Paper Citation Record · LEDGER

DiMaS: Distribution Matching for Steering Vision-Language-Action Models

As of 7 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2607.14280.

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

pith.paper-citation-record.v1
2607.14280 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T02:40:39.162784Z

measured 31 of 31 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 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

31 of 31 outbound references displayed

verified exact0
verified fuzzy0
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f3427038-a19f-42cf-a590-2bf1babc13e2 · outbound

This paper cites Flamingo: a visual language model for few-shot learning.Advances in Neural Information Processing Systems (NeurIPS), 35:23716–23736, 2022.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Flamingo: a visual language model for few-shot learning.Advances in Neural Information Processing Systems (NeurIPS), 35:23716–23736, 2022

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:35.506325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a30d7ba-9533-40e5-bdde-87a241b0f689 · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Refusal in Language Models Is Mediated by a Single Direction

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:35.586733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dc3674a-bc72-4ea7-b059-1d480503630f · outbound

This paper cites Do Sparse Autoencoders Capture Concept Manifolds?.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Do Sparse Autoencoders Capture Concept Manifolds?

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:35.723487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba6503d9-4bc4-4e5a-b0ab-6c96a4bc06bf · outbound

This paper cites Language models are few-shot learners.Advances in Neural Information Processing Systems (NeurIPS), 33:1877–1901, 2020.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Language models are few-shot learners.Advances in Neural Information Processing Systems (NeurIPS), 33:1877–1901, 2020

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:35.852924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 120e8c9b-123f-48b5-8a7a-d094de50e1ea · outbound

This paper cites Observing and controlling features in vision-language-action models.arXiv preprint arXiv:2603.05487, 2026.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Observing and controlling features in vision-language-action models.arXiv preprint arXiv:2603.05487, 2026

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:35.914579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dde5830-9c05-4b3c-b17c-cad3fd708abf · outbound

This paper cites Toy Models of Superposition.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Toy Models of Superposition

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:36.096408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8678e445-db98-4b56-920e-fc76d4637c67 · outbound

This paper cites Not all language model features are one-dimensionally linear.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Not all language model features are one-dimensionally linear

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:36.180715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf7ae672-17fb-434a-a3b0-84017c78795e · outbound

This paper cites MolmoAct2: Action Reasoning Models for Real-world Deployment.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models MolmoAct2: Action Reasoning Models for Real-world Deployment

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:36.286530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b14d983-37a2-4af7-832f-d19cce02f6bd · outbound

This paper cites Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:36.370496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c1350fa-3ba2-484d-b98d-3404970b62c0 · outbound

This paper cites Pot: Python optimal transport.Journal of Machine Learning Research, 22(78):1–8, 2021.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Pot: Python optimal transport.Journal of Machine Learning Research, 22(78):1–8, 2021

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:36.551513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c86c9f4-cc50-41d1-ac27-748b97a1308f · outbound

This paper cites Mechanistic interpretability for steering vision-language-action models.Conference on Robot Learning (CoRL), 2025.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Mechanistic interpretability for steering vision-language-action models.Conference on Robot Learning (CoRL), 2025

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:36.683377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13a74650-c95e-4844-93f9-16cc65fce2cb · outbound

This paper cites An- alyzing fine-tuning representation shift for multimodal llms steering alignment.International Conference on Computer Vision, 2025.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models An- alyzing fine-tuning representation shift for multimodal llms steering alignment.International Conference on Computer Vision, 2025

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:36.881882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 069c8e2d-7624-4379-9476-738f6ddbd6d0 · outbound

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

DiMaS: Distribution Matching for Steering Vision-Language-Action Models OpenVLA: An Open-Source Vision-Language-Action Model

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:37.026430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 986a4fb8-74a9-4271-8292-8b9fef74e44b · outbound

This paper cites Auto-Encoding Variational Bayes.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Auto-Encoding Variational Bayes

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:37.179132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faab1575-d75a-4c1c-8016-02174d1fc844 · outbound

This paper cites Flow Matching for Generative Modeling.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Flow Matching for Generative Modeling

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:37.340685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8f32887-4d43-4ccb-a5e7-2862122ee2e7 · outbound

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

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Libero: Benchmarking knowledge transfer for lifelong robot learning.Advances in Neural Information Processing Systems, 36:44776–44791, 2023

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:37.486935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3d1aa53-b579-48ee-9565-3a8d10bcce68 · outbound

This paper cites Sparse autoencoders learn monosemantic features in vision-language models.Advances in Neural Information Processing Systems, 38:95706–95742, 2026.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Sparse autoencoders learn monosemantic features in vision-language models.Advances in Neural Information Processing Systems, 38:95706–95742, 2026

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:37.602817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4854176b-10ef-4120-9c37-9d140b99f210 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Steering Llama 2 via Contrastive Activation Addition

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:37.783344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da093ff9-40fb-406d-bc10-9d6d111fbb68 · outbound

This paper cites Learning to steer: Input-dependent steering for multimodal llms.Advances in Neural Information Processing Systems, 38:159799–159834, 2026.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Learning to steer: Input-dependent steering for multimodal llms.Advances in Neural Information Processing Systems, 38:159799–159834, 2026

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:37.875011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d97f847-b05c-4ef1-9ff9-0cf5190eec42 · outbound

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

DiMaS: Distribution Matching for Steering Vision-Language-Action Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:37.980804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa8408ba-f25e-437a-be40-cbcce7a70f3d · outbound

This paper cites $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:38.119936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f90c9b0-0516-4e52-a06c-b5a4630a2fb1 · outbound

This paper cites Hallucination reduction with casal: Contrastive activation steering for amortized learning.arXiv preprint arXiv:2510.02324, 2025.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Hallucination reduction with casal: Contrastive activation steering for amortized learning.arXiv preprint arXiv:2510.02324, 2025

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:38.236474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 915d921a-4246-4d20-a916-2d19047ccf6c · outbound

This paper cites Learning transferable visual models from natural language supervision.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Learning transferable visual models from natural language supervision

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:38.358389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a9430f9-f464-4ede-9c1f-b0526618a1af · outbound

This paper cites Controlling language and diffusion models by transporting activations.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Controlling language and diffusion models by transporting activations

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:38.478432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9470cf52-499e-4ad6-9718-c0aad4b03fb3 · outbound

This paper cites Low-rank sinkhorn factorization, 2021.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Low-rank sinkhorn factorization, 2021

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:38.585122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53c2017b-b7c2-4715-a759-e1921699240d · outbound

This paper cites Interfacegan: Interpreting the disentangled face representation learned by gans.IEEE transactions on pattern analysis and machine intelligence, 44(4):2004–2018, 2020.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Interfacegan: Interpreting the disentangled face representation learned by gans.IEEE transactions on pattern analysis and machine intelligence, 44(4):2004–2018, 2020

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:38.707927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bc26fef-90c7-4b4c-9023-cabe43107699 · outbound

This paper cites SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:38.837139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cbe06d8-5449-4b1f-a9d1-cc301832e0b9 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models LLaMA: Open and Efficient Foundation Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:38.956222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ec30ff9-62fd-46d4-abf1-c486d951e540 · outbound

This paper cites Steering Language Models With Activation Engineering.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Steering Language Models With Activation Engineering

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:39.042605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 831d7ae1-65ed-4614-aed4-582c51a15d9a · outbound

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

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Rt-2: Vision-language-action models transfer web knowledge to robotic control

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:39.080256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a020e014-5f7f-4421-8563-51059d6b564c · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

DiMaS: Distribution Matching for Steering Vision-Language-Action Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T02:40:39.162784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.