Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility | Paper Citation Record

Observation e6ffaf9f-8ac9-46b1-8c61-13950a9429bb · outbound

This paper cites AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.645004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa6e671d-48c4-424d-b9ef-99a26f5f6052 · outbound

This paper cites an unresolved cited work.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.921961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 941a8852-f148-495e-adc1-2f315c994527 · outbound

This paper cites an unresolved cited work.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.898209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 837d8e08-1a9c-4bf5-a8de-6d29292c0cfb · outbound

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

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.661378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b14a6376-96c4-44c2-b5f1-eea0a32f76c1 · outbound

This paper cites Modality Forcing for Scalable Spatial Generation.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Modality Forcing for Scalable Spatial Generation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.681746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04bc6012-f868-4191-9ebf-794c9447d678 · outbound

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

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility MolmoAct2: Action Reasoning Models for Real-world Deployment

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.686671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f98e3bb7-a645-42b2-b603-d9bdacb4697c · outbound

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

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.691552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d80cb87-d499-4666-b72d-db9259765fa6 · outbound

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

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.696157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac27cb13-5f7e-4504-99e1-d4c8ea415a58 · outbound

This paper cites Vla-0: Building state- of-the-art vlas with zero modification.arXiv preprint arXiv:2510.13054,.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Vla-0: Building state- of-the-art vlas with zero modification.arXiv preprint arXiv:2510.13054,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.700893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66095e97-adb6-498c-a002-e7d3a399134c · outbound

This paper cites LTX-Video: Realtime Video Latent Diffusion.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility LTX-Video: Realtime Video Latent Diffusion

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.705411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2de3af5-f846-4d7b-afc0-ee8a34e5ca54 · outbound

This paper cites Mastering Atari with Discrete World Models.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Mastering Atari with Discrete World Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.710095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0d4a030-e5de-4585-9353-5a9144a337b7 · outbound

This paper cites ParticleFormer: A 3D Point Cloud World Model for Multi-Object, Multi-Material Robotic Manipulation.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility ParticleFormer: A 3D Point Cloud World Model for Multi-Object, Multi-Material Robotic Manipulation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.724453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d27ad74-41a3-4d22-870a-0e9d0ae19a11 · outbound

This paper cites Adapower: Specializing world foundation models for predictive manipulation.arXiv preprint arXiv:2512.03538, 2025b.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Adapower: Specializing world foundation models for predictive manipulation.arXiv preprint arXiv:2512.03538, 2025b

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.729270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed19a4c5-d87a-47d3-98df-03f809c8a075 · outbound

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

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.733682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0d9be3e-e517-42b9-b69a-a9d4445a7ed3 · outbound

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

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility DreamGen: Unlocking Generalization in Robot Learning through Video World Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.738395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 342fa441-a043-4d1a-9b77-c06ec2733e69 · outbound

This paper cites RLDX-1 Technical Report.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility RLDX-1 Technical Report

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.743357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d712c706-595d-462e-ac52-2bb3426db746 · outbound

This paper cites Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.748235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94492e8e-3013-431d-b13d-d35df057069a · outbound

This paper cites Auto-Encoding Variational Bayes.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Auto-Encoding Variational Bayes

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.752767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7df9d1d1-ce7a-457a-bd1f-caea9c476833 · outbound

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

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility MolmoAct: Action Reasoning Models that can Reason in Space

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.762461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 353a4aaa-54d3-40d1-b42c-ec3733549fe5 · outbound

This paper cites Causal World Modeling for Robot Control.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Causal World Modeling for Robot Control

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.767248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eea0bed-8ada-439a-9958-1beddc12302f · outbound

This paper cites Back to Basics: Let Denoising Generative Models Denoise.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Back to Basics: Let Denoising Generative Models Denoise

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.772111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ce11f2f-08a3-4cba-acb5-7b3961752735 · outbound

This paper cites Integrating LMM Planners and 3D Skill Policies for Generalizable Manipulation.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Integrating LMM Planners and 3D Skill Policies for Generalizable Manipulation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.776955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e13117c5-8edf-482e-8126-ef13059b28f8 · outbound

This paper cites LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.781788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6d14147-13d2-46c1-84a2-e752dddda723 · outbound

This paper cites LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.786479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61f81a59-b4c3-43c2-b192-b364950dfc67 · outbound

This paper cites GR00T N1: An Open Foundation Model for Generalist Humanoid Robots.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility GR00T N1: An Open Foundation Model for Generalist Humanoid Robots

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.791321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61647c44-9396-4099-9bf2-3267108eacad · outbound

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

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Cosmos 3: Omnimodal World Models for Physical AI

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.796034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b62893a1-ef18-4be0-8ec0-ef203b183e10 · outbound

This paper cites Peebles and Saining Xie.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Peebles and Saining Xie

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.800839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78ec6ea1-1a31-47ce-b811-71ec0fa518ca · outbound

This paper cites SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.805779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f600282b-7a0f-4d0f-ba85-e6fbafdda907 · outbound

This paper cites U-net: Convolutional networks for biomed- ical image segmentation.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility U-net: Convolutional networks for biomed- ical image segmentation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.810496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aff1e29e-98d7-4f88-a3d9-4ffe6619eb69 · outbound

This paper cites RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.815491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56b17a77-c7d2-4eb0-b7af-b983129d93df · outbound

This paper cites Featured Certification.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Featured Certification

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.820313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dad40d7-e50f-4a7b-9aae-f4d28500b00a · outbound

This paper cites Interactive Post-Training for Vision-Language-Action Models.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Interactive Post-Training for Vision-Language-Action Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.824804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97e82b35-a335-46d9-9e2f-c494940eeaf5 · outbound

This paper cites Gemini Robotics: Bringing AI into the Physical World.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Gemini Robotics: Bringing AI into the Physical World

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.829496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61028ee3-0e29-427a-87a7-deba321b2d6b · outbound

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

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Wan: Open and Advanced Large-Scale Video Generative Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.834534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ec8d2a9-6288-47e3-848e-4d223fd8fc6a · outbound

This paper cites Hongtao Wu, Ya Jing, Chilam Cheang, Guangzeng Chen, Jiafeng Xu, Xinghang Li, Minghuan Liu, Hang Li, and Tao Kong.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Hongtao Wu, Ya Jing, Chilam Cheang, Guangzeng Chen, Jiafeng Xu, Xinghang Li, Minghuan Liu, Hang Li, and Tao Kong

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.839383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 553899b5-2105-499a-9572-6a57a3fa57aa · outbound

This paper cites From Foundation to Application: Improving VLA Models in Practice.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility From Foundation to Application: Improving VLA Models in Practice

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.845505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e5a16e2-cd19-4b1d-b42f-4cc6f47887e9 · outbound

This paper cites Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.855037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02024d55-933e-4d1d-bd8d-a657e52c5a53 · outbound

This paper cites Lap: Language-action pre-training enables zero-shot cross- embodiment transfer.arXiv preprint arXiv:2602.10556,.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Lap: Language-action pre-training enables zero-shot cross- embodiment transfer.arXiv preprint arXiv:2602.10556,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.859485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab61b01b-3d4e-49bf-ad36-3df8fd7f856f · outbound

This paper cites Native Video-Action Pretraining for Generalizable Robot Control.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Native Video-Action Pretraining for Generalizable Robot Control

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.863870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13d91bdb-67d1-4e6d-8609-4a43bf33cfc7 · outbound

This paper cites 3D-VLA: A 3D Vision-Language-Action Generative World Model.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility 3D-VLA: A 3D Vision-Language-Action Generative World Model

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.868471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ff57021-61c8-42ac-80fd-3a1a8bccca1f · outbound

This paper cites X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.873298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92998946-cab0-451a-967d-98a4c6a7d221 · outbound

This paper cites DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.878245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aa744b2-8067-4262-9ca2-eb46caa54351 · outbound

This paper cites robosuite: A Modular Simulation Framework and Benchmark for Robot Learning.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.883709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ce5a35e-4ea9-4953-aa58-2870b46bd71d · outbound

This paper cites (1)) when the data dimension is large, and we also found this to empirically be the case for our setting.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility (1)) when the data dimension is large, and we also found this to empirically be the case for our setting

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:17:56.066724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c3a60c7e-9558-4610-ad49-0fd49ffc64a9 · outbound

This paper cites rows marked† in Table 7 are our own evaluations of the released checkpoints, following Fei et al.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility rows marked† in Table 7 are our own evaluations of the released checkpoints, following Fei et al

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:17:56.041294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1cf2b8bf-30fb-416b-bb13-f4497e684ce6 · outbound

This paper cites C) or the five tasks of Sec.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility C) or the five tasks of Sec

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.907776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0e5585a-2419-4b02-9d18-b9b68040945f · outbound

This paper cites ManiFlow (Yan et al., 2025b) takes the three RGB views at the same resolution plus the three depth maps, back-projected to pointmaps on device by its own encoder.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility ManiFlow (Yan et al., 2025b) takes the three RGB views at the same resolution plus the three depth maps, back-projected to pointmaps on device by its own encoder

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.912479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8b6a959-7502-4659-a59f-8854fbb6ef4c · outbound

This paper cites This experiment uses the50random-scene RoboTwin tasks, not the five-task recipe of the ablations above.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility This experiment uses the50random-scene RoboTwin tasks, not the five-task recipe of the ablations above

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:17:56.005257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9b2bab86-45a8-4313-a6a1-74a2d3e7f0fb · outbound

This paper cites an unresolved cited work.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Unresolved cited work

Reference 59

Resolution: malformed identifier; no resolver link, observed 2026-08-15T14:17:54.926509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c8b4c3a-6cde-4365-a747-bc49a2f8736d · outbound

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

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility HunyuanVideo: A Systematic Framework For Large Video Generative Models

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.757672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d48b2278-5ea5-47a7-8a46-439e8dd5366b · outbound

This paper cites The rearrangement is exactly invertible, so no feature content is lost; the model simply predicts each2×2neighborhood jointly within one token instead of across four.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility The rearrangement is exactly invertible, so no feature content is lost; the model simply predicts each2×2neighborhood jointly within one token instead of across four

Reference 2016

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:17:56.082146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bfe40f54-2b88-4a36-8ac7-e45f116c2749 · outbound

This paper cites doi: 10.18653/v1/N19-1423.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility doi: 10.18653/v1/N19-1423

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.676437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d43aa294-6c43-471b-b68c-6d9b80542e3b · outbound

This paper cites Mastering Diverse Domains through World Models.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Mastering Diverse Domains through World Models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.715087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 094d9598-d4dd-4d28-87ab-5bde64791b5c · outbound

This paper cites Matthew M.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Matthew M

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.719758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0744f5b5-5a7b-4b7f-aeec-cbcca1d9ba82 · outbound

This paper cites BERT: Pre-training of deep bidirectional transformers for language understanding.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility BERT: Pre-training of deep bidirectional transformers for language understanding

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.671558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dec31f4-9e4b-4cfc-9c8f-eb0af8e6e871 · outbound

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

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.666424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe9b40ef-6686-4cec-8aa1-dfe9fcede75d · outbound

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

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.656283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62b807a6-9ba4-4c41-bc10-2b7939d5e669 · outbound

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

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Motus: A Unified Latent Action World Model

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.651115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c635e78d-9294-4cbc-a9f5-b95cd02a762f · outbound

This paper cites Ge Yan, Jiyue Zhu, Yuquan Deng, Shiqi Yang, Ri-Zhao Qiu, Xuxin Cheng, Marius Memmel, Ranjay Krishna, Ankit Goyal, Xiaolong Wang, and Dieter Fox.

Flex-$\pi$: A Multi-Stream World-Action Model with Compute Flexibility Ge Yan, Jiyue Zhu, Yuquan Deng, Shiqi Yang, Ri-Zhao Qiu, Xuxin Cheng, Marius Memmel, Ranjay Krishna, Ankit Goyal, Xiaolong Wang, and Dieter Fox

Reference 9471

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:54.850417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers