 1996.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference The empirical case for two systems of reasoning.Psychological bulletin, 119(1):3, 1996

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:00.549066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75ed1a02-0afd-416b-b93f-805c4fe91e6c · outbound

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

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:00.705370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e4abb21-c177-4996-9aa2-3e69f4e1caff · outbound

This paper cites SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:00.801346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e06c39cc-e4a6-439e-9558-234babef7436 · outbound

This paper cites Tinyvla: Towards fast, data-efficient vision- language-action models for robotic manipulation.IEEE Robotics and Automation Letters, 2025.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Tinyvla: Towards fast, data-efficient vision- language-action models for robotic manipulation.IEEE Robotics and Automation Letters, 2025

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:00.875153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28c49101-3c7e-4802-babd-5ad70ed90bb7 · outbound

This paper cites Forecasting seasonals and trends by expo- nentially weighted moving averages.Management science, 6(3):324–342, 1960.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Forecasting seasonals and trends by expo- nentially weighted moving averages.Management science, 6(3):324–342, 1960

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:00.977431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c415a1b-a7f4-49ae-9b5c-8e17fb3d699c · outbound

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

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:01.173554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd8f6a09-6348-45be-a579-39c188ce6d35 · outbound

This paper cites Video question answer- ing via gradually refined attention over appearance and mo- tion.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Video question answer- ing via gradually refined attention over appearance and mo- tion

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:01.231594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ec9c681-d72e-4c98-adb0-e8c267f02693 · outbound

This paper cites Vla-cache: Efficient vision- language-action manipulation via adaptive token caching.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Vla-cache: Efficient vision- language-action manipulation via adaptive token caching

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:01.307967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4be9b7c8-3b0a-49ab-894d-67778610a006 · outbound

This paper cites EfficientVLA: Training-free acceleration and com- pression for vision-language-action models.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference EfficientVLA: Training-free acceleration and com- pression for vision-language-action models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:01.427269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b81a8881-a0df-424e-975b-c8c0750684e5 · outbound

This paper cites Fit and prune: Fast and training-free visual token pruning for multi- modal large language models.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Fit and prune: Fast and training-free visual token pruning for multi- modal large language models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:01.543512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4221a2b1-0d2e-4d4f-a8c5-f9c1957f29c2 · outbound

This paper cites A survey on efficient vision-language-action models,.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference A survey on efficient vision-language-action models,

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:01.706653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f2306d0-3252-4b81-affa-ba7a1a35e760 · outbound

This paper cites Deer-vla: Dynamic inference of multimodal large language models for efficient robot execution.Advances in Neural Information Processing Systems, 37:56619–56643, 2024.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Deer-vla: Dynamic inference of multimodal large language models for efficient robot execution.Advances in Neural Information Processing Systems, 37:56619–56643, 2024

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:01.815488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a3ef22d-aed3-4c3e-a224-a53f6ea7211e · outbound

This paper cites SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:01.887983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eb5f061-9989-49ad-8165-6dbda3e917aa · outbound

This paper cites H2o: Heavy-hitter ora- cle for efficient generative inference of large language mod- els.Advances in Neural Information Processing Systems, 36: 34661–34710, 2023.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference H2o: Heavy-hitter ora- cle for efficient generative inference of large language mod- els.Advances in Neural Information Processing Systems, 36: 34661–34710, 2023

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:01.967848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7823c72f-9e8f-45ee-89b1-6ed27e8713f8 · outbound

This paper cites Cot-vla: Visual chain-of-thought rea- soning for vision-language-action models.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Cot-vla: Visual chain-of-thought rea- soning for vision-language-action models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:02.069112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85dea76b-7c6e-4575-ada1-45ffb7fbb0b8 · outbound

This paper cites Rt-2: Vision-language-action models transfer web knowledge to robotic control.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference Rt-2: Vision-language-action models transfer web knowledge to robotic control

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:02.239106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb3d0ee1-30fa-497e-a58f-e20864894eb9 · outbound

This paper cites highlighted tokens.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference highlighted tokens

Reference 64

Resolution: malformed identifier; no resolver link, observed 2026-08-03T21:14:02.361658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c028bb8a-eca3-4120-95a3-508c257b5e13 · inbound

FASTER: Rethinking Real-Time Flow VLAs cites this paper.

FASTER: Rethinking Real-Time Flow VLAs Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:58.134498Z

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 9472c73b-7ba7-4a65-81ed-78210ecd7561 · inbound

FASTER: Rethinking Real-Time Flow VLAs cites this paper.

FASTER: Rethinking Real-Time Flow VLAs Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:58.134498Z

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 07e8a87a-679e-4656-b5d9-029ff9a003a0 · inbound

Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference cites this paper.

Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:58.134498Z

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 3f177c87-3da0-455d-80d7-2737b7ff620e · inbound

Premover: Fast Vision-Language-Action Control by Acting Before Instructions Are Complete cites this paper.

Premover: Fast Vision-Language-Action Control by Acting Before Instructions Are Complete Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:58.134498Z

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 1721c3c9-0fbf-49dc-ad41-b40bcaae07ce · inbound

ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models cites this paper.

ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference

Reference 21

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T07:23:13.033777Z

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 3344ac15-497f-49f1-9f8a-754a284f91f7 · inbound

SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation cites this paper.

SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-06-29T08:43:14.929449Z

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 f383a69e-fd5d-4d48-b8f8-811ebf58efa6 · inbound

SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation cites this paper.

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T12:54:41.821598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd6a2328-aa74-4ade-942f-ff01d09b57fc · inbound

ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning cites this paper.

ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-02T03:26:28.729967Z

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 55ed6354-5505-41e3-bd37-7a7b4a353d67 · inbound

LA4VLA: Learning to Act without Seeing via Language-Action Pretraining cites this paper.

LA4VLA: Learning to Act without Seeing via Language-Action Pretraining Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-07-04T13:59:52.613556Z

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 1b9c9e52-e297-4207-a682-8bbf99d7c9a6 · inbound

LA4VLA: Learning to Act without Seeing via Language-Action Pretraining cites this paper.

LA4VLA: Learning to Act without Seeing via Language-Action Pretraining Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-06-29T19:53:56.093245Z

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.