Paper Citation Record · LEDGER

Token Activation Map to Visually Explain Multimodal LLMs

As of 9 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 3 inbound Pith citation observations for arXiv:2506.23270.

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

pith.paper-citation-record.v1
2506.23270 v1

Coverage vector

measured 65 of 65 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T21:52:29.407583Z

measured 68 of 68 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T14:58:38.554863Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T01:45:52.034775Z

Reference resolution

65 of 65 outbound references displayed

verified exact0
verified fuzzy47
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d4de39f2-8367-4a38-bd53-b02dca29f34c · outbound

This paper cites Quantifying attention flow in transformers.

Token Activation Map to Visually Explain Multimodal LLMs Quantifying attention flow in transformers

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:39.315954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ebc98010-930a-4a15-834f-258ab58ade04 · outbound

This paper cites Attnlrp: Attention- aware layer-wise relevance propagation for transformers.

Token Activation Map to Visually Explain Multimodal LLMs Attnlrp: Attention- aware layer-wise relevance propagation for transformers

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:39.029975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bffa45d5-158c-4fba-819a-1a9fed0a37c3 · outbound

This paper cites Vl-interpret: An interactive visualization tool for interpreting vision-language transformers.

Token Activation Map to Visually Explain Multimodal LLMs Vl-interpret: An interactive visualization tool for interpreting vision-language transformers

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:38.481689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 021db75b-a6aa-45f6-8a2f-df56eea62a9b · outbound

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

Token Activation Map to Visually Explain Multimodal LLMs Flamingo: a visual language model for few-shot learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:23.200165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e28f49e7-adc0-47b5-b63b-7b1ae3ee0216 · outbound

This paper cites Xai for trans- formers: Better explanations through conservative propa- gation.

Token Activation Map to Visually Explain Multimodal LLMs Xai for trans- formers: Better explanations through conservative propa- gation

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:38.145550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 818ccc59-2c78-4235-9a49-8d9538a00479 · outbound

This paper cites Text2live: Text-driven layered image and video editing.

Token Activation Map to Visually Explain Multimodal LLMs Text2live: Text-driven layered image and video editing

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:37.802003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3aa7372b-2964-43cc-8255-0946c3531fbe · outbound

This paper cites Lvlm-intrepret: An interpretability tool for large vision-language models.

Token Activation Map to Visually Explain Multimodal LLMs Lvlm-intrepret: An interpretability tool for large vision-language models

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:37.419141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 56241116-b3c1-4dd0-826a-56f3dc54d316 · outbound

This paper cites An adaptive median filter for image denoising.

Token Activation Map to Visually Explain Multimodal LLMs An adaptive median filter for image denoising

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:37.138362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e807e267-b14c-43a4-9570-7995aaa5a0f0 · outbound

This paper cites Grad-cam++: General- ized gradient-based visual explanations for deep convolu- tional networks.

Token Activation Map to Visually Explain Multimodal LLMs Grad-cam++: General- ized gradient-based visual explanations for deep convolu- tional networks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:23.673939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 387ed1b8-79d1-4255-ad4f-234b5fe8ea23 · outbound

This paper cites Generic attention- model explainability for interpreting bi-modal and encoder- decoder transformers.

Token Activation Map to Visually Explain Multimodal LLMs Generic attention- model explainability for interpreting bi-modal and encoder- decoder transformers

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:23.743484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3551c4f-decd-459b-9d8c-447cd54b6c89 · outbound

This paper cites Transformer inter- pretability beyond attention visualization.

Token Activation Map to Visually Explain Multimodal LLMs Transformer inter- pretability beyond attention visualization

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:36.945210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b092b981-a4fe-4711-b9ed-7c5fca5c3b20 · outbound

This paper cites Less is more: Fewer interpretable region via submodular subset selection.

Token Activation Map to Visually Explain Multimodal LLMs Less is more: Fewer interpretable region via submodular subset selection

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:36.796077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation acc9bf12-e418-4552-8424-9ffd90af11f8 · outbound

This paper cites Microsoft COCO Captions: Data Collection and Evaluation Server.

Token Activation Map to Visually Explain Multimodal LLMs Microsoft COCO Captions: Data Collection and Evaluation Server

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:24.065434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afb0bd74-59d4-4c8c-af1c-87319c0c7084 · outbound

This paper cites Clip-ad: A language-guided staged dual-path model for zero-shot anomaly detection.

Token Activation Map to Visually Explain Multimodal LLMs Clip-ad: A language-guided staged dual-path model for zero-shot anomaly detection

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:36.619683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 60315eb3-3ff5-45aa-adee-6f7db657e89f · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

Token Activation Map to Visually Explain Multimodal LLMs Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:24.270466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b8b3449-02d5-490e-b819-49d285b05ae2 · outbound

This paper cites Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks.

Token Activation Map to Visually Explain Multimodal LLMs Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:36.447607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d83c952b-6c0e-4d7f-9b64-d0d02c398361 · outbound

This paper cites A survey on multimodal large lan- guage models for autonomous driving.

Token Activation Map to Visually Explain Multimodal LLMs A survey on multimodal large lan- guage models for autonomous driving

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:36.265238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 55e032c7-68f7-43e4-83e8-000f889c35f2 · outbound

This paper cites Flashattention: Fast and memory-efficient exact at- tention with io-awareness.

Token Activation Map to Visually Explain Multimodal LLMs Flashattention: Fast and memory-efficient exact at- tention with io-awareness

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:36.123765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 562b6886-6ac5-4d32-9905-332e33589d3e · outbound

This paper cites Vision transformers need registers.

Token Activation Map to Visually Explain Multimodal LLMs Vision transformers need registers

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:36.001289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9e0a0169-afc6-4f6d-9d91-4bc9b4618612 · outbound

This paper cites Bert: Pre-training of deep bidirectional trans- formers for language understanding.

Token Activation Map to Visually Explain Multimodal LLMs Bert: Pre-training of deep bidirectional trans- formers for language understanding

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:24.628249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e29031a5-45de-4ba7-a704-248d703c7195 · outbound

This paper cites Hia: Towards chinese multimodal llms for comparative high-resolution joint diagnosis.

Token Activation Map to Visually Explain Multimodal LLMs Hia: Towards chinese multimodal llms for comparative high-resolution joint diagnosis

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:35.848320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 30eddce3-f46c-4af8-93d8-03533192b924 · outbound

This paper cites Holistic autonomous driving un- derstanding by bird’view injected multi-modal large models.

Token Activation Map to Visually Explain Multimodal LLMs Holistic autonomous driving un- derstanding by bird’view injected multi-modal large models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:35.696589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 06b09a51-da1c-4187-8bbb-77138383df40 · outbound

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

Token Activation Map to Visually Explain Multimodal LLMs An image is worth 16x16 words: Trans- formers for image recognition at scale

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:35.560451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0c3f78d9-6d9e-4956-ab1c-2079b9b30237 · outbound

This paper cites Deep residual learning for image recognition.

Token Activation Map to Visually Explain Multimodal LLMs Deep residual learning for image recognition

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:35.398468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fceaabdb-ae1f-4e8c-a0e0-329b2a3b56d9 · outbound

This paper cites GPT-4o System Card.

Token Activation Map to Visually Explain Multimodal LLMs GPT-4o System Card

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:24.893909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3350316-b32e-4812-8ffb-e3e32ae89606 · outbound

This paper cites Layercam: Exploring hierarchical class activation maps for localization.

Token Activation Map to Visually Explain Multimodal LLMs Layercam: Exploring hierarchical class activation maps for localization

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:35.237320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 138f9eb9-5bc3-4bc4-98d9-eaf078fd15b0 · outbound

This paper cites Causal inference meets deep learning: A compre- hensive survey.

Token Activation Map to Visually Explain Multimodal LLMs Causal inference meets deep learning: A compre- hensive survey

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:35.053887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 755369e1-7dd3-4e7d-ae27-6c9169819545 · outbound

This paper cites Unmasking clever hans predictors and as- sessing what machines really learn.

Token Activation Map to Visually Explain Multimodal LLMs Unmasking clever hans predictors and as- sessing what machines really learn

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:34.884300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f96de966-94a9-40fb-a609-1d9f5bb8c4c6 · outbound

This paper cites Llava-docent: Instruction tuning with multimodal large lan- guage model to support art appreciation education.

Token Activation Map to Visually Explain Multimodal LLMs Llava-docent: Instruction tuning with multimodal large lan- guage model to support art appreciation education

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:34.688437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2da65a26-37a5-417a-ba21-7ff09e4f63ff · outbound

This paper cites Manipllm: Embodied multimodal large language model for object-centric robotic manipulation.

Token Activation Map to Visually Explain Multimodal LLMs Manipllm: Embodied multimodal large language model for object-centric robotic manipulation

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:34.487383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 591122c2-d792-48f2-9ef0-af9ae5158136 · outbound

This paper cites Exploring Visual Interpretability for Contrastive Language-Image Pre-training.

Token Activation Map to Visually Explain Multimodal LLMs Exploring Visual Interpretability for Contrastive Language-Image Pre-training

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:25.254347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67b51a60-2297-48fb-a314-4198d1beea9a · outbound

This paper cites A closer look at the explainability of con- trastive language-image pre-training.

Token Activation Map to Visually Explain Multimodal LLMs A closer look at the explainability of con- trastive language-image pre-training

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:34.338754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0889dc48-50f3-439e-8bd1-2a2762db6951 · outbound

This paper cites Microsoft coco: Common objects in context.

Token Activation Map to Visually Explain Multimodal LLMs Microsoft coco: Common objects in context

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:25.381037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8732b887-ceae-4a94-a807-544e0a93460e · outbound

This paper cites A medical multimodal large language model for future pandemics.

Token Activation Map to Visually Explain Multimodal LLMs A medical multimodal large language model for future pandemics

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:34.156408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 36fd000f-a697-4568-b524-23d0242845e7 · outbound

This paper cites Visual instruction tuning.

Token Activation Map to Visually Explain Multimodal LLMs Visual instruction tuning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:34.016402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3ed8483e-c879-4098-a0e1-200d1baa53ad · outbound

This paper cites A unified approach to interpreting model predictions.

Token Activation Map to Visually Explain Multimodal LLMs A unified approach to interpreting model predictions

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:33.817131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 443a3d6b-8434-4fc5-9679-3d49fcda9473 · outbound

This paper cites Ok-vqa: A visual question answering benchmark requiring external knowledge.

Token Activation Map to Visually Explain Multimodal LLMs Ok-vqa: A visual question answering benchmark requiring external knowledge

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:33.554791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 01780bf3-78f0-4ac8-b323-3af92010a72c · outbound

This paper cites Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models.

Token Activation Map to Visually Explain Multimodal LLMs Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:25.702588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fdfa9fa-56af-4347-9d35-47813276b48a · outbound

This paper cites Towards vision-language mechanistic interpretabil- ity: A causal tracing tool for blip.

Token Activation Map to Visually Explain Multimodal LLMs Towards vision-language mechanistic interpretabil- ity: A causal tracing tool for blip

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:33.356930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 57c3a70d-810f-4ae9-8b7c-fb8d406672dc · outbound

This paper cites Causality.

Token Activation Map to Visually Explain Multimodal LLMs Causality

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:25.778705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5da96631-5200-416d-a009-0ce47338e1df · outbound

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

Token Activation Map to Visually Explain Multimodal LLMs Learning transferable visual models from natural language supervi- sion

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:33.222645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6fae3910-a117-40af-a75a-4eb733df3128 · outbound

This paper cites Glamm: Pixel grounding large multimodal model.

Token Activation Map to Visually Explain Multimodal LLMs Glamm: Pixel grounding large multimodal model

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:32.993373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5687849b-dc4f-402c-88d4-74696d16da54 · outbound

This paper cites ” why should i trust you?” explaining the predictions of any classifier.

Token Activation Map to Visually Explain Multimodal LLMs ” why should i trust you?” explaining the predictions of any classifier

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:32.802753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 05a57b0f-e59c-410c-a9bb-cfb97897fd94 · outbound

This paper cites Causal interpretation of self-attention in pre-trained trans- formers.

Token Activation Map to Visually Explain Multimodal LLMs Causal interpretation of self-attention in pre-trained trans- formers

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:32.626574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 196618f3-66a4-4c43-aee8-be7d529c1fed · outbound

This paper cites Grad-cam: Visual explanations from deep networks via gradient-based localization.

Token Activation Map to Visually Explain Multimodal LLMs Grad-cam: Visual explanations from deep networks via gradient-based localization

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:26.849975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67ed4cc3-904b-4d83-a56e-cd116cc1d3a2 · outbound

This paper cites Training- free object counting with prompts.

Token Activation Map to Visually Explain Multimodal LLMs Training- free object counting with prompts

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:32.256509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1a7d0272-266c-4853-b2cc-4f7fc734a287 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Token Activation Map to Visually Explain Multimodal LLMs Gemini: A Family of Highly Capable Multimodal Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:27.282270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6150cd2f-2db5-48e3-bbb1-95b8b2d7738d · outbound

This paper cites Understanding how vision-language models rea- son when solving visual math problems.

Token Activation Map to Visually Explain Multimodal LLMs Understanding how vision-language models rea- son when solving visual math problems

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:32.082031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7a765326-b36b-454a-9900-2259ac8c7c62 · outbound

This paper cites Attention is all you need.

Token Activation Map to Visually Explain Multimodal LLMs Attention is all you need

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:31.920473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c69c4e1c-7ea3-477a-827b-b814833df753 · outbound

This paper cites Interpretable bilin- gual multimodal large language model for diverse biomed- ical tasks.

Token Activation Map to Visually Explain Multimodal LLMs Interpretable bilin- gual multimodal large language model for diverse biomed- ical tasks

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:31.726790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f3bf8d0d-6f75-4ecd-baf9-b4b3a078a944 · outbound

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

Token Activation Map to Visually Explain Multimodal LLMs Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:27.901257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1593e6e8-1fc5-4776-a1c7-7620dcf83565 · outbound

This paper cites Star: A benchmark for situated reasoning in real-world videos.

Token Activation Map to Visually Explain Multimodal LLMs Star: A benchmark for situated reasoning in real-world videos

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:31.519512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1e49da6f-40ab-42a7-aeb0-a8ae0eeb2f01 · outbound

This paper cites Efficient streaming language models with attention sinks.

Token Activation Map to Visually Explain Multimodal LLMs Efficient streaming language models with attention sinks

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:31.306564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 84be4017-1d5c-4212-b382-2eb7d37008b0 · outbound

This paper cites A survey on causal inference.

Token Activation Map to Visually Explain Multimodal LLMs A survey on causal inference

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:31.119616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0e52b13d-beb8-43b3-8e25-e2980e367942 · outbound

This paper cites From redundancy to relevance: Enhancing explainability in multimodal large language mod- els.

Token Activation Map to Visually Explain Multimodal LLMs From redundancy to relevance: Enhancing explainability in multimodal large language mod- els

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:30.950021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0ec2ab28-29f7-4ab3-8a1a-d02842692370 · outbound

This paper cites Learning deep features for discrimina- tive localization.

Token Activation Map to Visually Explain Multimodal LLMs Learning deep features for discrimina- tive localization

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T21:52:28.534320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9278089c-6546-41d2-b914-a25a9151eebb · outbound

This paper cites with” and the punctuation mark “.

Token Activation Map to Visually Explain Multimodal LLMs with” and the punctuation mark “

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:30.630735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6bf0e808-16c8-4475-b27e-9a9e1a53e8d0 · outbound

This paper cites an unresolved cited work.

Token Activation Map to Visually Explain Multimodal LLMs Unresolved cited work

Reference 61

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:52:30.447211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 34a50edb-53d1-4e84-b268-dc2130cfdc34 · outbound

This paper cites living wall.

Token Activation Map to Visually Explain Multimodal LLMs living wall

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:30.265472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cad3c0e3-9e47-4c87-b66d-b1722867a254 · outbound

This paper cites living wall.

Token Activation Map to Visually Explain Multimodal LLMs living wall

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:30.081243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0ec197a3-1b0d-48b1-85b4-bda3adb45db0 · outbound

This paper cites Object-determined.

Token Activation Map to Visually Explain Multimodal LLMs Object-determined

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:29.923294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 42bfa086-e8c6-463a-8d82-7eb6d2113a8c · outbound

This paper cites Missing arrows led to erroneous reasoning.

Token Activation Map to Visually Explain Multimodal LLMs Missing arrows led to erroneous reasoning

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:29.760939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fa6da81a-05a1-4059-a00b-26a19f33bfe0 · outbound

This paper cites 2, 5, 6, 7, 14, 15.

Token Activation Map to Visually Explain Multimodal LLMs 2, 5, 6, 7, 14, 15

Reference 168

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:52:38.764893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c8836885-99c1-429f-8b6c-71ada12ddd70 · outbound

This paper cites an unresolved cited work.

Token Activation Map to Visually Explain Multimodal LLMs Unresolved cited work

Reference 2016

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:52:30.757393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ea323d48-56d5-4c18-97cd-36edf6b02d54 · outbound

This paper cites an unresolved cited work.

Token Activation Map to Visually Explain Multimodal LLMs Unresolved cited work

Reference 2017

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:52:32.418675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

Observation ee607a6c-424c-4103-8a9b-d5ac4adba379 · inbound

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models cites this paper.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Token Activation Map to Visually Explain Multimodal LLMs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:38.554863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61037376-a873-45fb-a438-086e6355c419 · inbound

Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward cites this paper.

Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward Token Activation Map to Visually Explain Multimodal LLMs

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:20:47.892061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 68b4e094-aaed-4176-9567-dc7d2db5ea9d · inbound

MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference cites this paper.

MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference Token Activation Map to Visually Explain Multimodal LLMs

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-11T01:45:52.037170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.