Paper Citation Record · LEDGER

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

As of 5 August 2026, this Paper Citation Record lists 100 of 131 outbound references and 4 inbound Pith citation observations for arXiv:2607.07675.

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

pith.paper-citation-record.v1
2607.07675 v1

Coverage vector

measured 100 of 131 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-09T02:55:58.018234Z

measured 104 of 104 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 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T07:53:39.262642Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T04:16:48.701434Z

Reference resolution

100 of 131 outbound references displayed

verified exact42
verified fuzzy54
unresolved0
parse uncertain1
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 70853329-5a65-4852-a42a-03772111d8dd · outbound

This paper cites GPT-4 Technical Report.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence GPT-4 Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.225604Z

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 ad2ace2e-2a21-4fd2-b5d8-120e307a1492 · outbound

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

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Cosmos 3: Omnimodal World Models for Physical AI

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.157813Z

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 00c84fef-d6df-4237-8229-0a35e6d9ae50 · outbound

This paper cites Pytorch 2: Faster machine learning through dynamic python bytecode transformation and graph compilation.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Pytorch 2: Faster machine learning through dynamic python bytecode transformation and graph compilation

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.727547Z

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 96a0c4da-5074-4812-965a-8512c139310b · outbound

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

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.138662Z

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 790734dc-2f3f-40e6-9758-20a24e3e9b82 · outbound

This paper cites Qwen Technical Report.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Qwen Technical Report

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.345416Z

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 b2073d22-0f88-49c7-9e87-21da66fe9cdd · outbound

This paper cites Qwen3-VL Technical Report.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Qwen3-VL Technical Report

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.250167Z

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 81243553-b743-49d7-bb9a-3133304947e3 · outbound

This paper cites Lumiere: A space-time diffusion model for video generation.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Lumiere: A space-time diffusion model for video generation

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.764181Z

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 78e0aa2b-8e95-4a3e-af79-48401eafa4b4 · outbound

This paper cites DeepSeek LLM: Scaling Open-Source Language Models with Longtermism.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.314557Z

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 a2a0244b-024c-42ad-a3ed-ae2f800a8981 · outbound

This paper cites Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.206327Z

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 8f3ac1ac-3e91-4896-8cb6-3417118b3c05 · outbound

This paper cites Genie: Generative interactive environments.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Genie: Generative interactive environments

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.690954Z

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 95ef248b-fb5e-48f7-91f7-c950704d2ed8 · outbound

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

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.311053Z

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 d4c12d5c-89ba-4ff0-a00e-4c9cee1c9fce · outbound

This paper cites Longcat-video technical report.arXiv preprint arXiv:2510.22200.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Longcat-video technical report.arXiv preprint arXiv:2510.22200

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-09T03:05:55.255582Z

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 b94d3e9f-2e63-40d2-827b-f1cfcb88fb3b · outbound

This paper cites Pixart- alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Pixart- alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.869506Z

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 31900569-fe83-41c8-9184-883a84f9f380 · outbound

This paper cites Training Deep Nets with Sublinear Memory Cost.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Training Deep Nets with Sublinear Memory Cost

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.263611Z

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 3a7e8a4e-fd38-4800-9a60-48a79854cdf1 · outbound

This paper cites Realdpo: Real or not real, that is the preference.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Realdpo: Real or not real, that is the preference

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-07-09T03:05:55.255294Z

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 3d6dec75-acb6-4329-bfd9-ab782929c6f7 · outbound

This paper cites Local all-pair correspondence for point tracking.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Local all-pair correspondence for point tracking

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.871387Z

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 39e2ad2d-15b6-4305-b0b0-c84e6e515996 · outbound

This paper cites Palm: Scaling language modeling with pathways.Journal of machine learning research, 24(240):1–113.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Palm: Scaling language modeling with pathways.Journal of machine learning research, 24(240):1–113

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.859303Z

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 b7ae041d-9c39-407a-a9fe-696665c95d96 · outbound

This paper cites Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.854259Z

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 2cff44b4-ed21-4aaa-8474-9e300a5d59af · outbound

This paper cites Fu, Stefano Ermon, Atri Rudra, and Christopher Ré.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Fu, Stefano Ermon, Atri Rudra, and Christopher Ré

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.857277Z

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 361bc574-79af-4a30-a5ca-63a06608670f · outbound

This paper cites Deepep: An efficient expert-parallel communication library.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Deepep: An efficient expert-parallel communication library

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.861339Z

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 84b6211c-a79b-4471-a909-5d5e15156e8e · outbound

This paper cites an unresolved cited work.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Unresolved cited work

Reference 21

Resolution: parse uncertain; raw_fallback, observed 2026-07-09T03:05:55.873149Z

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 3f10346e-3d51-4593-a139-84fc97169474 · outbound

This paper cites Scaling vision transformers to 22 billion parameters.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Scaling vision transformers to 22 billion parameters

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.876791Z

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 ff20bb95-561d-4a7e-8693-9672bdf59099 · outbound

This paper cites Rethinking video generation model for the embodied world.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Rethinking video generation model for the embodied world

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.849007Z

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 751852de-e464-4e8b-ac62-1b7b76841d70 · outbound

This paper cites Structure and content- guided video synthesis with diffusion models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Structure and content- guided video synthesis with diffusion models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.839376Z

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 0b9319d0-9ca9-4227-8d00-6f52d6408626 · outbound

This paper cites Scaling rectified flow transformers for high-resolution image synthesis.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Scaling rectified flow transformers for high-resolution image synthesis

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.836466Z

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 24c48c8d-ee24-4d31-9fe7-7aee347baa19 · outbound

This paper cites Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.Journal of Machine Learning Research, 23(120):1–39.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.Journal of Machine Learning Research, 23(120):1–39

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.836894Z

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 e55f2f81-05ef-4fe7-8e12-5e194e8ba58e · outbound

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

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.287932Z

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 8d650eef-2cf5-4fd0-812c-1f61edeaa5a8 · outbound

This paper cites The pulse of motion: Measuring physical frame rate from visual dynamics.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence The pulse of motion: Measuring physical frame rate from visual dynamics

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-07-09T03:05:55.274549Z

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 9fb154c2-6d77-4b74-b654-2aa890816496 · outbound

This paper cites Vlaw: Iterative co-improvement of vision-language-action policy and world model.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Vlaw: Iterative co-improvement of vision-language-action policy and world model

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-07-09T03:05:55.348812Z

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 0bdb0a86-22fd-478f-96a3-5836865a55e5 · outbound

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

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Ctrl-World: A Controllable Generative World Model for Robot Manipulation

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.295756Z

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 5acb3f5d-73af-468a-af59-ce45d6b02848 · outbound

This paper cites OmniAID: Decoupling Semantics and Artifacts for Universal AI-Generated Image Detection in the Wild.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence OmniAID: Decoupling Semantics and Artifacts for Universal AI-Generated Image Detection in the Wild

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.361324Z

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 41247c9b-e748-4939-9afe-8a5c203df4ef · outbound

This paper cites Animatediff: Animate your personalized text-to-image diffusion models without specific tuning.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Animatediff: Animate your personalized text-to-image diffusion models without specific tuning

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.807674Z

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 b4dbe36b-8ed4-4402-bbd1-d37a5fccfdce · outbound

This paper cites Photorealistic video generation with diffusion models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Photorealistic video generation with diffusion models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.804135Z

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 75f559d0-8341-45aa-a9a8-0e1b63c88c6a · outbound

This paper cites Generating an image from 1,000 words: Enhancing text-to-image with structured captions.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Generating an image from 1,000 words: Enhancing text-to-image with structured captions

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-07-09T03:05:55.270798Z

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 81e1d7e4-80b8-425c-88b0-5c90c330cae9 · outbound

This paper cites Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.295529Z

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 88fd76ff-7fe0-4edb-839d-93ac2586b840 · outbound

This paper cites TempFlow-GRPO: When Timing Matters for GRPO in Flow Models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence TempFlow-GRPO: When Timing Matters for GRPO in Flow Models

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.314045Z

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 bc549c17-ce48-4bf8-b2aa-111d831738f1 · outbound

This paper cites Imagen Video: High Definition Video Generation with Diffusion Models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Imagen Video: High Definition Video Generation with Diffusion Models

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.336407Z

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 689ba7c5-0767-467f-a07d-7ea3db82e036 · outbound

This paper cites Video diffusion models.Advances in neural information processing systems, 35:8633–8646.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Video diffusion models.Advances in neural information processing systems, 35:8633–8646

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.831622Z

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 57e26a9b-e1f4-4288-9a4f-621ca83404ab · outbound

This paper cites Rae, Oriol Vinyals, and Laurent Sifre.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Rae, Oriol Vinyals, and Laurent Sifre

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.851486Z

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 9dd81e01-b8af-4197-81d7-3f8557cb4add · outbound

This paper cites Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.844301Z

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 56cc5ead-2d39-44be-9093-e4e9708f1749 · outbound

This paper cites OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.340810Z

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 11127d1f-bc22-4b80-9969-5c438155834d · outbound

This paper cites Tutel: Adaptive mixture-of-experts at scale.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Tutel: Adaptive mixture-of-experts at scale

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.880891Z

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 9f6d8b17-da7d-412c-80d6-a3ab8ef9d57a · outbound

This paper cites Jacobs, Michael I.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Jacobs, Michael I

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.784513Z

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 2cbc8996-b7ae-432a-acea-528bc3fff068 · outbound

This paper cites DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.170422Z

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 4fc0cfcb-86c5-456e-805f-1171b3c1e9a9 · outbound

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

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.347531Z

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 0ce3b01e-01ee-406c-8090-fcf3a2469eac · outbound

This paper cites Hierarchical mixtures of experts and the em algorithm.Neural computation, 6(2):181– 214, 1994.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Hierarchical mixtures of experts and the em algorithm.Neural computation, 6(2):181– 214, 1994

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.756750Z

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 92a09cda-2931-4fa5-9a7e-aaa0f977994c · outbound

This paper cites Scaling Laws for Neural Language Models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Scaling Laws for Neural Language Models

Reference 47

Resolution: metadata mismatch; local_arxiv, observed 2026-07-09T03:05:55.200980Z

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 394d93db-e316-430d-b94a-dc8a9f3e1955 · outbound

This paper cites Pick-a-pic: An open dataset of user preferences for text-to-image generation.Advances in neural information processing systems, 36:36652–36663.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Pick-a-pic: An open dataset of user preferences for text-to-image generation.Advances in neural information processing systems, 36:36652–36663

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.761087Z

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 fb7231a6-0d13-4315-b6a0-535134fd160d · outbound

This paper cites Reducing activation recomputation in large transformer models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Reducing activation recomputation in large transformer models

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.775761Z

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 31adb489-bf50-4f65-b85c-c432ba8c3717 · outbound

This paper cites Efficient Sequence Packing without Cross-contamination: Accelerating Large Language Models without Impacting Performance.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Efficient Sequence Packing without Cross-contamination: Accelerating Large Language Models without Impacting Performance

Reference 50

Resolution: metadata mismatch; local_arxiv, observed 2026-07-09T03:05:55.225351Z

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 6a38081c-64f9-42e9-939b-50f0f509036c · outbound

This paper cites Gshard: Scaling giant models with conditional computation and automatic sharding.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Gshard: Scaling giant models with conditional computation and automatic sharding

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.791386Z

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 eeef1473-3eaf-4837-88a0-1ef8999344ec · outbound

This paper cites MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.325140Z

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 c7c95d25-a18b-41a9-9f97-59a0d7a6139b · outbound

This paper cites Causal World Modeling for Robot Control.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Causal World Modeling for Robot Control

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.339484Z

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 c4cbe177-a852-4d45-9eca-d3a27456b067 · outbound

This paper cites Pytorch distributed: Experiences on accelerating data parallel training.Proceedings of the VLDB Endowment, 13(12):3005–3018, 2020.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Pytorch distributed: Experiences on accelerating data parallel training.Proceedings of the VLDB Endowment, 13(12):3005–3018, 2020

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.794858Z

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 40d7770b-4240-4ce4-a229-93bb23617050 · outbound

This paper cites Torchtitan: One-stop pytorch native solution for production ready LLM pretraining.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Torchtitan: One-stop pytorch native solution for production ready LLM pretraining

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.738988Z

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 473c2d7a-4c49-488f-80d6-8945664f9613 · outbound

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

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.333017Z

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 464c14f7-12a4-4a2f-9696-f95fba431445 · outbound

This paper cites Flow matching for generative modeling.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Flow matching for generative modeling

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.736148Z

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 d6ff8eda-bb2f-446a-ac7b-fe0605904ecf · outbound

This paper cites DeepSeek-V3 Technical Report.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence DeepSeek-V3 Technical Report

Reference 58

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.318622Z

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 fcb022fb-6e5d-4feb-9d85-acc5e2a9d5d4 · outbound

This paper cites Flow-grpo: Training flow matching models via online rl.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Flow-grpo: Training flow matching models via online rl

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.732991Z

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 11334e03-e355-4ae6-924e-e86d06c2c4c8 · outbound

This paper cites GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.271067Z

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 52239194-9700-4306-9bd4-5cc0c812d290 · outbound

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

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Flow straight and fast: Learning to generate and transfer data with rectified flow

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.889150Z

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 e232313d-ae74-41ba-85ca-1aa9ac3cfe1e · outbound

This paper cites VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

Reference 62

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.350703Z

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 9c5523d9-31bb-45bc-a636-bb086c6a3f6a · outbound

This paper cites Hpsv3: Towards wide-spectrum human preference score.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Hpsv3: Towards wide-spectrum human preference score

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.724491Z

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 d4824ef0-bd1d-40e3-849c-37499dde4a93 · outbound

This paper cites Real: Efficient rlhf training of large language models with parameter reallocation.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Real: Efficient rlhf training of large language models with parameter reallocation

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.727250Z

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 f58a3575-7986-45ba-91bf-c53d208e01e2 · outbound

This paper cites Ray: A distributed framework for emerging {AI} applications.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Ray: A distributed framework for emerging {AI} applications

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.750194Z

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 bc37b517-4919-4e5d-9f5f-d77b863bd67a · outbound

This paper cites Do generative video models understand physical principles? InProceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Do generative video models understand physical principles? InProceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.717244Z

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 968dffcc-9434-4bda-8baf-a5f669c945b4 · outbound

This paper cites Efficient large-scale language model training on gpu clusters using megatron-lm.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Efficient large-scale language model training on gpu clusters using megatron-lm

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.851883Z

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 09dac93e-8f76-4794-8acf-32225fee767f · outbound

This paper cites Nowlan and Geoffrey E.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Nowlan and Geoffrey E

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.816957Z

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 aec767cb-602e-4f70-90bc-7685a2c7220f · outbound

This paper cites The pagerank citation ranking : Bringing order to the web.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence The pagerank citation ranking : Bringing order to the web

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.741486Z

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 d1773c59-9cad-413b-9689-f6e09ad96be3 · outbound

This paper cites Switch diffusion transformer: Synergizing denoising tasks with sparse mixture-of-experts.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Switch diffusion transformer: Synergizing denoising tasks with sparse mixture-of-experts

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.792609Z

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 2be8db7f-9845-4cdf-9b24-72d192a2f82e · outbound

This paper cites Scalable diffusion models with transformers.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Scalable diffusion models with transformers

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.882836Z

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 84511f17-e38c-46c3-a1ff-6e671e40ce22 · outbound

This paper cites Lumina- image 2.0: A unified and efficient image generative framework.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Lumina- image 2.0: A unified and efficient image generative framework

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.846711Z

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 6ad04e81-d91d-4b06-9c47-5dca10302cd9 · outbound

This paper cites Qwen3.6-27B: Flagship-level coding in a 27B dense model.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Qwen3.6-27B: Flagship-level coding in a 27B dense model

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.830705Z

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 4bc46d9b-1a6d-4bcd-bc14-32014c801094 · outbound

This paper cites Physics-IQ Verified.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Physics-IQ Verified

Reference 74

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.354852Z

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 da621f34-97d6-409b-b817-23bb2e5dcb2e · outbound

This paper cites Manning, and Chelsea Finn.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Manning, and Chelsea Finn

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.810864Z

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 038b75f1-3de7-44e6-8e8c-3777eaf8cbf2 · outbound

This paper cites Deepspeed-moe: Advancing mixture-of-experts inference and training to power next-generation ai scale.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Deepspeed-moe: Advancing mixture-of-experts inference and training to power next-generation ai scale

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.814087Z

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 919fc223-ef0e-4f77-af59-e31f86ed8a71 · outbound

This paper cites Zero: Memory optimizations toward training trillion parameter models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Zero: Memory optimizations toward training trillion parameter models

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.817163Z

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 dae434a5-f7d6-44e8-9344-81cd38555028 · outbound

This paper cites Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models

Reference 78

Resolution: metadata mismatch; local_arxiv, observed 2026-07-09T03:05:55.168574Z

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 a650b96b-0a8a-4a9f-8ab7-24366bf6f934 · outbound

This paper cites GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving

Reference 79

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.259747Z

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 97ea944d-6de3-4aa4-9a62-14759002b823 · outbound

This paper cites Image super-resolution via iterative refinement.IEEE transactions on pattern analysis and machine intelligence, 45(4):4713–4726, 2022.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Image super-resolution via iterative refinement.IEEE transactions on pattern analysis and machine intelligence, 45(4):4713–4726, 2022

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.806491Z

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 38a07966-514c-4155-a6e7-fe155d515dfa · outbound

This paper cites Proximal Policy Optimization Algorithms.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Proximal Policy Optimization Algorithms

Reference 81

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.322189Z

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 c47deaf5-7d9f-4e98-973e-5430389a9be2 · outbound

This paper cites Seedance 2.0: Advancing Video Generation for World Complexity.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Seedance 2.0: Advancing Video Generation for World Complexity

Reference 82

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.356921Z

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 5d982b03-7d9b-4c05-8e04-0c63c9ced34f · outbound

This paper cites Sparse Mixture-of-Experts Routing in Visual Diffusion Transformers:Diagnosis, Boundary Calibration and Evolutionary Roadmap from Routing Collapse to Selective Deadlock.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Sparse Mixture-of-Experts Routing in Visual Diffusion Transformers:Diagnosis, Boundary Calibration and Evolutionary Roadmap from Routing Collapse to Selective Deadlock

Reference 83

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.352039Z

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 835da1a1-d149-49c7-a65f-865026b1d31b · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 84

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.353715Z

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 2a2a4251-64d1-4448-869e-7ab78b2c0bc5 · outbound

This paper cites GLU Variants Improve Transformer.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence GLU Variants Improve Transformer

Reference 85

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.184581Z

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 fb08d893-8931-4f43-89d8-362c3c877578 · outbound

This paper cites Mesh-tensorflow: Deep learning for supercomputers.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Mesh-tensorflow: Deep learning for supercomputers

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.870274Z

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 32ae3d71-85b3-4adf-a9a1-8d7689e95057 · outbound

This paper cites Outrageously large neural networks: The sparsely-gated mixture-of-experts layer.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Outrageously large neural networks: The sparsely-gated mixture-of-experts layer

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.864664Z

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 1e44ba84-e90d-490b-a7b2-88690518180c · outbound

This paper cites Hybridflow: A flexible and efficient rlhf framework.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Hybridflow: A flexible and efficient rlhf framework

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.884832Z

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 6d976b50-22dc-484d-a0af-becea7fd26c9 · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 89

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.328143Z

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 1d797439-c349-460b-898b-43d24b56e346 · outbound

This paper cites Make-a-video: Text-to-video generation without text-video data.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Make-a-video: Text-to-video generation without text-video data

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.868532Z

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 8cf65560-843c-4178-95a5-a23029179f14 · outbound

This paper cites Denoising diffusion implicit models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Denoising diffusion implicit models

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.875666Z

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 d6d45c22-70df-4efe-bd4e-c9ed7ebb22cf · outbound

This paper cites Transnet v2: An effective deep network architecture for fast shot transition detection.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Transnet v2: An effective deep network architecture for fast shot transition detection

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.862914Z

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 0755ce10-6287-42c9-857e-670fedd53d33 · outbound

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

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

Reference 93

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.236141Z

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 160d8aa8-d12f-43e4-a359-51c79c75ad8d · outbound

This paper cites Enhancing spatial understanding in image generation via reward modeling.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Enhancing spatial understanding in image generation via reward modeling

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.857468Z

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 fcc3de0e-a0fe-440d-96e2-fab7e393983c · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Gemini: A Family of Highly Capable Multimodal Models

Reference 95

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.328674Z

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 f74cdbbd-8267-4731-a1ee-2b41c2990fad · outbound

This paper cites Evaluating Gemini Robotics Policies in a Veo World Simulator.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Evaluating Gemini Robotics Policies in a Veo World Simulator

Reference 96

Resolution: verified exact; arxiv_id, observed 2026-07-09T03:05:55.344354Z

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 29b8e9b5-aa8a-4167-ad5f-f5db53fff0b4 · outbound

This paper cites Advancing Open-source World Models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Advancing Open-source World Models

Reference 97

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.240536Z

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 5eef6e33-39c3-4207-9b22-36a51d5beee7 · outbound

This paper cites slime: An LLM post-training framework for reinforcement learning at scale.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence slime: An LLM post-training framework for reinforcement learning at scale

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.859462Z

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 6ee41ac9-c8d5-49ce-bebb-de466474b3b1 · outbound

This paper cites Improving and generalizing flow-based generative models with minibatch optimal transport.Transactions on Machine Learning Research, 2024.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Improving and generalizing flow-based generative models with minibatch optimal transport.Transactions on Machine Learning Research, 2024

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T03:05:55.847540Z

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 f36e0406-9dc6-46d4-9573-787d6d1d8b00 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence LLaMA: Open and Efficient Foundation Language Models

Reference 100

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.285108Z

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 8aa0e333-3d98-4862-baff-6907f5db724c · inbound

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

Native Video-Action Pretraining for Generalizable Robot Control Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Reference 70

Resolution: verified exact; local_arxiv, observed 2026-07-10T04:16:48.702844Z

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 a760df59-1c6b-4b7a-b322-088f2b59a3c9 · inbound

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

Native Video-Action Pretraining for Generalizable Robot Control Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-02T07:53:39.262642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2119e194-4fbd-4a60-b3f8-fc2cb5f98de2 · inbound

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation cites this paper.

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T07:09:07.343135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c80363e-6ece-424e-95f9-5f98349c3f9f · inbound

$N_0$-TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich Manipulation cites this paper.

$N_0$-TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich Manipulation Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-30T12:42:18.533960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.