Paper Citation Record · LEDGER

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

As of 5 August 2026, this Paper Citation Record lists 99 of 99 outbound references and 8 inbound Pith citation observations for arXiv:2606.19531.

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

pith.paper-citation-record.v1
2606.19531 v1

Coverage vector

measured 99 of 99 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-26T21:02:24.792139Z

measured 107 of 107 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T00:44:09.563673Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-09T22:16:36.343123Z

Reference resolution

99 of 99 outbound references displayed

verified exact57
verified fuzzy0
unresolved39
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bb88c99b-f26e-4f06-ac68-7f8144631f14 · outbound

This paper cites Video prediction policy: A generalist robot policy with predictive visual representations.arXiv preprint, 2024.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Video prediction policy: A generalist robot policy with predictive visual representations.arXiv preprint, 2024

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55cf8d2c-e378-446b-aafe-a18898ff0784 · outbound

This paper cites World Action Models are Zero-shot Policies.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? World Action Models are Zero-shot Policies

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.467808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3e5fb449-95e6-44bb-a884-981bea3df0cc · outbound

This paper cites Causal World Modeling for Robot Control.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Causal World Modeling for Robot Control

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.491633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1d603c82-7b96-4ff3-9bc8-944b3ab84c57 · outbound

This paper cites Dit4dit: Jointly modeling video dynamics and actions for generalizable robot control.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Dit4dit: Jointly modeling video dynamics and actions for generalizable robot control

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.484291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation da15809f-ac50-4c19-88ab-a4941754f2d2 · outbound

This paper cites Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.436744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8806fd25-8b79-4fb0-8f2d-fbc5721e0fef · outbound

This paper cites Bagelvla: Enhancing long-horizon manipulation via interleaved vision-language-action generation.CoRR, abs/2602.09849.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Bagelvla: Enhancing long-horizon manipulation via interleaved vision-language-action generation.CoRR, abs/2602.09849

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.459384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2fc7ab0e-a2cc-4f98-8656-9c603164ae31 · outbound

This paper cites UAM: A Dual-Stream Perspective on Forgetting in VLA Training.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? UAM: A Dual-Stream Perspective on Forgetting in VLA Training

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.457436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8745c12b-469d-43bf-befc-56524f10daa2 · outbound

This paper cites AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.489624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3cbd8d2b-fb12-46a5-a3b1-5336238b6068 · outbound

This paper cites Unified world models: Coupling video and action diffusion for pretraining on large robotic datasets.arXiv preprint, 2025.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Unified world models: Coupling video and action diffusion for pretraining on large robotic datasets.arXiv preprint, 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66749db6-7b82-4394-8ced-461f35ebfd52 · outbound

This paper cites LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T00:39:17.385932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c2350027-27ce-45d1-a687-15dbb9000079 · outbound

This paper cites Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.374363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 57a6f44a-2bea-45f8-bdf3-5c200963474c · outbound

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

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Motus: A Unified Latent Action World Model

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.374184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 25347798-464b-4aa2-8c5a-9e67c39771b9 · outbound

This paper cites Fast-WAM: Do World Action Models Need Test-time Future Imagination?.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Fast-WAM: Do World Action Models Need Test-time Future Imagination?

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.345770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 97fae678-9072-4b65-9a4f-26a728759995 · outbound

This paper cites arXiv preprint arXiv:2603.17240 , year=.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? arXiv preprint arXiv:2603.17240 , year=

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.410662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fc6a206d-370a-47f8-8eaf-08b9c22d2e2d · outbound

This paper cites MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.382706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5c779dd0-6daf-4f43-895b-811706055d88 · outbound

This paper cites Reworld: Multi-dimensional reward modeling for embodied world models.arXiv preprint arXiv:2601.12428.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Reworld: Multi-dimensional reward modeling for embodied world models.arXiv preprint arXiv:2601.12428

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.379964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4468830d-c137-4bd6-a2b7-526e744b2ea5 · outbound

This paper cites Orv: 4d occupancy-centric robot video generation.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Orv: 4d occupancy-centric robot video generation

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.318561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8a7e792b-03f0-4fe0-ae1e-fc9c18abf86b · outbound

This paper cites TesserAct: Learning 4D Embodied World Models.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? TesserAct: Learning 4D Embodied World Models

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T00:39:17.407562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 09a1f3a2-efba-441a-bf4d-3066a5bc7ecb · outbound

This paper cites Scene graph disentanglement and composition for generalizable complex image generation.Advances in Neural Information Processing Systems, 37:98478–98504, 2024.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Scene graph disentanglement and composition for generalizable complex image generation.Advances in Neural Information Processing Systems, 37:98478–98504, 2024

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68c14e92-5f93-4d71-89ab-50c2bed12ba4 · outbound

This paper cites Nano banana pro.https://deepmind.google/technologies/gemini/, 2025.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Nano banana pro.https://deepmind.google/technologies/gemini/, 2025

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f02af53-4df3-4ecf-a7f9-c2c9f8353a79 · outbound

This paper cites GPT-Image-1.5.https://openai.com/index/new-chatgpt-images-is-here/, 2026.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? GPT-Image-1.5.https://openai.com/index/new-chatgpt-images-is-here/, 2026

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dfacc50-3044-436e-b1a1-c696d17de981 · outbound

This paper cites ImgEdit: A Unified Image Editing Dataset and Benchmark.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? ImgEdit: A Unified Image Editing Dataset and Benchmark

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.358514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d3fd09fc-a1e0-4db5-9927-11331ab8be47 · outbound

This paper cites Qwen-Image Technical Report.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Qwen-Image Technical Report

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.443553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e5ce8f5c-1ada-4a42-af99-6ebfc034226a · outbound

This paper cites Glm-image.https://huggingface.co/zai-org/GLM-Image, 2026.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Glm-image.https://huggingface.co/zai-org/GLM-Image, 2026

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91eb9690-007e-4ce1-8383-78c7d784bd25 · outbound

This paper cites NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.419935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7b80f4f7-d35e-47e2-84bf-ab3887ecc7b9 · outbound

This paper cites Longcat-next: Lexicalizing modalities as discrete tokens.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Longcat-next: Lexicalizing modalities as discrete tokens

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.481511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c5aaa63f-f241-4dcf-89ff-08905dbda029 · outbound

This paper cites Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.454286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d7782d6b-c758-40a0-8a40-0e99d0d7f834 · outbound

This paper cites Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.489219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3b2a4355-4f7a-4393-b59d-445e17d75e08 · outbound

This paper cites Magicbrush: A manually annotated dataset for instruction-guided image editing.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Magicbrush: A manually annotated dataset for instruction-guided image editing

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a9bca96-0817-4ad8-8670-8541b39e6314 · outbound

This paper cites Guiding instruction-based image editing via multimodal large language models.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Guiding instruction-based image editing via multimodal large language models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85834bbe-24b8-4385-886f-b331ea5d66a2 · outbound

This paper cites Emu edit: Precise image editing via recognition and generation tasks.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Emu edit: Precise image editing via recognition and generation tasks

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60268c47-cab4-4bd4-832b-ed8b01614dc6 · outbound

This paper cites Anyedit: Mastering unified high-quality image editing for any idea.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Anyedit: Mastering unified high-quality image editing for any idea

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afc015af-0f20-46b7-b41d-27add10fb77a · outbound

This paper cites Image Generators are Generalist Vision Learners.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Image Generators are Generalist Vision Learners

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.438144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d4147ffa-7d69-4dc8-95e0-276839c1df09 · outbound

This paper cites Diffusion Model as a Generalist Segmentation Learner.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Diffusion Model as a Generalist Segmentation Learner

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.422990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 526d87a1-7c32-4881-a54b-ddfdd7862d4b · outbound

This paper cites Leveraging Image Generators to Address Data Scarcity: The Gen4Regen Dataset for Forest Regeneration Mapping.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Leveraging Image Generators to Address Data Scarcity: The Gen4Regen Dataset for Forest Regeneration Mapping

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.416927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0509c2cc-1de9-4542-875d-ce00f9e75795 · outbound

This paper cites pi0: A vision-language-action flow model for general robot control.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? pi0: A vision-language-action flow model for general robot control

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 375cd041-792b-41f4-8889-e89e8caae296 · outbound

This paper cites pi0.5: a vision-language-action model with open-world generalization.arXiv preprint, 2025.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? pi0.5: a vision-language-action model with open-world generalization.arXiv preprint, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 105870cd-06ae-4c3c-9d6b-c3ca971de2ec · outbound

This paper cites Gr00t n1: An open foundation model for generalist humanoid robots.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Gr00t n1: An open foundation model for generalist humanoid robots

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc0dc4f3-9207-42c1-bbb4-4f0c6824d81f · outbound

This paper cites Dreamvla: A vision-language-action model dreamed with comprehensive world knowledge.arXiv preprint, 2025.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Dreamvla: A vision-language-action model dreamed with comprehensive world knowledge.arXiv preprint, 2025

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc2f5178-863e-4215-b1f6-ba371fc13ec7 · outbound

This paper cites Reconvla: Reconstructive vision-language-action model as effective robot perceiver.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Reconvla: Reconstructive vision-language-action model as effective robot perceiver

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c953e55b-3a7a-43a8-aae7-6005ab8d20f8 · outbound

This paper cites HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.448929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation db88cc04-c30a-4c28-864c-8cfed2513b62 · outbound

This paper cites PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policies.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policies

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.425754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4928c709-4293-4dd2-a8c9-ae42f4f9e16b · outbound

This paper cites Depthvla: Enhancing vision-language-action models with depth-aware spatial reasoning.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Depthvla: Enhancing vision-language-action models with depth-aware spatial reasoning

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.351632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9e20d433-8483-424e-8815-44a13802bb41 · outbound

This paper cites Spatialvla: Exploring spatial representations for visual-language-action model.arXiv preprint, 2025.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Spatialvla: Exploring spatial representations for visual-language-action model.arXiv preprint, 2025

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7488449-f3a2-412a-8bc5-3ffce10961a3 · outbound

This paper cites Predictive inverse dynamics models are scalable learners for robotic manipulation.ICLR, 2024.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Predictive inverse dynamics models are scalable learners for robotic manipulation.ICLR, 2024

Reference 45

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c0567e8-f909-4605-aefe-da49d1e3874a · outbound

This paper cites Cot-vla: Visual chain-of-thought reasoning for vision-language-action models.arXiv preprint, 2025.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Cot-vla: Visual chain-of-thought reasoning for vision-language-action models.arXiv preprint, 2025

Reference 46

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d3d711b-191d-4090-a626-c0bb205772f8 · outbound

This paper cites Transport Discrepancy as a Reliability Signal for Vision-Language-Action Models.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Transport Discrepancy as a Reliability Signal for Vision-Language-Action Models

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.496728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3f43bd6c-0aa9-4096-9776-af5ce84dcc5b · outbound

This paper cites Being-h0: Vision-language-action pretraining from large-scale human videos.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Being-h0: Vision-language-action pretraining from large-scale human videos

Reference 48

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61d533a4-7712-4317-b84c-043e57ea2e73 · outbound

This paper cites Unified diffusion vla: Vision-language-action model via joint discrete denoising diffusion process.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Unified diffusion vla: Vision-language-action model via joint discrete denoising diffusion process

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.352756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ab6841ed-a7aa-46b8-889c-cd84731cb13b · outbound

This paper cites Spatial forcing: Implicit spatial representation alignment for vision- language-action model.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Spatial forcing: Implicit spatial representation alignment for vision- language-action model

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.361427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7304a538-edaa-4395-b132-608c61fc49b8 · outbound

This paper cites Vla-jepa: Enhancing vision-language-action model with latent world model.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Vla-jepa: Enhancing vision-language-action model with latent world model

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.494341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d5cdf597-1f76-4d68-b72a-c0f1332bb108 · outbound

This paper cites Vla-adapter: An effective paradigm for tiny-scale vision-language-action model.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Vla-adapter: An effective paradigm for tiny-scale vision-language-action model

Reference 52

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2bb38f6-3ddc-47fa-8f33-a49eaf5c2754 · outbound

This paper cites A Pragmatic VLA Foundation Model.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? A Pragmatic VLA Foundation Model

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.379412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 69cf02e9-7140-473b-b6ba-a15b7c624c4a · outbound

This paper cites MolmoAct: Action Reasoning Models that can Reason in Space.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? MolmoAct: Action Reasoning Models that can Reason in Space

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.411368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 29857894-4f8e-42cd-9a14-732efa9d282d · outbound

This paper cites F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.372041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f1f3d92f-c05d-4754-b3e8-4e56ea20eac5 · outbound

This paper cites Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.315926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 11fa9e64-fa22-4e49-a0f3-d2cc74c18463 · outbound

This paper cites Seeing to act, prompting to specify: A bayesian factorization of vision language action policy.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Seeing to act, prompting to specify: A bayesian factorization of vision language action policy

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.377234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6056000c-c1ab-41ad-b785-3109ca2cd912 · outbound

This paper cites Learning universal policies via text-guided video generation.NeurIPS, 2024.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Learning universal policies via text-guided video generation.NeurIPS, 2024

Reference 58

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 784b60f0-9eeb-43f2-8e59-4863e28530af · outbound

This paper cites Zero-shot robotic manipulation with pretrained image-editing diffusion models.arXiv preprint, 2023.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Zero-shot robotic manipulation with pretrained image-editing diffusion models.arXiv preprint, 2023

Reference 59

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78d94391-2ea9-404c-a55d-9f6700deb43d · outbound

This paper cites Generalist bimanual manipulation via foundation video diffusion models.arXiv preprint, 2025.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Generalist bimanual manipulation via foundation video diffusion models.arXiv preprint, 2025

Reference 60

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b5e2f14-2e13-463d-9e72-a8bf5c2c14b8 · outbound

This paper cites Vidman: Exploiting implicit dynamics from video diffusion model for effective robot manipulation.NeurIPS, 2024.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Vidman: Exploiting implicit dynamics from video diffusion model for effective robot manipulation.NeurIPS, 2024

Reference 61

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74fcc968-2799-4902-913c-45a3397f77dd · outbound

This paper cites Murphy, Chelsea Finn, and Yilun Du.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Murphy, Chelsea Finn, and Yilun Du

Reference 62

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a78fae03-fe60-4ad9-a60c-293f8a4c3896 · outbound

This paper cites Large Video Planner Enables Generalizable Robot Control.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Large Video Planner Enables Generalizable Robot Control

Reference 63

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T00:39:17.321453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 00920460-fc74-4407-8332-ed14b0520ee3 · outbound

This paper cites Anypos: Automated task-agnostic actions for bimanual manipulation.arXiv preprint, 2025.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Anypos: Automated task-agnostic actions for bimanual manipulation.arXiv preprint, 2025

Reference 64

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de19a9f3-fd6e-47e8-9c07-45022c798637 · outbound

This paper cites Tc-idm: Grounding video generation for executable zero-shot robot motion.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Tc-idm: Grounding video generation for executable zero-shot robot motion

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.428620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e58da869-edcd-492c-95ea-0f9fb0fce6f7 · outbound

This paper cites Veo-act: How far can frontier video models advance generalizable robot manipulation? 2026.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Veo-act: How far can frontier video models advance generalizable robot manipulation? 2026

Reference 66

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d98d9d2e-6f0c-4044-900b-1bf18c42b8cd · outbound

This paper cites V AMPO: Policy optimization for improving visual dynamics in video action models.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? V AMPO: Policy optimization for improving visual dynamics in video action models

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.394923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fd943eb4-7439-4c96-bd18-58f8cf3a2319 · outbound

This paper cites Do World Action Models Generalize Better than VLAs? A Robustness Study.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Do World Action Models Generalize Better than VLAs? A Robustness Study

Reference 68

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.427944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3448e806-290e-4388-83ae-79aea7606673 · outbound

This paper cites WorldEval: World Model as Real-World Robot Policies Evaluator.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? WorldEval: World Model as Real-World Robot Policies Evaluator

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.498204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0aa67ed4-4f61-4427-9ba1-0dd92c6fa43a · outbound

This paper cites Kinema4d: Kinematic 4d world modeling for spatiotemporal embodied simulation, 2026.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Kinema4d: Kinematic 4d world modeling for spatiotemporal embodied simulation, 2026

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.486632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 935e3104-67d5-4bb1-ae65-53764a4d2599 · outbound

This paper cites WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL

Reference 71

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.433965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dfbbef40-6a09-4aa3-89ed-07011a2a21aa · outbound

This paper cites RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization

Reference 72

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.445163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4ff1ec73-74e3-4a7d-b10c-126d3e147026 · outbound

This paper cites UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling

Reference 73

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.465109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 905869cc-0d2d-42ac-b5a1-f95b68dda1dc · outbound

This paper cites Persistent robot world models: Stabilizing multi- step rollouts via reinforcement learning.arXiv preprint arXiv:2603.25685, 2026.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Persistent robot world models: Stabilizing multi- step rollouts via reinforcement learning.arXiv preprint arXiv:2603.25685, 2026

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.414015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation de531357-d7d4-4ba2-8563-86cfc7f0f692 · outbound

This paper cites Fate: Closed-loop feasibility-aware task generation with active repair for physically grounded robotic curricula.arXiv preprint arXiv:2603.01505, 2026.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Fate: Closed-loop feasibility-aware task generation with active repair for physically grounded robotic curricula.arXiv preprint arXiv:2603.01505, 2026

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.451736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0f438a2f-b26c-4524-8e23-1d02b2425c4a · outbound

This paper cites VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis

Reference 76

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.456675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c7a70452-d578-409e-a32a-a9c6d08002a6 · outbound

This paper cites Interactive world simulator for robot policy training and evaluation.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Interactive world simulator for robot policy training and evaluation

Reference 77

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.451543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 57c7b703-25db-4956-9d2c-87d108d8d84e · outbound

This paper cites World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry

Reference 78

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.462991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e6c788ca-136a-4193-a8b3-8ecb38839b1b · outbound

This paper cites World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems

Reference 79

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.470339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bbbb3e9b-cda3-43ae-a63d-5bd3d44b3f2b · outbound

This paper cites Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

Reference 80

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.499177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2251de90-0eb7-4782-8ab7-a819a181c546 · outbound

This paper cites dworldeval: Scalable robotic policy evaluation via discrete diffusion world model.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? dworldeval: Scalable robotic policy evaluation via discrete diffusion world model

Reference 81

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68440a13-9d8c-410b-9de8-5c82605775cf · outbound

This paper cites Interactive world simulator for robot policy training and evaluation.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Interactive world simulator for robot policy training and evaluation

Reference 82

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e537418e-723c-4118-8f8f-2c213335ddbe · outbound

This paper cites an unresolved cited work.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Unresolved cited work

Reference 83

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 891ebd45-3d91-4e59-b077-7546724672b3 · outbound

This paper cites Cosmos 3: Omnimodal World Models for Physical AI.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Cosmos 3: Omnimodal World Models for Physical AI

Reference 84

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.503977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation db9e670c-aa8c-4e7f-9acc-74fd93acba5c · outbound

This paper cites OmniGen2: Towards Instruction-Aligned Multimodal Generation.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? OmniGen2: Towards Instruction-Aligned Multimodal Generation

Reference 85

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.425424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 86578b31-29d0-469b-b3f0-e0c6be404263 · outbound

This paper cites Ovis-U1 Technical Report.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Ovis-U1 Technical Report

Reference 86

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.483974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6daf48e1-c49d-4601-b795-4e10bd1bd6ae · outbound

This paper cites FLUX.2: Frontier Visual Intelligence.https://bfl.ai/blog/flux-2, 2025.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? FLUX.2: Frontier Visual Intelligence.https://bfl.ai/blog/flux-2, 2025

Reference 87

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f66e74c9-5128-42bb-a262-ac921091081c · outbound

This paper cites Libero: Benchmarking knowledge transfer for lifelong robot learning.arXiv preprint, 2023.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Libero: Benchmarking knowledge transfer for lifelong robot learning.arXiv preprint, 2023

Reference 88

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcbcddc8-c2a0-40b7-84c6-e42809dcef7b · outbound

This paper cites LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models

Reference 89

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.501582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bb81c9a5-2dbb-4999-bd92-34e297a3d90a · outbound

This paper cites RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation

Reference 90

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.478920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7bd0c31e-2336-4fc0-a92b-09e08f8e7897 · outbound

This paper cites ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning

Reference 91

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:39:17.476110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 358e5826-1b6d-4992-a9c2-c95f290d10b8 · outbound

This paper cites Openvla: An open-source vision-language-action model.arXiv preprint, 2024.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Openvla: An open-source vision-language-action model.arXiv preprint, 2024

Reference 92

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f6d3ece-d196-458e-bb2b-9f30247be5bd · outbound

This paper cites LIBERO: benchmarking knowledge transfer for lifelong robot learning.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? LIBERO: benchmarking knowledge transfer for lifelong robot learning

Reference 93

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9661e013-9c30-4787-b8ba-c16769e88032 · outbound

This paper cites Univla: Learning to act anywhere with task-centric latent actions.arXiv preprint, 2025.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Univla: Learning to act anywhere with task-centric latent actions.arXiv preprint, 2025

Reference 94

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6df536dd-5ba4-4a2e-860b-8f92479e53a7 · outbound

This paper cites Fine-tuning vision-language-action models: Optimizing speed and success.arXiv preprint, 2025.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Fine-tuning vision-language-action models: Optimizing speed and success.arXiv preprint, 2025

Reference 95

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6a9cb63-31cb-4abd-b7ca-7bf46aea9909 · outbound

This paper cites Fast: Efficient action tokenization for vision-language-action models.arXiv preprint, 2025.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Fast: Efficient action tokenization for vision-language-action models.arXiv preprint, 2025

Reference 96

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb9c0662-b8c2-4117-9d68-c1dc0dfaf584 · outbound

This paper cites Worldvla: Towards autoregressive action world model.arXiv preprint, 2025.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Worldvla: Towards autoregressive action world model.arXiv preprint, 2025

Reference 97

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c25c564c-8273-4211-9a7e-a372c55ad769 · outbound

This paper cites Unified Vision-Language-Action Model.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Unified Vision-Language-Action Model

Reference 98

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:39:17.478757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e1f2d5fa-4b5a-461b-9c8a-c65358a4e9a2 · outbound

This paper cites Representationalignmentforgeneration: Trainingdiffusiontransformersiseasierthanyouthink.

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? Representationalignmentforgeneration: Trainingdiffusiontransformersiseasierthanyouthink

Reference 99

Resolution: unresolved; no resolver link, observed 2026-06-26T21:02:24.792139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation db64921a-7e5f-4e69-8e4a-b4f9d1a4cb15 · inbound

ABot-M0.5: Unified Mobility-and-Manipulation World Action Model cites this paper.

ABot-M0.5: Unified Mobility-and-Manipulation World Action Model ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

Reference 77

Resolution: verified exact; local_arxiv, observed 2026-07-02T14:27:03.166204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 65c4f8c6-d1ef-47d5-a90f-41e7a1289e64 · inbound

ABot-M0.5: Unified Mobility-and-Manipulation World Action Model cites this paper.

ABot-M0.5: Unified Mobility-and-Manipulation World Action Model ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

Reference 77

Resolution: unresolved; no resolver link, observed 2026-07-12T09:22:08.000379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71d2ccd4-84eb-47f8-b566-dfded78279e5 · inbound

WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time cites this paper.

WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-07-09T22:16:36.344563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ec7efade-5d5f-4b4f-ae57-6a1d700fdc21 · inbound

WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time cites this paper.

WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T06:48:14.554799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95e3db30-fa90-42e0-8294-3544737834fb · inbound

LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments cites this paper.

LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

Reference 97

Resolution: unresolved; no resolver link, observed 2026-07-31T23:29:15.579570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 671ec938-b253-4260-961e-f997e3e5d774 · inbound

Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control cites this paper.

Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T11:27:05.681731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95b61b4f-5aed-4deb-8e15-66783e7c5618 · inbound

Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control cites this paper.

Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T03:23:44.956053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c35ee440-b94a-4d52-af34-7428fc87f338 · inbound

Disentangling Visuo-Tactile Foresight: Oracle-Guided Interface Discovery for World Action Models cites this paper.

Disentangling Visuo-Tactile Foresight: Oracle-Guided Interface Discovery for World Action Models ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T00:44:09.563673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.