Paper Citation Record · LEDGER

How Visual Representations Map to Language Feature Space in Multimodal LLMs

As of 13 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 4 inbound Pith citation observations for arXiv:2506.11976.

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

pith.paper-citation-record.v1
2506.11976 v2

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T01:06:08.321921Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T04:17:56.147155Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T22:17:26.125055Z

Reference resolution

29 of 29 outbound references displayed

verified exact0
verified fuzzy18
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d3699c23-1c90-4763-8c70-44707168202f · outbound

This paper cites Towards monosemanticity: Decomposing language models with dictionary learning, 2023.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Towards monosemanticity: Decomposing language models with dictionary learning, 2023

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:12.186433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 07ce8781-2025-4982-8acf-de1552b550a7 · outbound

This paper cites Interpreting and Controlling Vision Foundation Models via Text Explanations.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Interpreting and Controlling Vision Foundation Models via Text Explanations

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:06.285352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66ce3c5d-6bcf-4256-b409-918c0da41987 · outbound

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

How Visual Representations Map to Language Feature Space in Multimodal LLMs InstructBLIP: Towards general-purpose vision-language models with instruction tuning

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:11.979935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7e7d4643-cb6b-4356-abae-16728f76041d · outbound

This paper cites The cognitive revolution in interpretability: From explaining behavior to interpreting representations and algorithms, 2024.

How Visual Representations Map to Language Feature Space in Multimodal LLMs The cognitive revolution in interpretability: From explaining behavior to interpreting representations and algorithms, 2024

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:11.736793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7c89694a-e792-44b8-a725-35da8d656625 · outbound

This paper cites Arik, Tejas Nama, and Tomas Pfister.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Arik, Tejas Nama, and Tomas Pfister

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:11.548557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5236b704-0e78-42c1-9656-03a507e1ed67 · outbound

This paper cites A mathemati- cal framework for transformer circuits.

How Visual Representations Map to Language Feature Space in Multimodal LLMs A mathemati- cal framework for transformer circuits

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:11.309715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b317eb25-217e-4507-9681-f25af730f1b5 · outbound

This paper cites Mme: A compre- hensive evaluation benchmark for multimodal large language models, 2024.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Mme: A compre- hensive evaluation benchmark for multimodal large language models, 2024

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:06.715063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a117c9c-7741-4049-a70a-582d506c319e · outbound

This paper cites Interpreting CLIP's Image Representation via Text-Based Decomposition.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Interpreting CLIP's Image Representation via Text-Based Decomposition

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:06.784761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1144db9-52c8-4570-8c84-dbfcb944205a · outbound

This paper cites Sparse autoencoders find highly interpretable features in language models.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Sparse autoencoders find highly interpretable features in language models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:11.122586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 404ab531-414f-4122-a3e4-11bce77cf204 · outbound

This paper cites Hudson and Christopher D.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Hudson and Christopher D

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:10.917163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 25f00dca-de3e-4cfd-883d-653b0b12c346 · outbound

This paper cites Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:06.969709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8983eb4-1142-47d0-a99a-f09f64e827d3 · outbound

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

How Visual Representations Map to Language Feature Space in Multimodal LLMs Evaluating object hallucination in large vision- language models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:10.725401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation bc6efdc3-a151-4fdc-8221-4521bf9c9819 · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:07.108965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd8c4433-db51-480c-9055-8664a4eeb97a · outbound

This paper cites Vila: On pre-training for vi- sual language models.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Vila: On pre-training for vi- sual language models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:10.496925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation effa39d3-0c87-4fb8-82dc-ef0a4cb5c2e6 · outbound

This paper cites Visual instruction tuning.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Visual instruction tuning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:07.260602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84d95b6d-8393-4dd3-8645-5dce02161448 · outbound

This paper cites Improved baselines with visual instruction tuning.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Improved baselines with visual instruction tuning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:10.270709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f6af390d-ded8-46ac-8748-6fbbe7850e37 · outbound

This paper cites Linearly mapping from image to text space.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Linearly mapping from image to text space

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:10.054001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 92687b32-7c75-438b-814d-b08c34cffdf8 · outbound

This paper cites Towards Interpreting Visual Information Processing in Vision-Language Models.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Towards Interpreting Visual Information Processing in Vision-Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:07.506978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 847a9d7a-2e48-49a5-be4d-14db007b01ea · outbound

This paper cites Interpreting GPT: The Logit Lens.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Interpreting GPT: The Logit Lens

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:09.841272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5022e038-1a89-4d2d-97d9-b8f83fd8bd5a · outbound

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

How Visual Representations Map to Language Feature Space in Multimodal LLMs Towards vision-language mechanistic interpretabil- ity: A causal tracing tool for blip

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:07.644453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d98f162a-bd02-4070-869c-7b659162ab52 · outbound

This paper cites Bridg- ing vision and language spaces with assignment prediction.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Bridg- ing vision and language spaces with assignment prediction

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:09.654978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ca3e0edd-32ae-4375-bd68-ed81739091d9 · outbound

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

How Visual Representations Map to Language Feature Space in Multimodal LLMs Learning transferable visual models from natural language supervi- sion

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:09.493256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5f3e4212-a992-4b9f-8e5d-e364113e2139 · outbound

This paper cites Multimodal neurons in pre- trained text-only transformers.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Multimodal neurons in pre- trained text-only transformers

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:09.338873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 54ecaa4c-e899-43b5-925b-20aa394b7bd5 · outbound

This paper cites Open Problems in Mechanistic Interpretability.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Open Problems in Mechanistic Interpretability

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:07.977614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1937f5de-3784-4034-89c3-3e0a890480da · outbound

This paper cites Paligemma 2: A family of versatile vlms for transfer, 2024.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Paligemma 2: A family of versatile vlms for transfer, 2024

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:09.161200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2083da55-8b62-4185-94f9-0d851b8bdc27 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Gemma 2: Improving Open Language Models at a Practical Size

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T01:06:08.123176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9431d42-e8cf-47df-9a14-6e6a98d5e4d6 · outbound

This paper cites an unresolved cited work.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-07T01:06:08.998912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 35c4f53e-89b3-4c81-81b7-9e89d9844c1c · outbound

This paper cites Metamorph: Multimodal un- derstanding and generation via instruction tuning, 2024.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Metamorph: Multimodal un- derstanding and generation via instruction tuning, 2024

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:08.844753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 85d98845-988b-458e-8ad4-bda971176a71 · outbound

This paper cites Too late to recall: The two-hop prob- lem in multimodal knowledge retrieval.

How Visual Representations Map to Language Feature Space in Multimodal LLMs Too late to recall: The two-hop prob- lem in multimodal knowledge retrieval

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:06:08.657295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

Observation 7f81683f-e654-4363-ad77-03ebc2dffce9 · inbound

Interpretable Open-Vocabulary Referring Object Detection with Reverse Contrast Attention cites this paper.

Interpretable Open-Vocabulary Referring Object Detection with Reverse Contrast Attention How Visual Representations Map to Language Feature Space in Multimodal LLMs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T13:57:07.449816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab9ce2f3-d682-4f24-bbce-0a77ab76cb60 · inbound

Look Less, Reason More: Block-wise Attention Skipping for Efficient Multimodal LLMs cites this paper.

Look Less, Reason More: Block-wise Attention Skipping for Efficient Multimodal LLMs How Visual Representations Map to Language Feature Space in Multimodal LLMs

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:17:26.126763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4f28d0ec-44f2-4d3f-927d-2075dbb823b4 · inbound

Pathways of Visual Information Flow in Vision-Language Models cites this paper.

Pathways of Visual Information Flow in Vision-Language Models How Visual Representations Map to Language Feature Space in Multimodal LLMs

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-12T03:03:11.110105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e97f989c-c33a-4426-8979-5210adbd71a5 · inbound

Multimodal Model Diffing for Feature Discovery and Control cites this paper.

Multimodal Model Diffing for Feature Discovery and Control How Visual Representations Map to Language Feature Space in Multimodal LLMs

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-11T04:17:56.147155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.