Paper Citation Record · LEDGER

Multimodal Function Vectors for Visual Relations

As of 21 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2510.02528.

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

pith.paper-citation-record.v1
2510.02528 v2

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T12:44:42.337781Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+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

19 of 19 outbound references displayed

verified exact0
verified fuzzy0
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f13b2e2d-c20d-445b-9103-e55efb8cabcd · outbound

This paper cites Eliciting Latent Predictions from Transformers with the Tuned Lens.

Multimodal Function Vectors for Visual Relations Eliciting Latent Predictions from Transformers with the Tuned Lens

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:41.324937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef4c30a3-9983-491b-b1f1-65b4e19d96f3 · outbound

This paper cites Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901,.

Multimodal Function Vectors for Visual Relations Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:41.471583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 471bf564-8b18-4611-9926-538ddd761c18 · outbound

This paper cites In-Context Learning Creates Task Vectors.

Multimodal Function Vectors for Visual Relations In-Context Learning Creates Task Vectors

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:41.828160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 357b3f12-c6c0-4d03-bf30-9fac226e18a6 · outbound

This paper cites Multimodal task vectors enable many-shot multimodal in-context learning.

Multimodal Function Vectors for Visual Relations Multimodal task vectors enable many-shot multimodal in-context learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:41.860652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 047a46ae-68fa-4009-ac25-d380589c31be · outbound

This paper cites Linguistic regularities in continuous space word representations.

Multimodal Function Vectors for Visual Relations Linguistic regularities in continuous space word representations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:41.922600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56fa0c16-5ee1-4918-b368-1651308262ce · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

Multimodal Function Vectors for Visual Relations The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:41.944932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38d9874e-9fa0-4c22-a9b9-1634b3db42e3 · outbound

This paper cites Automatic Discovery of Visual Circuits.

Multimodal Function Vectors for Visual Relations Automatic Discovery of Visual Circuits

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:42.010766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c98764d-d507-417a-9f62-c5331986484f · outbound

This paper cites Li, Arnab Sen Sharma, Aaron Mueller, Byron C.

Multimodal Function Vectors for Visual Relations Li, Arnab Sen Sharma, Aaron Mueller, Byron C

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:42.062353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 881effc7-d9ee-45dc-b7f4-b27185076dc3 · outbound

This paper cites Function Vectors in Large Language Models.

Multimodal Function Vectors for Visual Relations Function Vectors in Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:42.073130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e83c6a99-8aa7-4f0b-aad7-9544aca42ce5 · outbound

This paper cites Steering Language Models With Activation Engineering.

Multimodal Function Vectors for Visual Relations Steering Language Models With Activation Engineering

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:42.102750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a45c559-da8b-4a11-8938-b7f306abf84d · outbound

This paper cites Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models.

Multimodal Function Vectors for Visual Relations Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:42.134230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0ea5ba7-73be-4cd4-8f3d-880d99310da9 · outbound

This paper cites Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning.

Multimodal Function Vectors for Visual Relations Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:42.196116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90a2fd80-c948-47a5-ac98-615f5aa172fe · outbound

This paper cites From this dataset, we selected 32 diverse objects spanning various categories and size ranges, which were subsequently mapped to a relatively uniform scale.

Multimodal Function Vectors for Visual Relations From this dataset, we selected 32 diverse objects spanning various categories and size ranges, which were subsequently mapped to a relatively uniform scale

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:42.337781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1564b451-a3a0-4ac9-80cf-75dad5e35538 · outbound

This paper cites Improving Activation Steering in Language Models with Mean-Centring.

Multimodal Function Vectors for Visual Relations Improving Activation Steering in Language Models with Mean-Centring

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:41.880589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67fde6f4-d426-4769-bb32-61f74d561522 · outbound

This paper cites Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey.

Multimodal Function Vectors for Visual Relations Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:41.600573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3ce60a4-f745-44e6-921f-7c994602a1d8 · outbound

This paper cites Flamingo: a Visual Language Model for Few-Shot Learning.

Multimodal Function Vectors for Visual Relations Flamingo: a Visual Language Model for Few-Shot Learning

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:41.101436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a78a07a3-cce5-4f77-afb8-59206c3f3828 · outbound

This paper cites What learning algorithm is in-context learning? Investigations with linear models.

Multimodal Function Vectors for Visual Relations What learning algorithm is in-context learning? Investigations with linear models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:41.036447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31d8b188-933d-420e-bb95-d9166820a6b1 · outbound

This paper cites Toy Models of Superposition.

Multimodal Function Vectors for Visual Relations Toy Models of Superposition

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:41.764749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e7dfa0c-e1f1-43f3-9915-c62bcfca6b7c · outbound

This paper cites OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models.

Multimodal Function Vectors for Visual Relations OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T12:44:41.223094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.