Paper Citation Record · LEDGER

DiLA: Disentangled Latent Action World Models

As of 21 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 2 inbound Pith citation observations for arXiv:2605.15725.

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

pith.paper-citation-record.v1
2605.15725 v1

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-20T19:35:37.527479Z

measured 36 of 36 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T02:52:21.389444Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

34 of 34 outbound references displayed

verified exact22
verified fuzzy4
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch6

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 38cb3b1b-11df-421f-82da-8537eb73c365 · outbound

This paper cites V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning.

DiLA: Disentangled Latent Action World Models V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:38:56.278078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4fee35a7-f781-418c-9eaf-bb0cbf3e2e0d · outbound

This paper cites Motus: A Unified Latent Action World Model.

DiLA: Disentangled Latent Action World Models Motus: A Unified Latent Action World Model

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:38:56.282432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d1eda4a1-a90c-47a9-ad47-6644f3388c4e · outbound

This paper cites RT-1: Robotics Transformer for Real-World Control at Scale.

DiLA: Disentangled Latent Action World Models RT-1: Robotics Transformer for Real-World Control at Scale

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:38:56.338873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 58bbdd36-2797-48af-aba1-d1228d1844e6 · outbound

This paper cites UniVLA: Learning to Act Anywhere with Task-centric Latent Actions.

DiLA: Disentangled Latent Action World Models UniVLA: Learning to Act Anywhere with Task-centric Latent Actions

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:38:56.301035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ec9a79a5-9e97-473b-bd2c-63a9685361e0 · outbound

This paper cites IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI.

DiLA: Disentangled Latent Action World Models IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T19:38:56.388138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d6b892e4-324c-4450-9bc8-557dfc84dcb4 · outbound

This paper cites Learning skills from action-free videos.

DiLA: Disentangled Latent Action World Models Learning skills from action-free videos

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:38:56.383962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 54ceb37a-6a29-4cc1-8003-87bef28834e6 · outbound

This paper cites Learning latent action world models in the wild.

DiLA: Disentangled Latent Action World Models Learning latent action world models in the wild

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:38:56.346894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 934f1c32-356b-44da-9f54-8e717575702e · outbound

This paper cites The "something something" video database for learning and evaluating visual common sense.

DiLA: Disentangled Latent Action World Models The "something something" video database for learning and evaluating visual common sense

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:38:56.295557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1dfa8652-7124-4f99-a039-7d29d0201766 · outbound

This paper cites Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning.

DiLA: Disentangled Latent Action World Models Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:38:56.392763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4874fe2e-bbb9-4a6c-a88f-d1c0aa950f49 · outbound

This paper cites 2018 , copyright =.

DiLA: Disentangled Latent Action World Models 2018 , copyright =

Reference 11

Resolution: metadata mismatch; doi, observed 2026-05-20T19:38:55.966820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a82c5498-a51f-4c3e-808a-425d6a29d149 · outbound

This paper cites Dream to Control: Learning Behaviors by Latent Imagination.

DiLA: Disentangled Latent Action World Models Dream to Control: Learning Behaviors by Latent Imagination

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T19:38:56.379480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 58b0b909-c325-4d96-86da-a50edb11dc0c · outbound

This paper cites Inter-environmental world modeling for continuous and compositional dynamics.

DiLA: Disentangled Latent Action World Models Inter-environmental world modeling for continuous and compositional dynamics

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:38:56.335090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 18da8698-da7c-4f7c-ba0d-8923f9c8c58a · outbound

This paper cites Pre-Trained Video Generative Models as World Simulators.

DiLA: Disentangled Latent Action World Models Pre-Trained Video Generative Models as World Simulators

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:38:56.309993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b8703ddf-bf99-4d80-a76f-6af48c168d09 · outbound

This paper cites J., and Lee, Y.

DiLA: Disentangled Latent Action World Models J., and Lee, Y

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:38:56.323113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 30b7b462-f774-472a-955f-aa18b8af29b6 · outbound

This paper cites Auto-Encoding Variational Bayes.

DiLA: Disentangled Latent Action World Models Auto-Encoding Variational Bayes

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:38:56.315302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e532c56d-2058-4223-9c1a-236b0c3ebb6d · outbound

This paper cites Neural Fourier Transform: A General Approach to Equivariant Representation Learning.

DiLA: Disentangled Latent Action World Models Neural Fourier Transform: A General Approach to Equivariant Representation Learning

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:38:56.351181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 19b7aa36-932c-4944-a7aa-e8c49e54981f · outbound

This paper cites LoopNav: Benchmarking Spatial Consistency in World Models.

DiLA: Disentangled Latent Action World Models LoopNav: Benchmarking Spatial Consistency in World Models

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T19:38:56.355713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c7f8863b-ea33-4af4-9924-394506769a34 · outbound

This paper cites StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation.

DiLA: Disentangled Latent Action World Models StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:38:56.319759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d0871f68-f569-4967-8a10-3331d16d1756 · outbound

This paper cites UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction.

DiLA: Disentangled Latent Action World Models UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:38:56.369402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a9217a7a-6a4e-49e1-acca-7626da8dc0bf · outbound

This paper cites Deep Dynamics Models for Learning Dexterous Manipulation.

DiLA: Disentangled Latent Action World Models Deep Dynamics Models for Learning Dexterous Manipulation

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:38:56.331449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 93deed4b-d888-4420-954e-e7f115c988a2 · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

DiLA: Disentangled Latent Action World Models DINOv2: Learning Robust Visual Features without Supervision

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:38:56.326517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5a38538d-779e-4407-92de-a105492aa84f · outbound

This paper cites A Generalist Agent.

DiLA: Disentangled Latent Action World Models A Generalist Agent

Reference 23

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T19:38:56.397131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1341d77d-aafa-4bc4-bc9b-3a9c5c13df36 · outbound

This paper cites Vipra: Video prediction for robot actions.

DiLA: Disentangled Latent Action World Models Vipra: Video prediction for robot actions

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:38:56.360528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a0eae18d-6457-4abe-a89d-537846eb6db3 · outbound

This paper cites Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video.

DiLA: Disentangled Latent Action World Models Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T19:38:56.373457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fd241733-68d4-4cf9-b831-9d64e63d715e · outbound

This paper cites Dyn-O: Building Structured World Models with Object-Centric Representations.

DiLA: Disentangled Latent Action World Models Dyn-O: Building Structured World Models with Object-Centric Representations

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:38:56.402159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 063d607a-2f9e-4e72-aa3b-2e12e0a5d47f · outbound

This paper cites DSVAE: Interpretable Disentangled Representation for Synthetic Speech Detection.

DiLA: Disentangled Latent Action World Models DSVAE: Interpretable Disentangled Representation for Synthetic Speech Detection

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:38:56.286919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9d077384-3d62-4f57-a49a-0e2e233766a6 · outbound

This paper cites Latent Action Pretraining from Videos.

DiLA: Disentangled Latent Action World Models Latent Action Pretraining from Videos

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:38:56.304993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 935890a6-3317-49f0-8971-aabcae494632 · outbound

This paper cites Diffusion Transformers with Representation Autoencoders.

DiLA: Disentangled Latent Action World Models Diffusion Transformers with Representation Autoencoders

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:38:56.365028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cb17dd21-9a31-4cfd-9136-7d1573502c95 · outbound

This paper cites To maintain an information capacity comparable to our continuous baseline, we configure the VQ layer with a codebook size of 8 and a quantized embedding dimension of.

DiLA: Disentangled Latent Action World Models To maintain an information capacity comparable to our continuous baseline, we configure the VQ layer with a codebook size of 8 and a quantized embedding dimension of

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:38:57.565810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 716bcc47-2e63-4812-b234-8dce2f849825 · outbound

This paper cites an unresolved cited work.

DiLA: Disentangled Latent Action World Models Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-05-20T19:38:57.562613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 46c6ab38-1c0a-4999-a581-ef7fd2bed67c · outbound

This paper cites ParametersDiLALAPA MOTOADAWORLD(LAM) ADAWORLD VILLA-X Trainable123M 344M 440M 500M 1.5B 239M Frozen500M - - - - - B.

DiLA: Disentangled Latent Action World Models ParametersDiLALAPA MOTOADAWORLD(LAM) ADAWORLD VILLA-X Trainable123M 344M 440M 500M 1.5B 239M Frozen500M - - - - - B

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:38:57.559604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d0d79b7c-b452-4bbb-a67a-5767573b5ff2 · outbound

This paper cites jump” and “pitch.

DiLA: Disentangled Latent Action World Models jump” and “pitch

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:38:57.556245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c02e5816-44a1-4c37-a043-8e914f1d76b0 · outbound

This paper cites Our implementation follows Nagabandi et al.

DiLA: Disentangled Latent Action World Models Our implementation follows Nagabandi et al

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:38:57.553244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 00195b45-fdb9-4854-b376-be99206e31c5 · outbound

This paper cites Unlike the discrete actions in LoopNav, RECON features continuous and compound actions that reflect real-world vehicle dynamics.

DiLA: Disentangled Latent Action World Models Unlike the discrete actions in LoopNav, RECON features continuous and compound actions that reflect real-world vehicle dynamics

Reference 35

Resolution: malformed identifier; raw_fallback, observed 2026-05-20T19:38:57.550281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

Observation 1b24f676-0c99-46d7-99b3-380c18a49f60 · inbound

From Pixels to States: Rethinking Interactive World Models as Game Engines cites this paper.

From Pixels to States: Rethinking Interactive World Models as Game Engines DiLA: Disentangled Latent Action World Models

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-02T02:52:21.389444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b300f296-6da2-49b8-8b38-dd34301db05c · inbound

PhiZero: A World Model Built Around Physical Language cites this paper.

PhiZero: A World Model Built Around Physical Language DiLA: Disentangled Latent Action World Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-31T01:50:30.722872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.