Paper Citation Record · LEDGER

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models

As of 18 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2607.04593.

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

pith.paper-citation-record.v1
2607.04593 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T16:44:16.649115Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+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

37 of 37 outbound references displayed

verified exact0
verified fuzzy0
unresolved37
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 068f632a-01ff-4501-a458-e93b1c850daf · outbound

This paper cites Flamingo: a visual language model for few-shot learning.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Flamingo: a visual language model for few-shot learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8617793d-35ed-4093-bc50-34cb2b645810 · outbound

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

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Divprune: Diversity-based visual token pruning for large multimodal models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 861ab4f6-0db7-465e-bfbf-824e94a6473d · outbound

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

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Hired: Attention-guided token dropping for efficient inference of high-resolution vision-language models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9395c68f-cda5-4364-9630-658f4af8cc21 · outbound

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

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ccbda54-53d3-4dce-948e-65e22e5a71e7 · outbound

This paper cites Mechanistic inter- pretability for AI safety - a review.Transactions on Machine Learning Research, 2024.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Mechanistic inter- pretability for AI safety - a review.Transactions on Machine Learning Research, 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7daeea18-1912-4a97-8e96-7f633f1b9dd0 · outbound

This paper cites Token merging: Your vit but faster.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Token merging: Your vit but faster

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e95d11b0-e4c7-40ff-b04e-578e067df446 · outbound

This paper cites Towards Monosemanticity: Decomposing Language Models With Dictionary Learning,.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Towards Monosemanticity: Decomposing Language Models With Dictionary Learning,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06026149-92e0-42d0-b450-e85de426b33f · outbound

This paper cites Batchtopk sparse autoencoders.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Batchtopk sparse autoencoders

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07d3e62c-6d5c-426d-86c0-12c9b697757c · outbound

This paper cites Learning multi-level features with matryoshka sparse autoencoders.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Learning multi-level features with matryoshka sparse autoencoders

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e36cde1f-8f97-46b2-aa18-cdd8650800b7 · outbound

This paper cites SAEmne- sia: Erasing concepts in diffusion models with supervised sparse autoencoders.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models SAEmne- sia: Erasing concepts in diffusion models with supervised sparse autoencoders

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d25ca1c-92b0-4a43-b409-d1fcd02c0b29 · outbound

This paper cites SAeuron: Interpretable concept unlearning in diffusion models with sparse autoen- coders.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models SAeuron: Interpretable concept unlearning in diffusion models with sparse autoen- coders

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdbf46d3-9d60-491b-beab-2e075dd4d109 · outbound

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

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models InstructBLIP: Towards general-purpose vision-language models with instruction tuning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63dba388-0617-49e9-859f-8502c49bdecc · outbound

This paper cites Vlmevalkit: An open-source toolkit for evaluating large multi-modality models.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Vlmevalkit: An open-source toolkit for evaluating large multi-modality models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 746a2676-7921-4887-a586-f33e49668183 · outbound

This paper cites Davis, Gaowen Liu, George K.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Davis, Gaowen Liu, George K

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac785aa1-f20b-410a-9f82-8f7314eebaf4 · outbound

This paper cites Prune redundancy, pre- serve essence: Vision token compression in VLMs via syner- gistic importance-diversity.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Prune redundancy, pre- serve essence: Vision token compression in VLMs via syner- gistic importance-diversity

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80589208-d1fe-475c-86f5-0f16c00295d9 · outbound

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

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7da17069-3ceb-4c34-91ac-e881d750b987 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Scaling and evaluating sparse autoencoders

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d8f7624-fa58-40d4-b8df-84d72c4aa7d9 · outbound

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

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Vizwiz grand challenge: Answering visual questions from blind people

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 658170cd-4ed2-41eb-b5b8-909383b6a73d · outbound

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

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96a451e0-d8fc-47cb-9ed0-e0a5515dd23d · outbound

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

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Evaluating object hallucination in large vision-language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4ec53d2-9709-433c-b659-8a788423758c · outbound

This paper cites Visual instruction tuning.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Visual instruction tuning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 774869ec-8341-4856-b85c-d16649457ece · outbound

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

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Mmbench: Is your multi-modal model an all-around player? InEuropean conference on computer vi- sion, pages 216–233

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e3a5ef2-01e5-48eb-8d20-42beb9a45eb4 · 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,.

TORINO: Token Reduction via Interpretable Concept Overlap in 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 23

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d8cdb03-71ca-4da8-a746-fdd427f618fc · outbound

This paper cites ToMA: Token merge with attention for diffusion models.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models ToMA: Token merge with attention for diffusion models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acb4e5d2-4bb4-4069-893d-854c16f563e3 · outbound

This paper cites A pragmatic vision for inter- pretability.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models A pragmatic vision for inter- pretability

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbe6b26d-89fe-4c28-89db-109d731e221c · outbound

This paper cites Sparse autoencoders learn monosemantic features in vision-language models.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Sparse autoencoders learn monosemantic features in vision-language models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f00fe6d-dbcd-4eb7-aa8b-396e2828c621 · outbound

This paper cites Save: Sparse autoencoder-driven visual information enhancement for mitigating object hallucination.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Save: Sparse autoencoder-driven visual information enhancement for mitigating object hallucination

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81a7baf6-7b4b-4a06-9170-a19f1c279861 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Learning transferable visual models from natural language supervi- sion

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a287e67-958c-42da-be4f-c6c512388d13 · outbound

This paper cites Discover-then-name: Task-agnostic concept bottle- necks via automated concept discovery.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Discover-then-name: Task-agnostic concept bottle- necks via automated concept discovery

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 667c600e-fb57-4863-88dd-862c258e6922 · outbound

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

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Llava-prumerge: Adaptive token reduction for efficient large multimodal models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a760dff2-6a1e-4776-89e7-b560e5116c12 · outbound

This paper cites VL-SAE: Interpreting and enhancing vision-language alignment with a unified concept set.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models VL-SAE: Interpreting and enhancing vision-language alignment with a unified concept set

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfa2bcd1-672d-4873-bdfd-30694d3cec7f · outbound

This paper cites A survey on sparse autoencoders: Interpreting the internal mechanisms of large language models.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models A survey on sparse autoencoders: Interpreting the internal mechanisms of large language models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c9ebe76-c9ce-4221-bf8b-f14018c1449b · outbound

This paper cites Towards vqa models that can read.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Towards vqa models that can read

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 570b0c50-c485-4349-baf6-590815bbce1b · outbound

This paper cites Folder: Accelerating multi-modal large language models with en- hanced performance.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Folder: Accelerating multi-modal large language models with en- hanced performance

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb99e466-af90-4d11-9278-b3d6baa1a2c8 · outbound

This paper cites Gtp-vit: Efficient vision trans- formers via graph-based token propagation.

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Gtp-vit: Efficient vision trans- formers via graph-based token propagation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed394979-9395-4dc9-9037-158dbe4a639f · outbound

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

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Visionzip: Longer is better but not necessary in vision language models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cca032b-219b-4c9b-af00-ee7c7a8b1a39 · outbound

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

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Mm-vet: Evaluating large multimodal models for integrated capabilities

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-11T16:44:16.649115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.