ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow | Paper Citation Record

Observation 0cc3fdef-8df9-43dd-8036-3494ac4b319b · outbound

This paper cites Cosmos World Foundation Model Platform for Physical AI.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Cosmos World Foundation Model Platform for Physical AI

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.174832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2daa5e05-2e46-455b-b654-01b37e84aa2d · outbound

This paper cites Alemi, Ian Fischer, Joshua V.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Alemi, Ian Fischer, Joshua V

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.214748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50c5c747-829f-459e-afaf-d0249fe99f0a · outbound

This paper cites Diffusion for world modeling: Visual details matter in atari.NeurIPS,.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Diffusion for world modeling: Visual details matter in atari.NeurIPS,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.264815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95551ff5-9100-4a3d-a16c-3d6d5f9e35f9 · outbound

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

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.304749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a07afd64-f1a5-4664-b436-ec2e4df0a870 · outbound

This paper cites Video generation models as world simulators.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Video generation models as world simulators

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.344750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 895a2a40-c650-4975-9a1d-338dafd4e6f2 · outbound

This paper cites Genie: Generative interactive environments.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Genie: Generative interactive environments

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.394749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 921e214d-68bb-4b0a-adfb-80a4aafded6d · outbound

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

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow UniVLA: Learning to Act Anywhere with Task-centric Latent Actions

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.444748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b05301fe-6cf7-4ba0-9881-b3ed840bc7ac · outbound

This paper cites Unifying 9 precisely 3D-enhanced camera and human motion controls for video generation.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Unifying 9 precisely 3D-enhanced camera and human motion controls for video generation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.494747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e79f2140-3608-4fe3-ad27-5b5ce6e30a83 · outbound

This paper cites SkyReels-V2: Infinite-length Film Generative Model.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow SkyReels-V2: Infinite-length Film Generative Model

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.544741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eebf8b52-c392-45c3-a1ec-e1bd6647f5ad · outbound

This paper cites A simple framework for contrastive learning of visual representations.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow A simple framework for contrastive learning of visual representations

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.584747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58573bcf-2373-411b-884b-74b3d872dc1c · outbound

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

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.644737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e21d9a3-bb1e-4302-96d6-294f423697e5 · outbound

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

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.694744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d770cff0-6283-41d1-a248-f7da423f6238 · outbound

This paper cites Moto: Latent motion token as the bridging language for learning robot manipulation from videos.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Moto: Latent motion token as the bridging language for learning robot manipulation from videos

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.744743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78b40ba3-62ac-4488-9554-e59c27660042 · outbound

This paper cites Oasis: A universe in a transformer.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Oasis: A universe in a transformer

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.784743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0f8044a-cec1-47af-a8c9-f6c2b63d6bb6 · outbound

This paper cites Imitating latent policies from observation.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Imitating latent policies from observation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.824747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1981785-596a-4c46-a4d9-39b8067b59cc · outbound

This paper cites 3D-aware implicit motion control for view-adaptive human video gener- ation.arXiv preprint arXiv:2602.03796, 2026.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow 3D-aware implicit motion control for view-adaptive human video gener- ation.arXiv preprint arXiv:2602.03796, 2026

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.864743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84bb22fc-96aa-479e-863f-8368f939e21b · outbound

This paper cites Vista: A generalizable driving world model with high fidelity and versatile controllability.NeurIPS, 2024.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Vista: A generalizable driving world model with high fidelity and versatile controllability.NeurIPS, 2024

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.904990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 563af642-dccb-43ed-a031-911bca51205a · outbound

This paper cites AdaWorld: Learning adaptable world mod- els with latent actions.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow AdaWorld: Learning adaptable world mod- els with latent actions

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.944744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df9059cf-dc7b-4856-95f4-1f355f42e766 · outbound

This paper cites Infinite Worlds with Versatile Interactions.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Infinite Worlds with Versatile Interactions

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.994747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb78f706-167e-4ce2-ad41-30d5f8ee1484 · outbound

This paper cites Learning latent action world models in the wild.arXiv preprint arXiv:2601.05230, 2026.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Learning latent action world models in the wild.arXiv preprint arXiv:2601.05230, 2026

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.044742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5feff2b-b79a-4ecb-8b78-8fba41849b57 · outbound

This paper cites an unresolved cited work.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.094743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73b1e3b1-4027-4ea0-b37e-265520a250aa · outbound

This paper cites Rubenstein, Arash Mehrjou, Francesco Locatello, and Bernhard Sch¨olkopf.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Rubenstein, Arash Mehrjou, Francesco Locatello, and Bernhard Sch¨olkopf

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.144742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ba72ee7-6be7-4d19-abc6-da8ca5cd8ef6 · outbound

This paper cites Long-Context Autoregressive Video Modeling with Next-Frame Prediction.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Long-Context Autoregressive Video Modeling with Next-Frame Prediction

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.194744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ce3ba9a-d81e-4072-851d-a9ef803f328e · outbound

This paper cites World Models.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow World Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.244743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72725158-0425-4edf-9740-547d8922ea1a · outbound

This paper cites Mastering Diverse Domains through World Models.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Mastering Diverse Domains through World Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.294746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c8cbe4a-78dd-4770-a825-e8524144c0fb · outbound

This paper cites Matrix-game 2.0: An open-source real-time and streaming interactive world model.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Matrix-game 2.0: An open-source real-time and streaming interactive world model

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.344741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8af2c3d5-f526-4657-859a-2b5e30e2109d · outbound

This paper cites beta-V AE: Learning basic visual con- cepts with a constrained variational framework.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow beta-V AE: Learning basic visual con- cepts with a constrained variational framework

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.404741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e9efc1c-e99e-4aa8-9743-fe64528007c0 · outbound

This paper cites RELIC: Interactive video world model with long-horizon memory.arXiv preprint arXiv:2512.04040, 2025.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow RELIC: Interactive video world model with long-horizon memory.arXiv preprint arXiv:2512.04040, 2025

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.464744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cb12e9f-b891-47a9-9787-622a0e744be5 · outbound

This paper cites Approximation capabilities of multilayer feed- forward networks.Neural Networks, 4(2):251–257, 1991.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Approximation capabilities of multilayer feed- forward networks.Neural Networks, 4(2):251–257, 1991

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.505325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c62af3d-ae64-4402-8bd8-d6ef711749f3 · outbound

This paper cites Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.554745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1281d8f6-b67f-4f29-b990-7242d043ecdc · outbound

This paper cites DreamGen: Unlocking Generalization in Robot Learning through Video World Models.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow DreamGen: Unlocking Generalization in Robot Learning through Video World Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.604741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bb3bf1a-7a45-4fdc-aaef-54f4d41d3218 · outbound

This paper cites Olaf-World: Orienting Latent Actions for Video World Modeling.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Olaf-World: Orienting Latent Actions for Video World Modeling

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.654825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52553eb8-c1f5-4f2e-b376-4c63d57725ca · outbound

This paper cites Miradata: A large-scale video dataset with long durations and structured captions.NeurIPS, 2024.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Miradata: A large-scale video dataset with long durations and structured captions.NeurIPS, 2024

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.694742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d3eec29-3623-4dfb-8290-29809d2a3d3c · outbound

This paper cites Variational autoencoders and nonlinear ica: A unifying framework.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Variational autoencoders and nonlinear ica: A unifying framework

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.744749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11560339-4106-40e8-a708-3d019fba05ee · outbound

This paper cites UniSkill: Imitating human videos via cross-embodiment skill representations.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow UniSkill: Imitating human videos via cross-embodiment skill representations

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.786083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f723b869-1090-449f-811e-1fa79dc22363 · outbound

This paper cites HunyuanVideo: A Systematic Framework For Large Video Generative Models.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow HunyuanVideo: A Systematic Framework For Large Video Generative Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.834746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dee87a8f-0485-4974-84ec-4f57ddb90ea1 · outbound

This paper cites Generative video motion editing with 3D point tracks.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Generative video motion editing with 3D point tracks

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.884745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c78f43de-7002-4f13-ba4d-579a94f7c48e · outbound

This paper cites DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.924748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8f1255c-c39e-4f31-bee4-f89ec0c71300 · outbound

This paper cites Flow straight and fast: Learning to generate and transfer data with rectified flow.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Flow straight and fast: Learning to generate and transfer data with rectified flow

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:44.974743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f235777-698b-48ce-9f9c-12c5fdcdd347 · outbound

This paper cites Challenging common assumptions in the unsu- pervised learning of disentangled representations.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Challenging common assumptions in the unsu- pervised learning of disentangled representations

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.024740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d5bd6d7-fb2e-4f77-afbc-6978adeb8ae9 · outbound

This paper cites Yume-1.5: A text-controlled interactive world genera- tion model.arXiv preprint arXiv:2512.22096, 2025.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Yume-1.5: A text-controlled interactive world genera- tion model.arXiv preprint arXiv:2512.22096, 2025

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.064516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 396025ae-ef9d-456e-ac99-89ee1ff44062 · outbound

This paper cites Open X-Embodiment: Robotic learning datasets and RT-X models.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Open X-Embodiment: Robotic learning datasets and RT-X models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.094743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cd400f1-5b09-46ae-874c-f5bbae320e60 · outbound

This paper cites Genie 3: A new frontier for world models.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Genie 3: A new frontier for world models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.134742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 433409cf-c64c-44f8-97c3-431b1d2df5f9 · outbound

This paper cites Scalable diffusion models with transformers.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Scalable diffusion models with transformers

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.174741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2cb2b64-d458-49af-9166-5b348862d420 · outbound

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

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Learning transferable visual models from natural language supervision

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.224756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26238142-ea5e-4b8a-ba98-57ddc4d26a70 · outbound

This paper cites Derpanis, and Kostas Daniilidis.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Derpanis, and Kostas Daniilidis

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.254752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74846c46-a311-4b97-8284-98ea7498c0c5 · outbound

This paper cites MotionStream: Real-time video generation with interactive motion controls.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow MotionStream: Real-time video generation with interactive motion controls

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.294744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f1f199a-cdfe-495c-b80a-da90c962969b · outbound

This paper cites A benchmark for the evalua- tion of RGB-D SLAM systems.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow A benchmark for the evalua- tion of RGB-D SLAM systems

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.374742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a951e2c-3d88-426c-b6ca-3cce94645f98 · outbound

This paper cites WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.424739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e805b93b-f423-4ab2-af04-ff8a40dc69bd · outbound

This paper cites Hunyuan-GameCraft-2: Instruction- following interactive game world model.arXiv preprint arXiv:2511.23429, 2025.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Hunyuan-GameCraft-2: Instruction- following interactive game world model.arXiv preprint arXiv:2511.23429, 2025

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.474756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43fe0fda-04ea-4bdb-ba3d-2b01be8bc169 · outbound

This paper cites ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.514747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08b133a7-dbda-4fc1-baa8-067943f204a0 · outbound

This paper cites Advancing Open-source World Models.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Advancing Open-source World Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.554829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41f4eefd-9ff4-4fbf-8c48-830643bd144e · outbound

This paper cites Video- MAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training.NeurIPS, 2022.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Video- MAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training.NeurIPS, 2022

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.604747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3eb4b689-a80c-4e22-9a83-a7bb099515ed · outbound

This paper cites Self-supervised learning with data aug- mentations provably isolates content from style.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Self-supervised learning with data aug- mentations provably isolates content from style

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.664746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 639b3838-19b3-4918-b9d7-ab953f42bac8 · outbound

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

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Wan: Open and Advanced Large-Scale Video Generative Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.715044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d23549d-0703-4a4f-b721-8caf0d5ddee8 · outbound

This paper cites VGGT: Visual geometry grounded transformer.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow VGGT: Visual geometry grounded transformer

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.754740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ac87890-768a-42b8-b744-82c34b53f473 · outbound

This paper cites Co-Evolving Latent Action World Models.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Co-Evolving Latent Action World Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.775224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb38dd9d-7174-467d-8b43-d12ba49e8857 · outbound

This paper cites Connectionist nonparametric regression: Mul- tilayer feedforward networks can learn arbitrary mappings.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Connectionist nonparametric regression: Mul- tilayer feedforward networks can learn arbitrary mappings

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.819531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f4e422b-ff2c-42a9-a777-a78ebb36c969 · outbound

This paper cites WorldMem: Long- term consistent world simulation with memory.arXiv preprint arXiv:2504.12369, 2025.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow WorldMem: Long- term consistent world simulation with memory.arXiv preprint arXiv:2504.12369, 2025

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.864743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8baa9522-1109-4440-8095-57ac4bc1d5e1 · outbound

This paper cites CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.914747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd31a456-41b9-424a-a857-8308ed90a1c8 · outbound

This paper cites Latent Action Pretraining from Videos.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Latent Action Pretraining from Videos

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.954745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d774304a-a384-43a0-a20d-22c284e775bb · outbound

This paper cites MIND: Benchmarking memory con- sistency and action control in world models.arXiv preprint arXiv:2602.08025, 2026.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow MIND: Benchmarking memory con- sistency and action control in world models.arXiv preprint arXiv:2602.08025, 2026

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:45.994742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f5894cd-aaa3-462e-96aa-e09344300f3d · outbound

This paper cites GameFactory: Creating new games with gen- erative interactive videos.arXiv preprint arXiv:2501.08325,.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow GameFactory: Creating new games with gen- erative interactive videos.arXiv preprint arXiv:2501.08325,

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:46.034739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbc12a0c-5b67-4b8d-b0de-0d00444cf8cd · outbound

This paper cites The unreasonable effectiveness of deep features as a perceptual metric.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow The unreasonable effectiveness of deep features as a perceptual metric

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:46.084741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f83cb955-d2ab-4a4a-b43e-b1ea3f7b082e · outbound

This paper cites Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models

Reference 65

Resolution: malformed identifier; no resolver link, observed 2026-07-31T09:42:46.124953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers