Paper Citation Record · LEDGER

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

As of 19 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 28 inbound Pith citation observations for arXiv:2506.03141.

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

pith.paper-citation-record.v1
2506.03141 v2

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:12:17.628244Z

measured 64 of 64 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 28 of 28 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T05:06:52.053244Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T17:58:47.760773Z

Reference resolution

36 of 36 outbound references displayed

verified exact0
verified fuzzy5
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 96500013-c643-49cf-bbf2-11d951ccd5f1 · outbound

This paper cites Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.523287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 468cb3db-974f-4d36-a19a-cea2cd2c4080 · outbound

This paper cites Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.526708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5207c38b-a15d-4fc2-9cad-8683c84282c9 · outbound

This paper cites Autoregressive Video Generation without Vector Quantization.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Autoregressive Video Generation without Vector Quantization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.529993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e17f759b-4999-4706-b9c5-0c7da8281d6d · outbound

This paper cites The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.533297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6a3478b-e369-4ba5-a83e-ec5dc458715d · outbound

This paper cites Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.536837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39b33f8d-ef86-4377-880c-95334fc5b127 · outbound

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

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Long-Context Autoregressive Video Modeling with Next-Frame Prediction

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.540549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94f46396-c3a3-488a-8088-5f17cf2bac18 · outbound

This paper cites Long Context Tuning for Video Generation.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Long Context Tuning for Video Generation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.543716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4968c0f2-f214-4591-a6d7-c0a464770805 · outbound

This paper cites CameraCtrl: Enabling Camera Control for Text-to-Video Generation.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval CameraCtrl: Enabling Camera Control for Text-to-Video Generation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.546924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bc79a47-42df-46fc-b00b-d217d8829960 · outbound

This paper cites Nature 638, 8051 (2025), 656–663.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Nature 638, 8051 (2025), 656–663

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:12:18.190896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1557b2fb-9902-45a5-bb9e-73018f3f936e · outbound

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

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval VideoPoet: A Large Language Model for Zero-Shot Video Generation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.562082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f164a619-6614-4125-8079-d425f15bb81e · outbound

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

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval HunyuanVideo: A Systematic Framework For Large Video Generative Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.565245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 773edda9-b519-40e9-bd44-3fbd4b748581 · outbound

This paper cites Autoregressive Image Generation without Vector Quantization.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Autoregressive Image Generation without Vector Quantization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.568138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bebabb30-3ed8-4b82-8837-93653fb3088a · outbound

This paper cites Flow Matching for Generative Modeling.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Flow Matching for Generative Modeling

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.571141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3034e4c1-579f-4738-8759-035a7747bfac · outbound

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

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.574359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1bdfee4-7e77-4aaf-bde2-6aa6c01532dc · outbound

This paper cites You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.577727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad3d3edd-91d0-4cee-b070-a8c5e36db9c5 · outbound

This paper cites WorldSimBench: Towards Video Generation Models as World Simulators.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval WorldSimBench: Towards Video Generation Models as World Simulators

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.580891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d5e1cb6-f92b-4d6b-b121-90883bf3ce44 · outbound

This paper cites GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.584083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ecc685f-7530-4d00-b580-cb169fdbe5cd · outbound

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

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.587192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dda9aaae-1482-42cc-a9f4-eda9127e58af · outbound

This paper cites History-Guided Video Diffusion.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval History-Guided Video Diffusion

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.590181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2d53f0e-589e-42a4-9d88-b4cb0224f1ca · outbound

This paper cites Neurocomputing 568 (2024), 127063.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Neurocomputing 568 (2024), 127063

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:12:18.116788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a001fb6c-167b-497d-abd4-6a2425a18c5d · outbound

This paper cites Diffusion Models Are Real-Time Game Engines.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Diffusion Models Are Real-Time Game Engines

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.602243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3954512d-2626-4f56-b70d-85bff10e5ceb · outbound

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

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Wan: Open and Advanced Large-Scale Video Generative Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.605426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51c0d825-0d6b-49cc-b3b1-3d36c4abce7b · outbound

This paper cites arXiv preprint arXiv:2504.12369 (2025).

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval arXiv preprint arXiv:2504.12369 (2025)

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.608684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63f2037b-dfa4-421c-8dff-7cc6ac4c35ff · outbound

This paper cites DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.611750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 070cf774-429d-4527-8ac3-3d3ac9f4e7b8 · outbound

This paper cites VideoGPT: Video Generation using VQ-VAE and Transformers.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval VideoGPT: Video Generation using VQ-VAE and Transformers

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.615226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 380ebcbe-bcee-4c43-920b-fcc981c7c491 · outbound

This paper cites Learning Interactive Real-World Simulators.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Learning Interactive Real-World Simulators

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.618634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7ac7720-375c-4570-8838-c8086d939f8b · outbound

This paper cites MiniCPM-V: A GPT-4V Level MLLM on Your Phone.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.621640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2e97719-1b60-47d7-b361-26030eecb2f6 · outbound

This paper cites arXiv preprint arXiv:2504.12626 (2025).

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval arXiv preprint arXiv:2504.12626 (2025)

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.625179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6a2a3d5-53e1-45bd-b213-d0d9de257a71 · outbound

This paper cites Stereo Magnification: Learning View Synthesis using Multiplane Images.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Stereo Magnification: Learning View Synthesis using Multiplane Images

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.628244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5be92bd-a567-4562-8033-355fce2ec885 · outbound

This paper cites Advances in neural information processing systems (2019).

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Advances in neural information processing systems (2019)

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:12:18.149202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 77ac232f-da3f-453a-afa3-9b1dbe1500d8 · outbound

This paper cites Advances in neural information processing systems (2020).

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Advances in neural information processing systems (2020)

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:12:18.253056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c5935c72-52a4-4402-a5b3-4dd5f6b98ae5 · outbound

This paper cites International Conference on Learning Representations (2021).

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval International Conference on Learning Representations (2021)

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:12:18.132297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a511b16c-3105-449a-bf73-f9b0187af0c6 · outbound

This paper cites Classifier-Free Diffusion Guidance.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval Classifier-Free Diffusion Guidance

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.553177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4be7c35-fe9b-4b9b-9f88-0027e84dbf49 · outbound

This paper cites GAIA-1: A Generative World Model for Autonomous Driving.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval GAIA-1: A Generative World Model for Autonomous Driving

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.556236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c299b7d-e5e4-4399-8a2c-bc9d2752a7ab · outbound

This paper cites SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.519375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 477ec2b4-1a64-493d-8dd1-d564b4d5e006 · outbound

This paper cites ReCamMaster: Camera-Controlled Generative Rendering from A Single Video.

Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:17.515261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 71645466-37ac-464f-bbfc-e2b05e1791ba · inbound

CDP: Towards Robust Autoregressive Visuomotor Policy Learning via Causal Diffusion cites this paper.

CDP: Towards Robust Autoregressive Visuomotor Policy Learning via Causal Diffusion Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:37.627688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce1a6f6f-7ba5-45e6-896e-8926d8ebb6d2 · inbound

Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention cites this paper.

Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-03T21:59:33.245663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1ff0185-3f70-425f-a363-857e497202a6 · inbound

Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets? cites this paper.

Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets? Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-17T20:02:04.221770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dde0d32c-cd0c-4c25-a363-3914c8c1b8c7 · inbound

Vision-Language Memory for Spatial Reasoning cites this paper.

Vision-Language Memory for Spatial Reasoning Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-03T20:15:36.183372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d25cc99-4b09-45c2-b852-a67e1d1a6801 · inbound

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

WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:29:56.497402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation be1124f5-f6ad-4afc-b78c-e2f9f667a430 · inbound

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

WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-03T16:11:18.301098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b4530a8-a06c-45de-88d2-bb72ea16e39d · inbound

CustomX: Unified Character, Action, and Scene Customization in Video World Models cites this paper.

CustomX: Unified Character, Action, and Scene Customization in Video World Models Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-03T15:29:00.649927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fe4146b-c908-4b1e-93fc-c505b9f41773 · inbound

UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models cites this paper.

UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T20:36:13.810793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08ab7c33-aa47-4062-9ef4-dc1d07f78abd · inbound

SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems cites this paper.

SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:30:50.645013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f841b663-8e70-4ab6-be4e-e21884641ba2 · inbound

Evolution of Video Generative Foundations cites this paper.

Evolution of Video Generative Foundations Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 281

Resolution: verified exact; arxiv_id, observed 2026-05-11T00:05:51.270209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9845b9fb-5bfd-40eb-9c42-9c1f1c7f4afb · inbound

Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction cites this paper.

Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 94

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:50:59.685157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9bd845dc-2172-4866-a22a-5d35380d1722 · inbound

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds cites this paper.

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 84

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:45:27.154100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f4f4daf0-08e0-4e10-9967-4d9d4c0dbb9d · inbound

MultiWorld: Scalable Multi-Agent Multi-View Video World Models cites this paper.

MultiWorld: Scalable Multi-Agent Multi-View Video World Models Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-10T10:09:08.126250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 036bfba9-9d4c-4994-835c-98b4c678c78f · inbound

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

Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-15T02:33:32.128967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 90e471ac-c942-4b50-b2fc-8f0d726cf0c4 · inbound

Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players cites this paper.

Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-06-29T13:53:29.081619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 11b18680-c829-415d-8f2e-fd1bbfbe7f9a · inbound

Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models cites this paper.

Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-07-01T19:26:00.130065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 32f981f9-c8bb-43fa-8478-fc258d0b67fd · inbound

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

DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-06-28T22:42:46.789949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8a09830f-5302-4e12-9481-88fd0609a359 · inbound

MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data cites this paper.

MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-07-01T22:56:20.240121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 31c4f39c-d9b9-47c6-917c-871c65fc4759 · inbound

Echo-Memory: A Controlled Study of Memory in Action World Models cites this paper.

Echo-Memory: A Controlled Study of Memory in Action World Models Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-07-03T00:57:29.617097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 99edf4a0-a104-4d72-b421-d62804aad845 · inbound

Latent Spatial Memory for Video World Models cites this paper.

Latent Spatial Memory for Video World Models Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-07-03T01:07:30.554029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1086bb37-ba36-442f-93c6-7b29e02e7aba · inbound

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

FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 82

Resolution: verified exact; arxiv_id, observed 2026-07-03T04:37:37.482634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6d2f390b-73ae-473a-8785-784f244508a6 · inbound

PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory cites this paper.

PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-03T17:58:47.762544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7bf165a4-308a-412f-8e7b-143ac53ad726 · inbound

MemLearner: Learning to Query Context memory for Video World Models cites this paper.

MemLearner: Learning to Query Context memory for Video World Models Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 66

Resolution: verified exact; arxiv_id, observed 2026-07-01T10:25:41.877273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8e84fb0f-18ac-4197-8c51-0b5170118c76 · inbound

WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory cites this paper.

WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-07-03T14:28:31.047823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d03d8117-f012-4c67-ad39-cdec4511a596 · inbound

SlotMem: Character-Addressable Internal Memory for Narrative Long Video Generation cites this paper.

SlotMem: Character-Addressable Internal Memory for Narrative Long Video Generation Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T22:25:26.677846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b85fad5-f630-4ea3-bbe1-05ccf3774b37 · inbound

StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation cites this paper.

StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T10:37:56.086456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9f5f915-f899-4ff6-bc6a-ddad2266ea8e · inbound

Wonder: Video World Model Done Better cites this paper.

Wonder: Video World Model Done Better Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T00:52:27.986020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb90fd8c-9d3c-4522-8872-b1243849f5be · inbound

Addressable Memory for Video World Models cites this paper.

Addressable Memory for Video World Models Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval

Reference 110

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:52.053244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.