Paper Citation Record · LEDGER

World Action Models: The Next Frontier in Embodied AI

As of 6 August 2026, this Paper Citation Record lists 100 of 299 outbound references and 28 inbound Pith citation observations for arXiv:2605.12090.

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

pith.paper-citation-record.v1
2605.12090 v1

Coverage vector

measured 100 of 299 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-13T05:01:16.802019Z

measured 128 of 128 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 28 of 28 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T14:52:35.528275Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-04T21:00:09.552907Z

Reference resolution

100 of 299 outbound references displayed

verified exact79
verified fuzzy11
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch9

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d0db0a94-0a79-41ba-9a30-923f59a2091e · outbound

This paper cites RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control.

World Action Models: The Next Frontier in Embodied AI RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.717454Z

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 fe20ddbe-47a4-4b93-8aec-de8731ec8aeb · outbound

This paper cites Openvla: An open-source vision-language-action model.

World Action Models: The Next Frontier in Embodied AI Openvla: An open-source vision-language-action model

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T11:07:40.201131Z

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 0abcb04e-8e8f-4ea2-85ef-99803828f873 · outbound

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

World Action Models: The Next Frontier in Embodied AI OpenVLA: An Open-Source Vision-Language-Action Model

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.706414Z

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 450957cc-ef1f-4417-a1be-3b38ced781b3 · outbound

This paper cites $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control.

World Action Models: The Next Frontier in Embodied AI $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.719828Z

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 0cb66ad3-f730-4c76-86ee-f49f60e17458 · outbound

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

World Action Models: The Next Frontier in Embodied AI LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.709173Z

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 a11ffd71-03ac-4ada-ae5a-f38467e3b14c · outbound

This paper cites World model- ing makes a better planner: Dual preference optimization for embodied task planning.

World Action Models: The Next Frontier in Embodied AI World model- ing makes a better planner: Dual preference optimization for embodied task planning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T11:07:40.203184Z

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 f057c73d-97fc-4863-9fe8-c063c4995ce2 · outbound

This paper cites ISBN 979-8-89176-251-0.

World Action Models: The Next Frontier in Embodied AI ISBN 979-8-89176-251-0

Reference 7

Resolution: verified exact; doi, observed 2026-05-13T05:02:16.743493Z

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 c20a33b8-6968-4825-b84f-1955a7f74b3f · outbound

This paper cites Learning Universal Policies via Text-Guided Video Generation.

World Action Models: The Next Frontier in Embodied AI Learning Universal Policies via Text-Guided Video Generation

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.703667Z

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 de8ea739-8432-4caa-85c4-0f2da5bca292 · outbound

This paper cites Video Language Planning.

World Action Models: The Next Frontier in Embodied AI Video Language Planning

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.714656Z

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 610ccdbc-e91b-4615-b336-d6e68066a720 · outbound

This paper cites Learning to Act from Actionless Videos through Dense Correspondences.

World Action Models: The Next Frontier in Embodied AI Learning to Act from Actionless Videos through Dense Correspondences

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.821723Z

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 c8055154-3b01-49ad-9700-3c6d301a2f61 · outbound

This paper cites RoboEnvision: A Long-Horizon Video Generation Model for Multi-Task Robot Manipulation.

World Action Models: The Next Frontier in Embodied AI RoboEnvision: A Long-Horizon Video Generation Model for Multi-Task Robot Manipulation

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.827249Z

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 36c4fb7f-0ca2-4fcb-bf0a-1fc6e99f0d71 · outbound

This paper cites Say , dream, and act: Learning video world models for instruction-driven robot manipulation.

World Action Models: The Next Frontier in Embodied AI Say , dream, and act: Learning video world models for instruction-driven robot manipulation

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.844505Z

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 d3614055-8e0c-401d-b59e-79d7e0f9619a · outbound

This paper cites Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations.

World Action Models: The Next Frontier in Embodied AI Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.882648Z

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 1e2f769e-830e-4f20-b70a-3cabf8312d80 · outbound

This paper cites mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs.

World Action Models: The Next Frontier in Embodied AI mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-15T10:41:00.438292Z

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 a2886d11-f120-4198-9b27-09d575610565 · outbound

This paper cites Video Generators are Robot Policies.

World Action Models: The Next Frontier in Embodied AI Video Generators are Robot Policies

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-15T21:43:37.585075Z

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 9fcbfffb-0e17-425a-b53e-e9dd41d9cdda · outbound

This paper cites S-vam: Shortcut video-action model by self-distilling geometric and semantic foresight.arXiv preprint arXiv:2603.16195.

World Action Models: The Next Frontier in Embodied AI S-vam: Shortcut video-action model by self-distilling geometric and semantic foresight.arXiv preprint arXiv:2603.16195

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.786542Z

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 91f3ceca-f450-40ce-a5e0-0e511b030861 · outbound

This paper cites Latent action pretraining from videos.

World Action Models: The Next Frontier in Embodied AI Latent action pretraining from videos

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T11:07:40.153426Z

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 cb42705f-bbb4-4825-b0c5-d0b1b3d39002 · outbound

This paper cites Cosmos policy: Fine-tuning video models for visuomotor control and planning.

World Action Models: The Next Frontier in Embodied AI Cosmos policy: Fine-tuning video models for visuomotor control and planning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T11:07:40.179123Z

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 3d0de9d8-147e-40c6-8c26-8fc9c4bb0cb5 · outbound

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

World Action Models: The Next Frontier in Embodied AI Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.800744Z

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 30d308a7-d253-408c-9216-3358357682af · outbound

This paper cites World action models are zero-shot policies.

World Action Models: The Next Frontier in Embodied AI World action models are zero-shot policies

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T11:07:40.160621Z

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 b3a1f224-543e-46e2-9260-47bc0728503b · outbound

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

World Action Models: The Next Frontier in Embodied AI World Action Models are Zero-shot Policies

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.734254Z

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 b353d6d8-859a-4a0e-a147-4088571df8fc · outbound

This paper cites Causal world modeling for robot control.

World Action Models: The Next Frontier in Embodied AI Causal world modeling for robot control

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T11:07:40.180966Z

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 328cd88c-ce3f-4939-a1c4-5a58b5619157 · outbound

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

World Action Models: The Next Frontier in Embodied AI Motus: A Unified Latent Action World Model

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:07:18.341097Z

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 1d26c770-c2b1-4aa1-a331-f4a053b4bac7 · outbound

This paper cites Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets.

World Action Models: The Next Frontier in Embodied AI Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-13T16:25:00.606134Z

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 776906c3-a569-4d81-bd73-e67635b3c252 · outbound

This paper cites Prediction with Action: Visual Policy Learning via Joint Denoising Process.

World Action Models: The Next Frontier in Embodied AI Prediction with Action: Visual Policy Learning via Joint Denoising Process

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T05:02:17.923754Z

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 d0f00b46-76a9-4147-b03e-6750e6dbdb98 · outbound

This paper cites Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation.

World Action Models: The Next Frontier in Embodied AI Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:07:18.254641Z

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 993b419c-8b00-403f-9ca9-22cb30aa54c0 · outbound

This paper cites iVideoGPT: Interactive VideoGPTs are Scalable World Models.

World Action Models: The Next Frontier in Embodied AI iVideoGPT: Interactive VideoGPTs are Scalable World Models

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.867757Z

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 17b37493-ab6f-45bb-9a25-610c2310a3f6 · outbound

This paper cites FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation.

World Action Models: The Next Frontier in Embodied AI FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.737197Z

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 565d9095-b877-451c-b5b9-b982329d6351 · outbound

This paper cites Enerverse: Envisioning embodied future space for robotics manipulation.

World Action Models: The Next Frontier in Embodied AI Enerverse: Envisioning embodied future space for robotics manipulation

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.960532Z

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 b1eec7be-e404-45cf-b546-79e829627749 · outbound

This paper cites Learning Latent Dynamics for Planning from Pixels.

World Action Models: The Next Frontier in Embodied AI Learning Latent Dynamics for Planning from Pixels

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.876732Z

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 5d97e352-3f56-42df-be04-923eff572587 · outbound

This paper cites TransDreamer: Reinforcement Learning with Transformer World Models.

World Action Models: The Next Frontier in Embodied AI TransDreamer: Reinforcement Learning with Transformer World Models

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:07:18.290142Z

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 00435132-6950-408a-ae71-89099b7dfd99 · outbound

This paper cites Revisiting Feature Prediction for Learning Visual Representations from Video.

World Action Models: The Next Frontier in Embodied AI Revisiting Feature Prediction for Learning Visual Representations from Video

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:07:18.219899Z

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 5a8a982c-f319-45cd-9bed-91da176b19c0 · outbound

This paper cites MoCoGAN: Decomposing Motion and Content for Video Generation.

World Action Models: The Next Frontier in Embodied AI MoCoGAN: Decomposing Motion and Content for Video Generation

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:07:18.287340Z

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 a5dc2cf1-1aa9-4b15-a745-2f12036fd56d · outbound

This paper cites U-Net: Convolutional Networks for Biomedical Image Segmentation.

World Action Models: The Next Frontier in Embodied AI U-Net: Convolutional Networks for Biomedical Image Segmentation

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:07:18.359422Z

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 d0fe472d-d9d8-4983-a7d8-9ba88e782339 · outbound

This paper cites Latte: Latent Diffusion Transformer for Video Generation.

World Action Models: The Next Frontier in Embodied AI Latte: Latent Diffusion Transformer for Video Generation

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-13T21:45:35.835056Z

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 ccf6f7fa-1893-4f7a-9d63-e8135801d2a3 · outbound

This paper cites Wan: Open and Advanced Large-Scale Video Generative Models.

World Action Models: The Next Frontier in Embodied AI Wan: Open and Advanced Large-Scale Video Generative Models

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:07:18.229081Z

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 6f5ae4a0-5dd1-4efa-b901-2653bd7a6322 · outbound

This paper cites an unresolved cited work.

World Action Models: The Next Frontier in Embodied AI Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-05-13T11:07:40.170575Z

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 8b8c7a37-866f-4098-aeb1-0d4e3f508a48 · outbound

This paper cites Structured World Models from Human Videos.

World Action Models: The Next Frontier in Embodied AI Structured World Models from Human Videos

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:07:18.263404Z

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 e331be21-3a8b-4ea5-beb9-6e393d6d4238 · outbound

This paper cites DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos.

World Action Models: The Next Frontier in Embodied AI DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-16T17:02:34.576842Z

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 e25e87e9-00d3-4c53-a04e-4c9b04561b93 · outbound

This paper cites RoboDreamer: Learning Compositional World Models for Robot Imagination.

World Action Models: The Next Frontier in Embodied AI RoboDreamer: Learning Compositional World Models for Robot Imagination

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-15T20:47:30.400020Z

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 a09438cd-c62c-42c2-b86e-b460a869c4f3 · outbound

This paper cites RoboScape: Physics-informed Embodied World Model.

World Action Models: The Next Frontier in Embodied AI RoboScape: Physics-informed Embodied World Model

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:07:18.367935Z

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 66c4bde1-1a00-4c81-8773-848201f6ac17 · outbound

This paper cites Ctrl-World: A Controllable Generative World Model for Robot Manipulation.

World Action Models: The Next Frontier in Embodied AI Ctrl-World: A Controllable Generative World Model for Robot Manipulation

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-16T01:14:10.607102Z

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 1d5134cf-cc1e-4bb8-acbf-ab187233f924 · outbound

This paper cites Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination.

World Action Models: The Next Frontier in Embodied AI Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.932798Z

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 c6855c92-9b62-4fc1-99c8-c80545848c40 · outbound

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

World Action Models: The Next Frontier in Embodied AI Dream to Control: Learning Behaviors by Latent Imagination

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.915130Z

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 adea8829-679e-4db2-b832-31a00708e585 · outbound

This paper cites Mastering Atari with Discrete World Models.

World Action Models: The Next Frontier in Embodied AI Mastering Atari with Discrete World Models

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-15T01:27:32.049853Z

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 e6f5a955-85fe-4593-819a-a4774fcb1cef · outbound

This paper cites Training Agents Inside of Scalable World Models.

World Action Models: The Next Frontier in Embodied AI Training Agents Inside of Scalable World Models

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-15T02:05:52.707385Z

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 f8ee2a58-5045-4d76-8852-7e07623ae707 · outbound

This paper cites RISE: Self-Improving Robot Policy with Compositional World Model.

World Action Models: The Next Frontier in Embodied AI RISE: Self-Improving Robot Policy with Compositional World Model

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.906235Z

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 2ad832da-dadc-45ba-9055-0509a7e1e6ef · outbound

This paper cites Mastering Diverse Domains through World Models.

World Action Models: The Next Frontier in Embodied AI Mastering Diverse Domains through World Models

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.917978Z

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 f1af7ded-96ed-4100-8f13-8aaa0de975a6 · outbound

This paper cites DayDreamer: World Models for Physical Robot Learning.

World Action Models: The Next Frontier in Embodied AI DayDreamer: World Models for Physical Robot Learning

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.963303Z

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 94eda5dc-5e1d-4375-b5d4-7d14f5e7616e · outbound

This paper cites World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training.

World Action Models: The Next Frontier in Embodied AI World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:07:18.222721Z

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 97a79258-a91e-4ebd-a601-213a9a370f71 · outbound

This paper cites Roboscape-r: Unified reward-observation world models for generalizable robotics training via rl.

World Action Models: The Next Frontier in Embodied AI Roboscape-r: Unified reward-observation world models for generalizable robotics training via rl

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.862465Z

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 4d42406f-a2cb-4ebd-a289-907edff72800 · outbound

This paper cites Wmpo: World model-based policy optimization for vision-language-action models.

World Action Models: The Next Frontier in Embodied AI Wmpo: World model-based policy optimization for vision-language-action models

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.859655Z

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 0abef4cf-05b5-4a07-8314-2d7e30300fef · outbound

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

World Action Models: The Next Frontier in Embodied AI WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-06-30T02:16:14.370216Z

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 851cd0d5-d996-4ba3-a003-ef58b7597f03 · outbound

This paper cites Vla-rft: Vision- language-action reinforcement fine-tuning with veri- fied rewards in world simulators.

World Action Models: The Next Frontier in Embodied AI Vla-rft: Vision- language-action reinforcement fine-tuning with veri- fied rewards in world simulators

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.847252Z

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 47cbfc8c-8de6-4ade-9913-f1c506e42232 · outbound

This paper cites Reinforcement world model learning for llm-based agents.

World Action Models: The Next Frontier in Embodied AI Reinforcement world model learning for llm-based agents

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.836042Z

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 7aad0f5e-ab3d-4c67-99cc-6c4648a8532c · outbound

This paper cites MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulation.

World Action Models: The Next Frontier in Embodied AI MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulation

Reference 56

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T05:02:17.833390Z

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 c04f4f1c-4f33-4a88-a8d9-9d94c3569b05 · outbound

This paper cites informativeness.

World Action Models: The Next Frontier in Embodied AI informativeness

Reference 57

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T05:02:17.838675Z

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 a4ad90ce-3bbf-40a1-8382-affdbd20526e · outbound

This paper cites Offline robotic world model: Learning robotic policies without a physics simulator.

World Action Models: The Next Frontier in Embodied AI Offline robotic world model: Learning robotic policies without a physics simulator

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.841387Z

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 1b55f211-529d-45db-b1b5-389824b9b5ac · outbound

This paper cites World4rl: Diffusion world models for policy refinement with reinforcement learning for robotic manipulation.

World Action Models: The Next Frontier in Embodied AI World4rl: Diffusion world models for policy refinement with reinforcement learning for robotic manipulation

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.819092Z

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 b6e57756-56a3-4435-9c08-f82c8c751187 · outbound

This paper cites Video Prediction Models as Rewards for Reinforcement Learning.

World Action Models: The Next Frontier in Embodied AI Video Prediction Models as Rewards for Reinforcement Learning

Reference 60

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T05:02:17.824311Z

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 988a6273-2a14-47d3-b523-cd2880e64285 · outbound

This paper cites Robot learning from a physical world model.

World Action Models: The Next Frontier in Embodied AI Robot learning from a physical world model

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T11:07:40.167892Z

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 a54ca1bf-e11a-4eb3-8e0c-ac5ef1e2d43d · outbound

This paper cites Robot learning from a physical world model.

World Action Models: The Next Frontier in Embodied AI Robot learning from a physical world model

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.829936Z

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 307a31a0-61b3-4a57-9b24-ebac8ba00068 · outbound

This paper cites Diffusion Reward: Learning Rewards via Conditional Video Diffusion.

World Action Models: The Next Frontier in Embodied AI Diffusion Reward: Learning Rewards via Conditional Video Diffusion

Reference 63

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.879813Z

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 0b94c3f8-375b-427b-94e7-4c5fe62c5e09 · outbound

This paper cites Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning.

World Action Models: The Next Frontier in Embodied AI Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.803813Z

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 6d57fe95-c6fe-4ffb-8b89-ee8321c290a8 · outbound

This paper cites Evaluating gemini robotics policies in a veo world simulator.

World Action Models: The Next Frontier in Embodied AI Evaluating gemini robotics policies in a veo world simulator

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T11:07:40.148245Z

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 deeb3f6f-0368-412d-b275-5e3ff422e3b8 · outbound

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

World Action Models: The Next Frontier in Embodied AI Interactive world simulator for robot policy training and evaluation

Reference 66

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.789299Z

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 937d7e38-6f9e-42ff-b1c7-7f6257a68f18 · outbound

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

World Action Models: The Next Frontier in Embodied AI WorldEval: World Model as Real-World Robot Policies Evaluator

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.743642Z

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 246201ff-ef28-4e8c-8d9c-fa5d45d41623 · outbound

This paper cites WorldGym: World Model as An Environment for Policy Evaluation.

World Action Models: The Next Frontier in Embodied AI WorldGym: World Model as An Environment for Policy Evaluation

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.740647Z

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 d31bfd62-94b7-4d2f-b897-ada82efd8711 · outbound

This paper cites dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model.

World Action Models: The Next Frontier in Embodied AI dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model

Reference 69

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.792190Z

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 c5043df6-5097-4cf3-be5b-6efce5f0ff7b · outbound

This paper cites This&That: Language-Gesture Controlled Video Generation for Robot Planning.

World Action Models: The Next Frontier in Embodied AI This&That: Language-Gesture Controlled Video Generation for Robot Planning

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.849904Z

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 bc8a2ebc-6638-4f64-ab11-80ee74ab9da2 · outbound

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

World Action Models: The Next Frontier in Embodied AI TesserAct: Learning 4D Embodied World Models

Reference 72

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T05:07:18.333533Z

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 4db02212-d871-4227-b06a-bfd8fb580806 · outbound

This paper cites MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation.

World Action Models: The Next Frontier in Embodied AI MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation

Reference 73

Resolution: verified exact; arxiv_id, observed 2026-05-27T03:06:04.942822Z

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 f1b5ec9d-cefb-4681-ae82-0a3516090585 · outbound

This paper cites Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation.

World Action Models: The Next Frontier in Embodied AI Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-05-15T12:17:01.597427Z

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 59979659-fe26-45e0-844c-b083b47a8469 · outbound

This paper cites Flow as the Cross-Domain Manipulation Interface.

World Action Models: The Next Frontier in Embodied AI Flow as the Cross-Domain Manipulation Interface

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.795371Z

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 613e048a-c865-4353-bfb9-d5e1142a4783 · outbound

This paper cites 3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model.

World Action Models: The Next Frontier in Embodied AI 3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model

Reference 76

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T05:02:17.761346Z

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 47e2f658-b4e4-443d-b7e5-a7be2a28c8fe · outbound

This paper cites Novaflow: Zero-shot manipulation via ac- tionable flow from generated videos.arXiv preprint arXiv:2510.08568, 2025a.

World Action Models: The Next Frontier in Embodied AI Novaflow: Zero-shot manipulation via ac- tionable flow from generated videos.arXiv preprint arXiv:2510.08568, 2025a

Reference 77

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.806678Z

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 17f1d915-a873-4a02-a646-a34aeee93364 · outbound

This paper cites Dream2flow: Bridging video generation and open-world manipulation with 3d object flow.

World Action Models: The Next Frontier in Embodied AI Dream2flow: Bridging video generation and open-world manipulation with 3d object flow

Reference 78

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.777208Z

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 a7d0a91d-4bc0-4118-a456-d83e8cd36f80 · outbound

This paper cites Dreamitate: Real-World Visuomotor Policy Learning via Video Generation.

World Action Models: The Next Frontier in Embodied AI Dreamitate: Real-World Visuomotor Policy Learning via Video Generation

Reference 79

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.885588Z

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 7409d818-af44-4a44-933e-f903d2a1e229 · outbound

This paper cites Geometry-aware 4d video generation for robot manipulation.

World Action Models: The Next Frontier in Embodied AI Geometry-aware 4d video generation for robot manipulation

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T11:07:40.162409Z

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 c294bfe1-e0be-423d-bd24-8628b23127be · outbound

This paper cites Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations.

World Action Models: The Next Frontier in Embodied AI Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations

Reference 81

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.935498Z

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 91548258-88d8-48a0-9bf5-a2333b7944c4 · outbound

This paper cites Large Video Planner Enables Generalizable Robot Control.

World Action Models: The Next Frontier in Embodied AI Large Video Planner Enables Generalizable Robot Control

Reference 82

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T05:02:17.873711Z

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 89f72487-c324-4b7f-b9c6-0831fd6f8b5e · outbound

This paper cites Vidar: Embodied Video Diffusion Model for Generalist Manipulation.

World Action Models: The Next Frontier in Embodied AI Vidar: Embodied Video Diffusion Model for Generalist Manipulation

Reference 83

Resolution: verified exact; arxiv_id, observed 2026-05-16T09:54:28.431425Z

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 723ca83d-5dbd-421f-832d-699417f40e52 · outbound

This paper cites Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?.

World Action Models: The Next Frontier in Embodied AI Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?

Reference 84

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:07:18.316499Z

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 243e0eb2-d1f2-4541-8b35-6d1bc3c1ff45 · outbound

This paper cites ${\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities.

World Action Models: The Next Frontier in Embodied AI ${\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities

Reference 85

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.798098Z

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 2d241684-5fd6-4c57-b569-f24393618fac · outbound

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

World Action Models: The Next Frontier in Embodied AI VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis

Reference 86

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:07:18.321988Z

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 c7589c38-ec74-4858-8017-fa64635727ea · outbound

This paper cites VILP: Imitation Learning with Latent Video Planning.

World Action Models: The Next Frontier in Embodied AI VILP: Imitation Learning with Latent Video Planning

Reference 87

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:07:18.324656Z

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 c3907f18-af68-418b-a486-2993ae1fd429 · outbound

This paper cites ARDuP: Active Region Video Diffusion for Universal Policies.

World Action Models: The Next Frontier in Embodied AI ARDuP: Active Region Video Diffusion for Universal Policies

Reference 88

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T05:07:18.293263Z

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 6a4d4cb6-c989-4c79-93e0-faae96578580 · outbound

This paper cites villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models.

World Action Models: The Next Frontier in Embodied AI villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

Reference 89

Resolution: verified exact; arxiv_id, observed 2026-05-15T21:52:03.356882Z

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 7fb26480-2d41-4207-b2ec-5b0bfe79f3b0 · outbound

This paper cites Omnivta: Visuo- tactile world modeling for contact-rich robotic manipulation.

World Action Models: The Next Frontier in Embodied AI Omnivta: Visuo- tactile world modeling for contact-rich robotic manipulation

Reference 90

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:17.809600Z

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 b0d1958a-bc8c-419e-8047-fa8e3695f17d · outbound

This paper cites Mask World Model: Predicting What Matters for Robust Robot Policy Learning.

World Action Models: The Next Frontier in Embodied AI Mask World Model: Predicting What Matters for Robust Robot Policy Learning

Reference 91

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.888560Z

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 e5761d60-d442-4b8e-be36-3d27940ad715 · outbound

This paper cites Unleashing large-scale video generative pre-training for visual robot manipulation.

World Action Models: The Next Frontier in Embodied AI Unleashing large-scale video generative pre-training for visual robot manipulation

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T11:07:40.142675Z

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 b8fbb6c5-04d2-4508-9905-6d4f13efa30c · outbound

This paper cites GR-MG: leveraging partially- annotated data via multi-modal goal-conditioned policy.

World Action Models: The Next Frontier in Embodied AI GR-MG: leveraging partially- annotated data via multi-modal goal-conditioned policy

Reference 93

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:16.724470Z

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 e94f52dd-197a-4f40-a927-bdf8b5818fa3 · outbound

This paper cites GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation.

World Action Models: The Next Frontier in Embodied AI GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation

Reference 94

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:02:17.926184Z

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 8258046e-84cf-4227-b789-79733f8645ec · outbound

This paper cites Freeman, Frédo Durand, Eli Shechtman, and Xun Huang.

World Action Models: The Next Frontier in Embodied AI Freeman, Frédo Durand, Eli Shechtman, and Xun Huang

Reference 95

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T05:02:16.741473Z

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 8502061e-72c6-4b8c-8ac1-66d099abb87d · outbound

This paper cites WorldVLA: Towards Autoregressive Action World Model.

World Action Models: The Next Frontier in Embodied AI WorldVLA: Towards Autoregressive Action World Model

Reference 96

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:07:18.190932Z

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 a3f0bdd1-8ee9-43b3-8a3b-5f6ee57f9cec · outbound

This paper cites RynnVLA-002: A Unified Vision-Language-Action and World Model.

World Action Models: The Next Frontier in Embodied AI RynnVLA-002: A Unified Vision-Language-Action and World Model

Reference 97

Resolution: verified exact; arxiv_id, observed 2026-06-02T02:03:36.254972Z

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 270183de-1f5b-4e89-bffc-bd6b31d6c789 · outbound

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

World Action Models: The Next Frontier in Embodied AI Vla-jepa: Enhancing vision-language-action model with latent world model

Reference 98

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:07:18.226290Z

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 0411d909-d780-41bc-a0e7-2fc78609032a · outbound

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

World Action Models: The Next Frontier in Embodied AI F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions

Reference 99

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:42:47.099823Z

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 13a4e612-4d84-414c-bfaa-7a655ee79e6a · outbound

This paper cites Videovla: Video generators can be generalizable robot manipulators.

World Action Models: The Next Frontier in Embodied AI Videovla: Video generators can be generalizable robot manipulators

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T11:07:40.156955Z

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 f405622d-9bcd-4727-9909-dcba3367f1c5 · outbound

This paper cites FLARE: Robot Learning with Implicit World Modeling.

World Action Models: The Next Frontier in Embodied AI FLARE: Robot Learning with Implicit World Modeling

Reference 101

Resolution: verified exact; arxiv_id, observed 2026-05-17T15:59:09.111136Z

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.

Pith citing papers

Observation 400664ee-09ab-4b59-8374-801b7dba9be1 · inbound

SANTS: A State-Adaptive Scheduler for World Action Models cites this paper.

SANTS: A State-Adaptive Scheduler for World Action Models World Action Models: The Next Frontier in Embodied AI

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:03:24.124667Z

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 904d1ce7-50c0-463e-9bf0-46594bc5e76a · inbound

SANTS: A State-Adaptive Scheduler for World Action Models cites this paper.

SANTS: A State-Adaptive Scheduler for World Action Models World Action Models: The Next Frontier in Embodied AI

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-15T11:04:29.593725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f45ad530-115d-4c99-ac89-84656a2c7c61 · inbound

Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision cites this paper.

Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision World Action Models: The Next Frontier in Embodied AI

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-30T15:44:48.249222Z

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 73838e77-2f03-46ef-a675-af443e7171d3 · inbound

ImagineUAV: Aerial Vision-Language Navigation via World-Action Modeling and Kinodynamic Planning cites this paper.

ImagineUAV: Aerial Vision-Language Navigation via World-Action Modeling and Kinodynamic Planning World Action Models: The Next Frontier in Embodied AI

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-01T21:16:14.900379Z

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 d8b74d70-ba96-4eea-8482-8d329008acef · inbound

See, Infer, Intervene: Proactive World Modeling for Goal-Oriented Social Intelligence cites this paper.

See, Infer, Intervene: Proactive World Modeling for Goal-Oriented Social Intelligence World Action Models: The Next Frontier in Embodied AI

Reference 35

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T02:56:29.731332Z

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 e3586fe9-adde-43e8-a8ce-42a9debc05ab · inbound

Dreaming when Necessary: Advancing World Action Models with Adaptive Multi-Modal Reasoning cites this paper.

Dreaming when Necessary: Advancing World Action Models with Adaptive Multi-Modal Reasoning World Action Models: The Next Frontier in Embodied AI

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-02T17:37:14.351039Z

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 04c0af78-6ba4-44aa-a7b4-65ba0499e32d · inbound

$\omega$-EVA: Envision, Verify, and Act with Latent Interactive World Models cites this paper.

$\omega$-EVA: Envision, Verify, and Act with Latent Interactive World Models World Action Models: The Next Frontier in Embodied AI

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-07-03T02:07:33.770339Z

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 bc46d8c6-5282-4191-8c7f-4b838f72692c · inbound

Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination cites this paper.

Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination World Action Models: The Next Frontier in Embodied AI

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-03T02:17:34.436601Z

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 569e4173-b8c7-485f-aea6-2f3fa94fca9f · inbound

VICX: Generalizable Robot Manipulation via Video Generation and In-Context Operator Network cites this paper.

VICX: Generalizable Robot Manipulation via Video Generation and In-Context Operator Network World Action Models: The Next Frontier in Embodied AI

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-03T11:28:04.543397Z

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 f9610b29-7b6e-45a3-8287-2f5d5575e4cb · inbound

RepWAM: World Action Modeling with Representation Visual-Action Tokenizers cites this paper.

RepWAM: World Action Modeling with Representation Visual-Action Tokenizers World Action Models: The Next Frontier in Embodied AI

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-07-03T14:58:33.428954Z

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 a760c1ca-7a94-494b-8d61-50e26c19ab08 · inbound

World Value Models for Robotic Manipulation cites this paper.

World Value Models for Robotic Manipulation World Action Models: The Next Frontier in Embodied AI

Reference 65

Resolution: verified exact; local_arxiv, observed 2026-07-04T17:40:00.357437Z

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 5d7d499b-0011-4a4c-bbf1-7009c3ccc06e · inbound

In-Context World Modeling for Robotic Control cites this paper.

In-Context World Modeling for Robotic Control World Action Models: The Next Frontier in Embodied AI

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-04T21:00:09.554296Z

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 62367699-e2e5-4225-bd80-3986750b2959 · inbound

In-Context World Modeling for Robotic Control cites this paper.

In-Context World Modeling for Robotic Control World Action Models: The Next Frontier in Embodied AI

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-04T13:29:51.597813Z

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 a8472bcc-b993-47b1-8e27-10ebe7917b59 · inbound

In-Context World Modeling for Robotic Control cites this paper.

In-Context World Modeling for Robotic Control World Action Models: The Next Frontier in Embodied AI

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-12T12:05:57.682386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 729382a0-a60b-4844-8820-9770810b51fd · inbound

Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy cites this paper.

Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy World Action Models: The Next Frontier in Embodied AI

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-04T13:49:52.049957Z

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 d5d3c1c8-dbc2-4f80-863b-4db211eb1306 · inbound

Bridge-WA: Predicting Where and How the World Changes for Robotic Action cites this paper.

Bridge-WA: Predicting Where and How the World Changes for Robotic Action World Action Models: The Next Frontier in Embodied AI

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-07-03T11:38:04.542408Z

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 3c360508-882c-4fa8-8d1d-f6eaa5232f30 · inbound

Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots cites this paper.

Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots World Action Models: The Next Frontier in Embodied AI

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-03T10:37:56.098280Z

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 64ad0141-8c17-4c08-b7de-805a0eec352f · inbound

Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots cites this paper.

Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots World Action Models: The Next Frontier in Embodied AI

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-12T08:00:25.815355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28edc7eb-59f2-4f6d-86ce-2c8ef028a9f5 · inbound

VT-WAM: Visual-Tactile World Action Model for Contact-Rich Manipulation cites this paper.

VT-WAM: Visual-Tactile World Action Model for Contact-Rich Manipulation World Action Models: The Next Frontier in Embodied AI

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-07-03T10:37:56.178544Z

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 1899715e-cec5-4a35-9f81-d73a61e7bb05 · inbound

HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models cites this paper.

HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models World Action Models: The Next Frontier in Embodied AI

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-11T20:32:22.412216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abd1aa0b-8d13-4672-8172-523dcbdbb894 · inbound

Learning 4D Geometric Priors for Inference-Efficient World Action Models cites this paper.

Learning 4D Geometric Priors for Inference-Efficient World Action Models World Action Models: The Next Frontier in Embodied AI

Reference 75

Resolution: unresolved; no resolver link, observed 2026-07-11T14:23:57.266710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b303fb6-33c8-4ede-97ee-8203a2558d40 · inbound

AgenticFocus: Object-Preserving Mixed Reality Synthesis from Human FPV Video for Dexterous Humanoid Learning cites this paper.

AgenticFocus: Object-Preserving Mixed Reality Synthesis from Human FPV Video for Dexterous Humanoid Learning World Action Models: The Next Frontier in Embodied AI

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-13T06:16:27.546219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03d8e224-f0d7-4545-ba45-66109aef3b19 · inbound

AgenticFocus: Object-Preserving Mixed Reality Synthesis from Human FPV Video for Dexterous Humanoid Learning cites this paper.

AgenticFocus: Object-Preserving Mixed Reality Synthesis from Human FPV Video for Dexterous Humanoid Learning World Action Models: The Next Frontier in Embodied AI

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-14T15:28:10.101325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e046b83-e828-42f6-bf65-af73e8b73fac · inbound

Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control cites this paper.

Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control World Action Models: The Next Frontier in Embodied AI

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T00:42:34.712744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 592bd980-22c4-4a8e-b128-40f099c00b37 · inbound

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

LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments World Action Models: The Next Frontier in Embodied AI

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T23:29:08.872529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b84cfe12-6297-4efb-90e8-a64bd191a598 · inbound

PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud cites this paper.

PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud World Action Models: The Next Frontier in Embodied AI

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-05T14:52:35.528275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aafc3a52-a6d2-4bba-9431-6e76bc48dc4c · inbound

LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation cites this paper.

LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation World Action Models: The Next Frontier in Embodied AI

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T14:32:56.118567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f1d3227-bae7-4d6c-b8bd-5d27974d90ee · inbound

ETA: A New Agentic Paradigm for Embodied Tasks cites this paper.

ETA: A New Agentic Paradigm for Embodied Tasks World Action Models: The Next Frontier in Embodied AI

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T05:44:43.007949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.