Paper Citation Record · LEDGER

MAGI-1: Autoregressive Video Generation at Scale

As of 6 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 100 inbound Pith citation observations for arXiv:2505.13211.

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

pith.paper-citation-record.v1
2505.13211 v1

Coverage vector

measured 52 of 52 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-13T20:31:15.700943Z

measured 152 of 152 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 100 of 134 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T16:01:30.781337Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T01:46:41.063877Z

Reference resolution

52 of 52 outbound references displayed

verified exact37
verified fuzzy3
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch9

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 40898742-15f6-47a5-8792-de233276cd37 · outbound

This paper cites GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints.

MAGI-1: Autoregressive Video Generation at Scale GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.853216Z

Source-reported events for the cited work

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

Observation c8f5e7b2-4ce7-4771-860b-08dded11dfd3 · outbound

This paper cites Building Normalizing Flows with Stochastic Interpolants.

MAGI-1: Autoregressive Video Generation at Scale Building Normalizing Flows with Stochastic Interpolants

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.727468Z

Source-reported events for the cited work

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

Observation ac0de60e-91f8-4783-b843-dd7b69fd9d75 · outbound

This paper cites VideoPhy: Evaluating Physical Commonsense for Video Generation.

MAGI-1: Autoregressive Video Generation at Scale VideoPhy: Evaluating Physical Commonsense for Video Generation

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-20T11:34:37.994076Z

Source-reported events for the cited work

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

Observation e117bfab-550c-41d8-944a-33956521430f · outbound

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

MAGI-1: Autoregressive Video Generation at Scale Lumiere: A space-time diffusion model for video generation

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T20:31:15.860688Z

Source-reported events for the cited work

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

Observation 108c7b27-eccc-4983-8141-a90ce92558f3 · outbound

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

MAGI-1: Autoregressive Video Generation at Scale Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.753806Z

Source-reported events for the cited work

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

Observation 6e35f018-2761-4a75-b4e9-2cfc59cd917e · outbound

This paper cites PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis.

MAGI-1: Autoregressive Video Generation at Scale PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T20:31:15.757258Z

Source-reported events for the cited work

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

Observation 5387d609-cfcc-483f-b3da-0427aa9013b8 · outbound

This paper cites LongVILA: Scaling Long-Context Visual Language Models for Long Videos.

MAGI-1: Autoregressive Video Generation at Scale LongVILA: Scaling Long-Context Visual Language Models for Long Videos

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-17T03:51:25.572615Z

Source-reported events for the cited work

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

Observation ee7ee286-0ca0-4c7f-9cab-8b9467b782e3 · outbound

This paper cites CoPhy: A Scalable, Portable, and Interactive Index Advisor for Large Workloads.

MAGI-1: Autoregressive Video Generation at Scale CoPhy: A Scalable, Portable, and Interactive Index Advisor for Large Workloads

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.764253Z

Source-reported events for the cited work

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

Observation 5b769f04-a27a-403f-b2c1-a6b682b3af3e · outbound

This paper cites Flex Attention: A Programming Model for Generating Optimized Attention Kernels.

MAGI-1: Autoregressive Video Generation at Scale Flex Attention: A Programming Model for Generating Optimized Attention Kernels

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-17T21:27:16.810492Z

Source-reported events for the cited work

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

Observation ee5f0c65-79ef-49b8-a74d-4e22d879d5a7 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

MAGI-1: Autoregressive Video Generation at Scale An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.769776Z

Source-reported events for the cited work

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

Observation 0a27491f-249b-41b2-b4ea-b0f91e2e2c0f · outbound

This paper cites USP: A Unified Sequence Parallelism Approach for Long Context Generative AI.

MAGI-1: Autoregressive Video Generation at Scale USP: A Unified Sequence Parallelism Approach for Long Context Generative AI

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T20:31:15.772850Z

Source-reported events for the cited work

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

Observation d062ed69-fb33-4f4d-9da4-7b47739030ca · outbound

This paper cites ByteScale: Efficient Scaling of LLM Training with a 2048K Context Length on More Than 12,000 GPUs.

MAGI-1: Autoregressive Video Generation at Scale ByteScale: Efficient Scaling of LLM Training with a 2048K Context Length on More Than 12,000 GPUs

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.775808Z

Source-reported events for the cited work

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

Observation 372ad332-0795-49e9-b7fb-a3f7b29689a9 · outbound

This paper cites LoongTrain: Efficient Training of Long-Sequence LLMs with Head-Context Parallelism.

MAGI-1: Autoregressive Video Generation at Scale LoongTrain: Efficient Training of Long-Sequence LLMs with Head-Context Parallelism

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T20:31:15.778726Z

Source-reported events for the cited work

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

Observation 8ce6ea0b-4f3d-4d1f-bc4f-154aab845976 · outbound

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

MAGI-1: Autoregressive Video Generation at Scale LTX-Video: Realtime Video Latent Diffusion

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.781129Z

Source-reported events for the cited work

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

Observation e6b5719f-8d14-4339-8308-9a19b6e8fd2c · outbound

This paper cites Scaling Laws and Interpretability of Learning from Repeated Data.

MAGI-1: Autoregressive Video Generation at Scale Scaling Laws and Interpretability of Learning from Repeated Data

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-17T15:52:40.700889Z

Source-reported events for the cited work

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

Observation b505e1b7-25f2-4dec-bfec-5b5bca140628 · outbound

This paper cites Classifier-Free Diffusion Guidance.

MAGI-1: Autoregressive Video Generation at Scale Classifier-Free Diffusion Guidance

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.787113Z

Source-reported events for the cited work

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

Observation 8200b37d-d3ee-4cc8-8ac6-d5ca80c818c9 · outbound

This paper cites Video Diffusion Models.

MAGI-1: Autoregressive Video Generation at Scale Video Diffusion Models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.790305Z

Source-reported events for the cited work

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

Observation cca792f4-4c2e-4636-b48e-d696a5063dd1 · outbound

This paper cites VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models.

MAGI-1: Autoregressive Video Generation at Scale VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T20:31:15.793611Z

Source-reported events for the cited work

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

Observation f9ff1230-4634-4536-b768-edaf934419f1 · outbound

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

MAGI-1: Autoregressive Video Generation at Scale DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models

Reference 19

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T20:31:15.796296Z

Source-reported events for the cited work

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

Observation 0176d427-0482-489a-ad5b-21ff5f5bff98 · outbound

This paper cites Auto-Encoding Variational Bayes.

MAGI-1: Autoregressive Video Generation at Scale Auto-Encoding Variational Bayes

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.799032Z

Source-reported events for the cited work

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

Observation 9ae9a470-cd0f-4065-836a-6a790a35dde2 · outbound

This paper cites VideoPoet: A Large Language Model for Zero-Shot Video Generation.

MAGI-1: Autoregressive Video Generation at Scale VideoPoet: A Large Language Model for Zero-Shot Video Generation

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:51:05.830483Z

Source-reported events for the cited work

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

Observation f65506e8-04b8-4284-85d3-668d7cecf64a · outbound

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

MAGI-1: Autoregressive Video Generation at Scale HunyuanVideo: A Systematic Framework For Large Video Generative Models

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.805001Z

Source-reported events for the cited work

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

Observation 1f8d3837-39da-4def-a512-63eac301188f · outbound

This paper cites Enhancing Training Efficiency Using Packing with Flash Attention.

MAGI-1: Autoregressive Video Generation at Scale Enhancing Training Efficiency Using Packing with Flash Attention

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.808040Z

Source-reported events for the cited work

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

Observation f722f808-41e8-494f-9022-2764e5f110a3 · outbound

This paper cites Deduplicating Training Data Makes Language Models Better.

MAGI-1: Autoregressive Video Generation at Scale Deduplicating Training Data Makes Language Models Better

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.810764Z

Source-reported events for the cited work

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

Observation b62ac5ff-08e4-45d8-936e-b76c8dac6155 · outbound

This paper cites TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training.

MAGI-1: Autoregressive Video Generation at Scale TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T20:31:15.813662Z

Source-reported events for the cited work

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

Observation f8c11fef-4e5b-409a-92d5-b5b5016bf511 · outbound

This paper cites Flow Matching for Generative Modeling.

MAGI-1: Autoregressive Video Generation at Scale Flow Matching for Generative Modeling

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.816427Z

Source-reported events for the cited work

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

Observation 368d5e6f-66cc-4a23-9757-53065ee289c4 · outbound

This paper cites Ring Attention with Blockwise Transformers for Near-Infinite Context.

MAGI-1: Autoregressive Video Generation at Scale Ring Attention with Blockwise Transformers for Near-Infinite Context

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.819075Z

Source-reported events for the cited work

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

Observation 0a8c0c05-a0ac-4bae-b777-6373aed0da67 · outbound

This paper cites Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow.

MAGI-1: Autoregressive Video Generation at Scale Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.821604Z

Source-reported events for the cited work

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

Observation e6bed780-a607-4ff0-b655-9b4d921f410d · outbound

This paper cites Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed.

MAGI-1: Autoregressive Video Generation at Scale Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-17T03:56:20.038756Z

Source-reported events for the cited work

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

Observation eed6a369-57ed-43b2-a4a0-53823b0bb2fe · outbound

This paper cites Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model.

MAGI-1: Autoregressive Video Generation at Scale Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-19T08:02:24.560574Z

Source-reported events for the cited work

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

Observation b1c639c2-4719-4781-bc78-4bcafbefaf42 · outbound

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

MAGI-1: Autoregressive Video Generation at Scale Latte: Latent Diffusion Transformer for Video Generation

Reference 31

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

Source-reported events for the cited work

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

Observation f9b51e61-de86-4545-b1c6-9e1db5cf753c · outbound

This paper cites Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation.

MAGI-1: Autoregressive Video Generation at Scale Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-18T14:40:00.221207Z

Source-reported events for the cited work

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

Observation 22a45069-e599-4c6c-84b2-6f492844737e · outbound

This paper cites Do generative video models understand physical principles?.

MAGI-1: Autoregressive Video Generation at Scale Do generative video models understand physical principles?

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:47:06.031259Z

Source-reported events for the cited work

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

Observation dbd52165-24bc-4f02-a730-875609d486de · outbound

This paper cites an unresolved cited work.

MAGI-1: Autoregressive Video Generation at Scale Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-05-13T20:31:15.871066Z

Source-reported events for the cited work

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

Observation dd52bf2f-0608-4efe-abea-051583d32cbe · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

MAGI-1: Autoregressive Video Generation at Scale DINOv2: Learning Robust Visual Features without Supervision

Reference 35

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T20:31:15.838885Z

Source-reported events for the cited work

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

Observation 73375d52-4a4f-450e-aef1-81bf8a4ef7b0 · outbound

This paper cites Movie Gen: A Cast of Media Foundation Models.

MAGI-1: Autoregressive Video Generation at Scale Movie Gen: A Cast of Media Foundation Models

Reference 36

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T20:31:15.841638Z

Source-reported events for the cited work

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

Observation 8baa8998-6780-44a0-bdf6-e2a4af2b779c · outbound

This paper cites ZeRO: Memory Optimizations Toward Training Trillion Parameter Models.

MAGI-1: Autoregressive Video Generation at Scale ZeRO: Memory Optimizations Toward Training Trillion Parameter Models

Reference 37

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T09:24:35.924862Z

Source-reported events for the cited work

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

Observation a22f5afc-f879-4f3d-9a26-5d1cfcac724b · outbound

This paper cites Progressive Distillation for Fast Sampling of Diffusion Models.

MAGI-1: Autoregressive Video Generation at Scale Progressive Distillation for Fast Sampling of Diffusion Models

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.847396Z

Source-reported events for the cited work

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

Observation a65e16b8-4448-48ea-b52c-67704f096478 · outbound

This paper cites FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision.

MAGI-1: Autoregressive Video Generation at Scale FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:45:36.571697Z

Source-reported events for the cited work

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

Observation 21c8a766-2231-4801-8626-067763bc29df · outbound

This paper cites Score-Based Generative Modeling through Stochastic Differential Equations.

MAGI-1: Autoregressive Video Generation at Scale Score-Based Generative Modeling through Stochastic Differential Equations

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.723649Z

Source-reported events for the cited work

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

Observation 4771d927-747e-4d0b-ab42-9d8a97912149 · outbound

This paper cites Reproducibility — pytorch 2.6 documentation.

MAGI-1: Autoregressive Video Generation at Scale Reproducibility — pytorch 2.6 documentation

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T20:31:15.867442Z

Source-reported events for the cited work

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

Observation 089ef97d-5fef-4d2e-b6fb-9eb172c1f0ca · outbound

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

MAGI-1: Autoregressive Video Generation at Scale Wan: Open and Advanced Large-Scale Video Generative Models

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.856005Z

Source-reported events for the cited work

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

Observation 642e6529-d8d6-4ecf-ab0a-1725952c88aa · outbound

This paper cites FlexSP: Accelerating Large Language Model Training via Flexible Sequence Parallelism.

MAGI-1: Autoregressive Video Generation at Scale FlexSP: Accelerating Large Language Model Training via Flexible Sequence Parallelism

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.858621Z

Source-reported events for the cited work

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

Observation 8360f730-b2a3-4d25-9691-0b7487de94f0 · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

MAGI-1: Autoregressive Video Generation at Scale Efficient Streaming Language Models with Attention Sinks

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.734450Z

Source-reported events for the cited work

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

Observation b8d53c12-68bd-47a3-a869-5e0867fca5db · outbound

This paper cites GSPMD: General and Scalable Parallelization for ML Computation Graphs.

MAGI-1: Autoregressive Video Generation at Scale GSPMD: General and Scalable Parallelization for ML Computation Graphs

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:36:36.562059Z

Source-reported events for the cited work

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

Observation 24566f36-45fc-4dab-96df-4650577c6bd2 · outbound

This paper cites CLEVRER: CoLlision Events for Video REpresentation and Reasoning.

MAGI-1: Autoregressive Video Generation at Scale CLEVRER: CoLlision Events for Video REpresentation and Reasoning

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-16T18:01:50.618167Z

Source-reported events for the cited work

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

Observation b6ad91ee-1af6-45b4-9094-32e5349c5826 · outbound

This paper cites From slow bidirectional to fast causal video generators.

MAGI-1: Autoregressive Video Generation at Scale From slow bidirectional to fast causal video generators

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.744482Z

Source-reported events for the cited work

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

Observation 34c65f09-1274-41e8-bec1-d236106d4720 · outbound

This paper cites OneFlow: Redesign the Distributed Deep Learning Framework from Scratch.

MAGI-1: Autoregressive Video Generation at Scale OneFlow: Redesign the Distributed Deep Learning Framework from Scratch

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.748238Z

Source-reported events for the cited work

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

Observation c4530406-ad43-4014-96c3-6cb0079e9acc · outbound

This paper cites PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel.

MAGI-1: Autoregressive Video Generation at Scale PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:31:15.750971Z

Source-reported events for the cited work

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

Observation eb9fdcd9-260b-499b-9bad-469d76b1e66a · outbound

This paper cites This enables an equivalent transformation of the form Y = ( X · diag(s)−1) · (diag(s)W), effectively mitigating the impact of outliers in channel-wise activations.

MAGI-1: Autoregressive Video Generation at Scale This enables an equivalent transformation of the form Y = ( X · diag(s)−1) · (diag(s)W), effectively mitigating the impact of outliers in channel-wise activations

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T20:31:15.865575Z

Source-reported events for the cited work

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

Observation 9e0b7fba-0291-4a42-937e-cd981ea7cb0a · outbound

This paper cites an unresolved cited work.

MAGI-1: Autoregressive Video Generation at Scale Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-05-13T20:31:15.869298Z

Source-reported events for the cited work

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

Observation 5c43cfda-bd5f-49ad-9e61-4dc9a043936a · outbound

This paper cites an unresolved cited work.

MAGI-1: Autoregressive Video Generation at Scale Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-05-13T20:31:15.863101Z

Source-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 09d5df73-b3fe-4a3b-9e27-7054e2b4d82b · inbound

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

Matrix-game 2.0: An open-source real-time and streaming interactive world model MAGI-1: Autoregressive Video Generation at Scale

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-18T22:36:53.344376Z

Source-reported events for the cited work

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

Observation be07b53f-fc56-413b-b096-767400a84c2a · inbound

MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation cites this paper.

MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:30.781337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 271442c1-62b2-4a68-aea6-e7ae265cbd28 · inbound

InfinityHuman: Towards Long-Term Audio-Driven Human cites this paper.

InfinityHuman: Towards Long-Term Audio-Driven Human MAGI-1: Autoregressive Video Generation at Scale

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T15:19:37.062536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6c22a85-d9b3-44ca-9fd1-605e58d1fa72 · inbound

LongLive: Real-time Interactive Long Video Generation cites this paper.

LongLive: Real-time Interactive Long Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-15T03:52:59.489177Z

Source-reported events for the cited work

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

Observation c8946ec8-94e0-4412-a28d-454e87fc2ac4 · inbound

Rolling Forcing: Autoregressive Long Video Diffusion in Real Time cites this paper.

Rolling Forcing: Autoregressive Long Video Diffusion in Real Time MAGI-1: Autoregressive Video Generation at Scale

Reference 93

Resolution: verified exact; local_arxiv, observed 2026-05-16T11:15:29.213136Z

Source-reported events for the cited work

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

Observation 0e176d43-61a4-4145-93ae-7dd11070d02d · inbound

Self-Forcing++: Towards Minute-Scale High-Quality Video Generation cites this paper.

Self-Forcing++: Towards Minute-Scale High-Quality Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-05-15T22:39:54.042812Z

Source-reported events for the cited work

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

Observation 9e28a3c3-a4d4-45b5-ba4e-5de1363e5b9f · inbound

Generative View Stitching cites this paper.

Generative View Stitching MAGI-1: Autoregressive Video Generation at Scale

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-18T02:55:46.636476Z

Source-reported events for the cited work

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

Observation 7084c971-22f4-4e40-9403-1a32c51b6135 · inbound

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation cites this paper.

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation MAGI-1: Autoregressive Video Generation at Scale

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-17T05:19:05.030361Z

Source-reported events for the cited work

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

Observation 0196392f-5a50-4b4d-902e-743a8247de51 · inbound

BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation cites this paper.

BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T19:41:58.485435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c61e4b2b-a080-455b-981b-3049682ffea4 · inbound

Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation cites this paper.

Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation MAGI-1: Autoregressive Video Generation at Scale

Reference 69

Resolution: verified exact; local_arxiv, observed 2026-05-16T18:17:55.036128Z

Source-reported events for the cited work

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

Observation 5ec526b6-301d-4313-9d81-0c5fb23bf4b3 · inbound

End-to-End Training for Autoregressive Video Diffusion via Self-Resampling cites this paper.

End-to-End Training for Autoregressive Video Diffusion via Self-Resampling MAGI-1: Autoregressive Video Generation at Scale

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-03T15:46:11.663008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 793e5169-c786-4b81-8c0c-884477b022c9 · inbound

Transition Matching Distillation for Fast Video Generation cites this paper.

Transition Matching Distillation for Fast Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-03T10:35:06.602602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 362cc648-f5e7-4b11-a69c-30cdd8f15824 · inbound

Advancing Open-source World Models cites this paper.

Advancing Open-source World Models MAGI-1: Autoregressive Video Generation at Scale

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-05-16T09:07:00.971701Z

Source-reported events for the cited work

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

Observation 3033a21e-7f7a-4f42-8940-3db14f64a63b · inbound

Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation cites this paper.

Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-05-21T17:32:01.822674Z

Source-reported events for the cited work

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

Observation 388cc9a6-0c2f-4bd3-90c1-e6312248db1c · inbound

Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation cites this paper.

Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-05-22T11:51:29.960821Z

Source-reported events for the cited work

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

Observation f5600c2a-2a43-4f67-9c36-1e9853f140d0 · inbound

Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation cites this paper.

Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T05:30:28.194599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42d49d8f-d9c2-446b-8e85-0b3a2a8afd30 · inbound

Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention cites this paper.

Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention MAGI-1: Autoregressive Video Generation at Scale

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T04:33:11.200535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfa20cb7-c72b-4e82-87ec-28f5e4e9345b · inbound

Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention cites this paper.

Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention MAGI-1: Autoregressive Video Generation at Scale

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T00:38:17.051050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7951c0a3-aa5f-4b19-9f20-904c45e229e0 · inbound

SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes cites this paper.

SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes MAGI-1: Autoregressive Video Generation at Scale

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-16T07:37:33.022750Z

Source-reported events for the cited work

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

Observation 1d01fc7f-0c92-490a-bac4-4cded94decaf · inbound

Optimizing Few-Step Generation with Adaptive Matching Distillation cites this paper.

Optimizing Few-Step Generation with Adaptive Matching Distillation MAGI-1: Autoregressive Video Generation at Scale

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-03T03:42:45.618222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c8ef9c9-d931-4f81-8ee6-dc2c1cc8c984 · inbound

Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion cites this paper.

Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion MAGI-1: Autoregressive Video Generation at Scale

Reference 86

Resolution: metadata mismatch; local_arxiv, observed 2026-05-16T07:07:29.787621Z

Source-reported events for the cited work

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

Observation 879f17e1-9231-44e1-9cd9-6a0bc4927fb0 · inbound

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

Olaf-World: Orienting Latent Actions for Video World Modeling MAGI-1: Autoregressive Video Generation at Scale

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T01:20:05.452452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1275c9e7-8139-4a68-a626-b24b70b4c603 · inbound

EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation cites this paper.

EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-15T22:20:22.206758Z

Source-reported events for the cited work

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

Observation ddb4dd0d-a749-4054-99f4-e1448607f985 · inbound

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

World Action Models are Zero-shot Policies MAGI-1: Autoregressive Video Generation at Scale

Reference 78

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation f50b51a8-d40d-4473-ad95-6f265343e380 · inbound

Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking cites this paper.

Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking MAGI-1: Autoregressive Video Generation at Scale

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T21:11:50.391061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e1361e4-9b74-4224-b18f-2d98f0379ea8 · inbound

GeoWorld: Geometric World Models cites this paper.

GeoWorld: Geometric World Models MAGI-1: Autoregressive Video Generation at Scale

Reference 73

Resolution: verified exact; local_arxiv, observed 2026-05-21T11:40:03.263344Z

Source-reported events for the cited work

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

Observation 79953a1d-6138-467e-8c33-d9a3653520d6 · inbound

Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows cites this paper.

Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows MAGI-1: Autoregressive Video Generation at Scale

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-05-15T07:05:11.548658Z

Source-reported events for the cited work

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

Observation 687ec34f-f96f-49e8-bbc4-fff00c638ffd · inbound

Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation cites this paper.

Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation MAGI-1: Autoregressive Video Generation at Scale

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:48:15.755455Z

Source-reported events for the cited work

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

Observation 2f9f4541-d474-4a4e-88c3-f6fc00958855 · inbound

Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation cites this paper.

Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 34

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 9db2d752-d4c2-4855-9d92-7e0c6abfe8ac · inbound

Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation cites this paper.

Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-13T13:36:01.141666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a4a3024-8741-40b1-b826-ce75901dc75c · inbound

Unified Vector Floorplan Generation via Markup Representation cites this paper.

Unified Vector Floorplan Generation via Markup Representation MAGI-1: Autoregressive Video Generation at Scale

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 56adeb92-607a-4435-9683-d4ecd8175cfc · inbound

Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis cites this paper.

Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis MAGI-1: Autoregressive Video Generation at Scale

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation c14101f3-e6ce-469f-b76b-18827ff11567 · inbound

MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation cites this paper.

MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 39dfb427-275b-436c-80e8-1a927140b71e · inbound

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory cites this paper.

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory MAGI-1: Autoregressive Video Generation at Scale

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation a34da892-3be7-4686-8614-55663c767ad4 · inbound

PhysInOne: Visual Physics Learning and Reasoning in One Suite cites this paper.

PhysInOne: Visual Physics Learning and Reasoning in One Suite MAGI-1: Autoregressive Video Generation at Scale

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation d448678a-2223-4db0-a613-0f1dc27d8ce6 · inbound

Envisioning the Future, One Step at a Time cites this paper.

Envisioning the Future, One Step at a Time MAGI-1: Autoregressive Video Generation at Scale

Reference 100

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 1249934a-411b-4c98-854e-fecb9b2f4b63 · inbound

DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer cites this paper.

DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer MAGI-1: Autoregressive Video Generation at Scale

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 40d449ee-6c12-48be-aeb7-0c2d07138df3 · inbound

Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation cites this paper.

Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 5ab91efd-160f-43e1-b2b0-ba405f708080 · inbound

Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation cites this paper.

Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 49efc2da-e127-4b97-8ca8-7b7eac439b59 · inbound

Mutual Forcing: Dual-Mode Self-Evolution for Fast Autoregressive Audio-Video Character Generation cites this paper.

Mutual Forcing: Dual-Mode Self-Evolution for Fast Autoregressive Audio-Video Character Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation d6e358d8-e9ad-4292-ac77-ff63f5702c47 · inbound

Motion-Aware Caching for Efficient Autoregressive Video Generation cites this paper.

Motion-Aware Caching for Efficient Autoregressive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation f1ec5648-4f20-4e3f-9341-f3eefa6ac2c6 · inbound

Motion-Aware Caching for Efficient Autoregressive Video Generation cites this paper.

Motion-Aware Caching for Efficient Autoregressive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-05-15T07:19:49.915489Z

Source-reported events for the cited work

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

Observation cc51c2c8-611f-4b30-ab50-8893b8ff6c90 · inbound

Video Generation with Predictive Latents cites this paper.

Video Generation with Predictive Latents MAGI-1: Autoregressive Video Generation at Scale

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 8db86566-fc65-46d1-96d4-206fcccdfd2c · inbound

Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation cites this paper.

Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 5c3ef276-96e2-4404-99cc-22d40cdeb3c9 · inbound

Stream-T1: Test-Time Scaling for Streaming Video Generation cites this paper.

Stream-T1: Test-Time Scaling for Streaming Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 44f70619-6df1-4080-9a37-295a960f1273 · inbound

RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control cites this paper.

RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control MAGI-1: Autoregressive Video Generation at Scale

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 7c14e5f8-983b-40d1-85ec-6ae8b92a74e2 · inbound

SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation cites this paper.

SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 3e93b62e-d9b8-4f1d-9bc1-e8868ec01286 · inbound

SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation cites this paper.

SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 614975d8-e969-4171-8e3d-7fc82b592808 · inbound

FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction cites this paper.

FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction MAGI-1: Autoregressive Video Generation at Scale

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 19b8335d-5763-4d00-9559-806aa267c3b4 · inbound

What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion cites this paper.

What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion MAGI-1: Autoregressive Video Generation at Scale

Reference 79

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 9a936151-ed29-47b5-b39a-bdde08ec4d16 · inbound

Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models cites this paper.

Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models MAGI-1: Autoregressive Video Generation at Scale

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:31:15.871842Z

Source-reported events for the cited work

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

Observation 9fe4a4a6-8544-4f17-8a57-a36d02d9a899 · inbound

Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation cites this paper.

Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:49:25.557101Z

Source-reported events for the cited work

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

Observation 1dcfddd1-2b1d-4222-a485-96f95369ffd5 · inbound

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation cites this paper.

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation MAGI-1: Autoregressive Video Generation at Scale

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-05-14T20:07:53.921619Z

Source-reported events for the cited work

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

Observation 5c150aff-550f-412b-95b2-fa6b11453d18 · inbound

Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation cites this paper.

Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-15T01:53:28.745055Z

Source-reported events for the cited work

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

Observation a57c24c4-ecc2-4d1f-aa30-f38ddf101dad · inbound

Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation cites this paper.

Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-20T21:59:06.486434Z

Source-reported events for the cited work

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

Observation c1c99123-f153-4ee4-88f7-5a092bf71b5b · inbound

Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation cites this paper.

Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-21T09:14:05.660209Z

Source-reported events for the cited work

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

Observation a9c9035b-d0ac-48b3-8e88-9e68383a7c9e · inbound

Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation cites this paper.

Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-06-30T21:45:05.517198Z

Source-reported events for the cited work

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

Observation 821c8003-761d-4aaa-8029-17bcf4e23185 · inbound

Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity cites this paper.

Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity MAGI-1: Autoregressive Video Generation at Scale

Reference 47

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T02:33:32.250226Z

Source-reported events for the cited work

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

Observation f7583d66-9111-413b-a440-d2b6e463d60b · inbound

EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration cites this paper.

EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration MAGI-1: Autoregressive Video Generation at Scale

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-06-30T21:25:04.891778Z

Source-reported events for the cited work

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

Observation 80fff1f3-fcf8-4156-b904-c40955e89347 · inbound

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation cites this paper.

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-06-30T21:05:04.328775Z

Source-reported events for the cited work

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

Observation a9fe6469-f3d8-455f-8c53-d2f0f293b637 · inbound

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer cites this paper.

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer MAGI-1: Autoregressive Video Generation at Scale

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-15T14:00:03.425581Z

Source-reported events for the cited work

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

Observation 833815d3-02af-4503-935a-b8a89e7321af · inbound

RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO cites this paper.

RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO MAGI-1: Autoregressive Video Generation at Scale

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-01T14:35:47.265349Z

Source-reported events for the cited work

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

Observation 9b9466e4-382d-492e-87e2-a7252fc835bc · inbound

Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation cites this paper.

Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-20T20:03:43.471204Z

Source-reported events for the cited work

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

Observation 51ff264d-b6b6-449c-a69d-0c593bedbfc0 · inbound

AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling cites this paper.

AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling MAGI-1: Autoregressive Video Generation at Scale

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-20T18:28:53.073849Z

Source-reported events for the cited work

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

Observation 23e96437-42fd-4dda-9881-9deed3e9091c · inbound

Image-to-Video Diffusion: From Foundations to Open Frontiers cites this paper.

Image-to-Video Diffusion: From Foundations to Open Frontiers MAGI-1: Autoregressive Video Generation at Scale

Reference 185

Resolution: verified exact; local_arxiv, observed 2026-05-20T15:08:25.012074Z

Source-reported events for the cited work

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

Observation 91ef9cb6-7633-453b-a010-29cc39832092 · inbound

Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos cites this paper.

Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos MAGI-1: Autoregressive Video Generation at Scale

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:58:13.898251Z

Source-reported events for the cited work

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

Observation 4d28d14f-c480-41c4-92c4-f04700d5c72d · inbound

Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion cites this paper.

Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion MAGI-1: Autoregressive Video Generation at Scale

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T11:23:14.137659Z

Source-reported events for the cited work

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

Observation 1955e5f2-9de2-4818-828e-56dc2d909464 · inbound

Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory cites this paper.

Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory MAGI-1: Autoregressive Video Generation at Scale

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-20T11:23:13.941716Z

Source-reported events for the cited work

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

Observation fa195093-dc29-4e3a-976e-fbe698c3766f · inbound

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation cites this paper.

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-05-20T11:03:13.302862Z

Source-reported events for the cited work

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

Observation ba24632d-cf05-4902-a2d9-31a9604ea092 · inbound

Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models cites this paper.

Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models MAGI-1: Autoregressive Video Generation at Scale

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-20T05:58:04.970841Z

Source-reported events for the cited work

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

Observation df42b9e9-f3a3-448f-b1ae-b95bfa8d12f1 · inbound

Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models cites this paper.

Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models MAGI-1: Autoregressive Video Generation at Scale

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:59:50.797957Z

Source-reported events for the cited work

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

Observation 87695064-156c-45ae-a369-2c88b3e4334f · inbound

Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models cites this paper.

Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models MAGI-1: Autoregressive Video Generation at Scale

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-06-30T18:35:00.110679Z

Source-reported events for the cited work

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

Observation f249b379-e18e-4948-9898-9b2525340e98 · inbound

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks cites this paper.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks MAGI-1: Autoregressive Video Generation at Scale

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-20T06:38:05.633588Z

Source-reported events for the cited work

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

Observation 047adea2-0f81-4da4-b988-0d4c77c9119e · inbound

DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation cites this paper.

DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-21T05:53:59.176561Z

Source-reported events for the cited work

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

Observation 271e7315-b37f-46ef-9508-a4cd10957af4 · inbound

DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation cites this paper.

DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:14:57.225761Z

Source-reported events for the cited work

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

Observation e2fcb934-737b-40e1-b7d8-e619de56c1f3 · inbound

DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation cites this paper.

DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T02:17:50.768138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e60f7e5-98c6-4166-ab6c-e4c7bf580d4d · inbound

Q-ARVD: Quantizing Autoregressive Video Diffusion Models cites this paper.

Q-ARVD: Quantizing Autoregressive Video Diffusion Models MAGI-1: Autoregressive Video Generation at Scale

Reference 19

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T05:29:39.507959Z

Source-reported events for the cited work

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

Observation e55c5da5-38d8-46b0-bb5a-8647053ef899 · inbound

WorldKV: Efficient World Memory with World Retrieval and Compression cites this paper.

WorldKV: Efficient World Memory with World Retrieval and Compression MAGI-1: Autoregressive Video Generation at Scale

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-22T06:21:10.186727Z

Source-reported events for the cited work

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

Observation 6cf572c8-3749-420b-b5dd-9431ea0bc144 · inbound

One-Forcing: Towards Stable One-Step Autoregressive Video Generation cites this paper.

One-Forcing: Towards Stable One-Step Autoregressive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-25T04:40:23.656245Z

Source-reported events for the cited work

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

Observation b09eb601-fd43-489f-b1c5-13717c26d177 · inbound

CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models cites this paper.

CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models MAGI-1: Autoregressive Video Generation at Scale

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-05-25T04:40:23.200922Z

Source-reported events for the cited work

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

Observation 0961f605-8fd2-43aa-9bb2-ea0d400e041b · inbound

minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models cites this paper.

minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models MAGI-1: Autoregressive Video Generation at Scale

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-06-29T08:23:14.782427Z

Source-reported events for the cited work

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

Observation b9f11c37-a463-41e0-bf41-5fa2dda9e688 · inbound

Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS cites this paper.

Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS MAGI-1: Autoregressive Video Generation at Scale

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T20:16:11.065754Z

Source-reported events for the cited work

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

Observation 2cbf2f11-d7cf-49dc-8544-34730138254e · inbound

Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation cites this paper.

Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-07-01T19:16:00.358022Z

Source-reported events for the cited work

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

Observation bc1476fe-31f7-4dca-bf7d-f19529a2e5b2 · inbound

DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory cites this paper.

DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory MAGI-1: Autoregressive Video Generation at Scale

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-06-28T22:42:46.836763Z

Source-reported events for the cited work

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

Observation b7b38a99-8384-4adf-a9c0-13709ac14deb · inbound

Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models cites this paper.

Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models MAGI-1: Autoregressive Video Generation at Scale

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-07-01T19:16:00.534286Z

Source-reported events for the cited work

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

Observation 1207205d-4708-4eba-b7f2-6443f6133cc3 · inbound

Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs cites this paper.

Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs MAGI-1: Autoregressive Video Generation at Scale

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-07-01T22:06:17.002298Z

Source-reported events for the cited work

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

Observation 612f9623-f140-4d98-9f03-1c44eeef643c · inbound

Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM Reasoning cites this paper.

Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM Reasoning MAGI-1: Autoregressive Video Generation at Scale

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-01T22:36:17.547746Z

Source-reported events for the cited work

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

Observation 62a04c9c-e0e7-441e-92b0-2e8a1f530cdb · inbound

LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation cites this paper.

LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-07-01T22:16:17.136015Z

Source-reported events for the cited work

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

Observation 844ee938-5036-41db-b270-1eca7d4a5a39 · inbound

Video-Mirai: Autoregressive Video Diffusion Models Need Foresight cites this paper.

Video-Mirai: Autoregressive Video Diffusion Models Need Foresight MAGI-1: Autoregressive Video Generation at Scale

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T02:56:29.545905Z

Source-reported events for the cited work

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

Observation edf4113a-23de-4939-a2c7-2298d985f095 · inbound

AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation cites this paper.

AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-02T03:06:29.323688Z

Source-reported events for the cited work

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

Observation 876cd0a8-0762-41d6-85a3-9cf6d1a15828 · inbound

DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation cites this paper.

DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-07-02T06:16:43.686394Z

Source-reported events for the cited work

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

Observation 378ba482-23de-4a42-b033-2db4354acbeb · inbound

Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation cites this paper.

Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-07-02T11:36:54.906133Z

Source-reported events for the cited work

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

Observation 6d4e9b8f-f751-41c4-a36f-5b98f52d9adc · inbound

Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them cites this paper.

Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them MAGI-1: Autoregressive Video Generation at Scale

Reference 87

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T12:36:57.149151Z

Source-reported events for the cited work

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

Observation 76f33f42-603e-4161-af5e-3f0dcc6ada7d · inbound

FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion cites this paper.

FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion MAGI-1: Autoregressive Video Generation at Scale

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-07-03T04:37:37.498788Z

Source-reported events for the cited work

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

Observation 365d3d35-253c-450c-b2c0-6124ff0e7828 · inbound

Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization cites this paper.

Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization MAGI-1: Autoregressive Video Generation at Scale

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-07-03T04:47:38.037937Z

Source-reported events for the cited work

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

Observation 8202919b-657e-49d2-9e17-bdee929368b2 · inbound

ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation cites this paper.

ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-07-03T08:17:45.946420Z

Source-reported events for the cited work

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

Observation 8e0474ac-b05d-401e-b293-cf7c3d0bc7d4 · inbound

Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI cites this paper.

Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI MAGI-1: Autoregressive Video Generation at Scale

Reference 119

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:28:44.980994Z

Source-reported events for the cited work

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

Observation 03223e0b-1289-4c85-966f-66e86e03ae19 · inbound

Physics-IQ Verified cites this paper.

Physics-IQ Verified MAGI-1: Autoregressive Video Generation at Scale

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:29:15.576571Z

Source-reported events for the cited work

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

Observation b89b2031-0cad-4800-8fde-c062349c20a1 · inbound

GEOPHYS: The Geometry of Physical Plausibility cites this paper.

GEOPHYS: The Geometry of Physical Plausibility MAGI-1: Autoregressive Video Generation at Scale

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:58:47.075360Z

Source-reported events for the cited work

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

Observation a709fb7f-7046-4ee8-8fcb-0aa9aa21adee · inbound

Towards Error-Free Long Video Generation cites this paper.

Towards Error-Free Long Video Generation MAGI-1: Autoregressive Video Generation at Scale

Reference 34

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T08:59:42.068844Z

Source-reported events for the cited work

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