Addressable Memory for Video World Models | Paper Citation Record

Observation 91dddf21-8cd7-473a-a03a-66e3ae65cbcf · outbound

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

Addressable Memory for Video World Models Cosmos 3: Omnimodal World Models for Physical AI

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.699806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7528a57e-f4fd-4f91-afb6-ee3666f0aa7e · outbound

This paper cites Round and Round We Go! What makes Rotary Positional Encodings useful?.

Addressable Memory for Video World Models Round and Round We Go! What makes Rotary Positional Encodings useful?

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.704237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8f3e74f-95e1-41ce-9902-adf2a33ca7dc · outbound

This paper cites NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation.

Addressable Memory for Video World Models NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-08-10T05:06:56.404991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5d95ce7c-d24c-4c40-9d2a-26901cf9f142 · outbound

This paper cites Longformer: The Long-Document Transformer.

Addressable Memory for Video World Models Longformer: The Long-Document Transformer

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.711233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c47d67ba-feee-4af2-ab43-c0b46352b11f · outbound

This paper cites Variance Reduction for Expectations with Diffusion Teachers.

Addressable Memory for Video World Models Variance Reduction for Expectations with Diffusion Teachers

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-10T05:06:56.381256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d29b49ed-1b39-413e-a48e-73f7cd861f3c · outbound

This paper cites Token merging: Your ViT but faster.

Addressable Memory for Video World Models Token merging: Your ViT but faster

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.718099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4c3c9d2-ba07-46f1-9448-e4fe74264f76 · outbound

This paper cites Recurrentmemorytransformer.

Addressable Memory for Video World Models Recurrentmemorytransformer

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.721638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe7ebef4-6ad7-4617-bf71-6a922bc30e3e · outbound

This paper cites Mixture of contexts for long video generation.

Addressable Memory for Video World Models Mixture of contexts for long video generation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.724686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f8f6f4e-e63a-4705-8c2c-04581997312a · outbound

This paper cites PyramidKV: Dynamic KV cache compression based on pyramidal information funneling.

Addressable Memory for Video World Models PyramidKV: Dynamic KV cache compression based on pyramidal information funneling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.727509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66121e07-549e-442d-9b59-46cfcd0d5f47 · outbound

This paper cites Diffusion forcing: Next-token prediction meets full-sequence diffusion.

Addressable Memory for Video World Models Diffusion forcing: Next-token prediction meets full-sequence diffusion

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.730698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72569696-3196-41d8-a983-122bbe4ae8d2 · outbound

This paper cites Past- and future-informed kv cache policy with salience estimation in autoregressive video diffusion.arXiv preprint arXiv:2601.21896, 2026.

Addressable Memory for Video World Models Past- and future-informed kv cache policy with salience estimation in autoregressive video diffusion.arXiv preprint arXiv:2601.21896, 2026

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.733972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ffda83b-fb20-41b7-af03-d9bafca2f1e2 · outbound

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

Addressable Memory for Video World Models Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.737173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc86cc5f-0460-4489-9718-5e58d3fe3b02 · outbound

This paper cites Extending Context Window of Large Language Models via Positional Interpolation.

Addressable Memory for Video World Models Extending Context Window of Large Language Models via Positional Interpolation

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.740643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64a0907e-d5ff-458c-bdeb-997c74c5484a · outbound

This paper cites Context forcing: Consistent autoregressive video generation with long context.arXiv preprint arXiv:2602.06028, 2026.

Addressable Memory for Video World Models Context forcing: Consistent autoregressive video generation with long context.arXiv preprint arXiv:2602.06028, 2026

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.744146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6baf39b6-e159-4933-80e4-39e35ece8d5b · outbound

This paper cites VRAG: Learning World Models for Interactive Video Generation.

Addressable Memory for Video World Models VRAG: Learning World Models for Interactive Video Generation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.747413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 634e47f8-392f-448a-aff0-da0d87426578 · outbound

This paper cites FINCH: Prompt-guided key-value cache compression for large language models.

Addressable Memory for Video World Models FINCH: Prompt-guided key-value cache compression for large language models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.751167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbd6ee8d-35dc-491d-8390-ac9135b57c4f · outbound

This paper cites Lol: Longer than longer, scaling video generation to hour.arXiv preprint arXiv:2601.16914, 2026.

Addressable Memory for Video World Models Lol: Longer than longer, scaling video generation to hour.arXiv preprint arXiv:2601.16914, 2026

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.754420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19f274db-1514-4a23-8140-2e0eacc5720d · outbound

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

Addressable Memory for Video World Models Self-Forcing++: Towards Minute-Scale High-Quality Video Generation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.757833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40a1ac60-fc60-45cb-8c83-9d9ada4bd0cf · outbound

This paper cites Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context.

Addressable Memory for Video World Models Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.761506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea1c6f51-d05b-4b31-96ce-bb17f324f423 · outbound

This paper cites Oasis: A universe in a transformer.https://oasis-model.github.io, 2024.

Addressable Memory for Video World Models Oasis: A universe in a transformer.https://oasis-model.github.io, 2024

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.765198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f437397a-bae7-430f-8b66-5650f628291b · outbound

This paper cites WorldScore: A unified evaluation benchmark for world generation.

Addressable Memory for Video World Models WorldScore: A unified evaluation benchmark for world generation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.768499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f019ce2e-f743-4eb5-89d2-ca3c65e8642a · outbound

This paper cites A unified framework for approximating and clustering data.

Addressable Memory for Video World Models A unified framework for approximating and clustering data

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.771607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03483878-b4e0-499b-81bd-85e31a3f7192 · outbound

This paper cites Memcam: Memory- augmented camera control for consistent video generation.arXiv preprint arXiv:2603.26193, 2026.

Addressable Memory for Video World Models Memcam: Memory- augmented camera control for consistent video generation.arXiv preprint arXiv:2603.26193, 2026

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.775432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3736da0-d508-4182-964d-a81e8e3f08e5 · outbound

This paper cites Contextual Position Encoding: Learning to Count What's Important.

Addressable Memory for Video World Models Contextual Position Encoding: Learning to Count What's Important

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.778667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6f6d7e9-d04d-43b0-b90f-1d8a30699903 · outbound

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

Addressable Memory for Video World Models Genie 3: A new frontier for world models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.781948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45dba7e6-fa47-460a-947d-89942018d259 · outbound

This paper cites Mamba: Linear-time sequence modeling with selective state spaces.

Addressable Memory for Video World Models Mamba: Linear-time sequence modeling with selective state spaces

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.784638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b919a9d-fe83-4fc2-966b-325295ad91bb · outbound

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

Addressable Memory for Video World Models Long-Context Autoregressive Video Modeling with Next-Frame Prediction

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.787420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e8384ef-1551-4dec-8358-f5370072c761 · outbound

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

Addressable Memory for Video World Models Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.790280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d25dd89a-6b4d-4c51-b4aa-3497b5ac48b2 · outbound

This paper cites Recurrent world models facilitate policy evolution.

Addressable Memory for Video World Models Recurrent world models facilitate policy evolution

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.793059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52bc8748-c20a-4621-be85-6e16b6584354 · outbound

This paper cites Mastering diverse control tasks through world models.Nature, 640:647–653, 2025.

Addressable Memory for Video World Models Mastering diverse control tasks through world models.Nature, 640:647–653, 2025

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.795696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3ed0f70-18c3-4768-826a-8056568bb32c · outbound

This paper cites A$^2$ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization.

Addressable Memory for Video World Models A$^2$ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-10T05:06:55.948862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 613f3692-f94d-4567-af19-01e552b5d47d · outbound

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

Addressable Memory for Video World Models Matrix-game 2.0: An open-source real-time and streaming interactive world model

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.801289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ecc7a16-0e7d-4c3a-91e9-62594a23f9c8 · outbound

This paper cites StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text.

Addressable Memory for Video World Models StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.804256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22778dbf-972b-4f61-a063-b0dcb288ae08 · outbound

This paper cites Rotary Position Embedding for Vision Transformer.

Addressable Memory for Video World Models Rotary Position Embedding for Vision Transformer

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.807153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5056227-bf25-4709-829e-8880f2b2cb0b · outbound

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

Addressable Memory for Video World Models RELIC: Interactive video world model with long-horizon memory.arXiv preprint arXiv:2512.04040, 2025

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.810004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfa75425-95e9-4cc8-95a2-268522f777dc · outbound

This paper cites Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization.

Addressable Memory for Video World Models Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.812677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 578fb85c-1927-4c6b-b32e-f9ebd635c0e0 · outbound

This paper cites Vid2World: Crafting video diffusion models to interactive world models.

Addressable Memory for Video World Models Vid2World: Crafting video diffusion models to interactive world models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.815893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7b5482e-334b-40b0-9d81-117133e1dfaa · outbound

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

Addressable Memory for Video World Models Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.818857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c161ec1f-f0c5-4703-939c-b9dcdc7b853a · outbound

This paper cites Block-Recurrent Transformers.

Addressable Memory for Video World Models Block-Recurrent Transformers

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.822520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee220334-8634-4eca-a680-40f0eee0b7e0 · outbound

This paper cites Transformers are RNNs: Fast autore- gressive transformers with linear attention.

Addressable Memory for Video World Models Transformers are RNNs: Fast autore- gressive transformers with linear attention

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.825902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f2611ed-07eb-4757-83a6-b167dacfe868 · outbound

This paper cites The Impact of Positional Encoding on Length Generalization in Transformers.

Addressable Memory for Video World Models The Impact of Positional Encoding on Length Generalization in Transformers

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.829142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1962a171-d7bb-4c8a-979f-14fbaf6a2575 · outbound

This paper cites Jay Kuo, and Peter A.

Addressable Memory for Video World Models Jay Kuo, and Peter A

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.832659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b421cdb8-9622-4ef8-b681-bbcdd47326a1 · outbound

This paper cites Robust nonnegative matrix factorization using l21-norm.

Addressable Memory for Video World Models Robust nonnegative matrix factorization using l21-norm

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.835834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88b6d623-057b-4204-9a35-ba8d372a4def · outbound

This paper cites Lee and H.

Addressable Memory for Video World Models Lee and H

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.839051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 383659e2-0643-4ac9-824d-9b509bfdda14 · outbound

This paper cites Understanding and Improving Length Generalization in Hierarchical Sparse Attention Models.

Addressable Memory for Video World Models Understanding and Improving Length Generalization in Hierarchical Sparse Attention Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.842394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 905facbf-630e-4981-9740-9d27a14b048c · outbound

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

Addressable Memory for Video World Models Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.845827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6723b123-bdad-46d4-bdbb-9b27cc723b67 · outbound

This paper cites Train short, inference long: Training-free horizon extension for autoregressive video generation.arXiv preprint arXiv:2602.14027, 2026.

Addressable Memory for Video World Models Train short, inference long: Training-free horizon extension for autoregressive video generation.arXiv preprint arXiv:2602.14027, 2026

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.849683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e76c29e-770c-49e0-a061-6c12c4a6f8b7 · outbound

This paper cites PackCache: A training-free acceleration method for unified autoregressive video generation via compact KV-cache.arXiv preprint arXiv:2601.04359, 2026.

Addressable Memory for Video World Models PackCache: A training-free acceleration method for unified autoregressive video generation via compact KV-cache.arXiv preprint arXiv:2601.04359, 2026

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.853092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02f61ce5-176a-42d0-b586-cf9e55dc44fb · outbound

This paper cites Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation.

Addressable Memory for Video World Models Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.856531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb0d9e24-d699-45a6-ac54-f152584b9165 · outbound

This paper cites Cameras as relative positional encoding.

Addressable Memory for Video World Models Cameras as relative positional encoding

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.860251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de891703-bf83-4994-a4e0-ab76812214f2 · outbound

This paper cites VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory.

Addressable Memory for Video World Models VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.863744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32182234-1248-4cdc-bd14-87e95f0bce03 · outbound

This paper cites Stable video infinity: Infinite-length video generation with error recycling.arXiv preprint arXiv:2510.09212, 2025.

Addressable Memory for Video World Models Stable video infinity: Infinite-length video generation with error recycling.arXiv preprint arXiv:2510.09212, 2025

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.866780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94be4b49-5b3b-4c47-9e14-b5e75d728040 · outbound

This paper cites SnapKV: LLM Knows What You are Looking for Before Generation.

Addressable Memory for Video World Models SnapKV: LLM Knows What You are Looking for Before Generation

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.869780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 562e98e3-2e84-4069-9556-a10cd7445178 · outbound

This paper cites LoopNav: Benchmarking Spatial Consistency in World Models.

Addressable Memory for Video World Models LoopNav: Benchmarking Spatial Consistency in World Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.873150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9329cf75-9c5e-4d92-8c27-a520c49578a8 · outbound

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

Addressable Memory for Video World Models Rolling Forcing: Autoregressive Long Video Diffusion in Real Time

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.876309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e2835f8-be93-4c5a-acbf-5a5e80310f76 · outbound

This paper cites KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache.

Addressable Memory for Video World Models KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.879558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f941b651-7c6a-4d9e-be46-daeada6be491 · outbound

This paper cites JacNet: Learning functions with structured Jacobians.

Addressable Memory for Video World Models JacNet: Learning functions with structured Jacobians

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.882731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 552639f3-182c-4464-b22a-91d52fc77809 · outbound

This paper cites Task Selection for AutoML System Evaluation.

Addressable Memory for Video World Models Task Selection for AutoML System Evaluation

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.885612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9525ee8d-21fe-4950-9617-1cc7aa81e211 · outbound

This paper cites ATT3D: Amortized text-to-3D object synthesis.

Addressable Memory for Video World Models ATT3D: Amortized text-to-3D object synthesis

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.888849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 710479b7-ebba-4f2e-a7f6-96d07dceb05c · outbound

This paper cites Flow caching for autoregressive video generation.arXiv preprint arXiv:2602.10825, 2026.

Addressable Memory for Video World Models Flow caching for autoregressive video generation.arXiv preprint arXiv:2602.10825, 2026

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.891520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db742686-b706-49a0-b81c-697c9cdfe559 · outbound

This paper cites TriAttention: Efficient Long Reasoning with Trigonometric KV Compression.

Addressable Memory for Video World Models TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.894378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a383fa8-5c2d-4d8f-aa09-a6fae5d36853 · outbound

This paper cites PackForcing: Short video training suffices for long video sampling and long context inference.arXiv preprint arXiv:2603.25730, 2026.

Addressable Memory for Video World Models PackForcing: Short video training suffices for long video sampling and long context inference.arXiv preprint arXiv:2603.25730, 2026

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.897344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d4e19e2-0b8a-485f-8a01-00bd839a6c22 · outbound

This paper cites Landmark Attention: Random-Access Infinite Context Length for Transformers.

Addressable Memory for Video World Models Landmark Attention: Random-Access Infinite Context Length for Transformers

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.900992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a788e2bf-48d1-495e-8bb0-e2821e928d0a · outbound

This paper cites Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention.

Addressable Memory for Video World Models Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.904460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7d0633f-ef88-46a1-8be5-ae07b9b18d9f · outbound

This paper cites KVPress: A compression library for transformer KV caches.https://github.com/NVIDIA/kvpress, 2024.

Addressable Memory for Video World Models KVPress: A compression library for transformer KV caches.https://github.com/NVIDIA/kvpress, 2024

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.908045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 866ad531-9c4e-4db8-952d-3b7609f609b1 · outbound

This paper cites WorldPack: Dynamic Frame Compression for Long-context Video World Modeling.

Addressable Memory for Video World Models WorldPack: Dynamic Frame Compression for Long-context Video World Modeling

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.911350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e412048b-faec-4d7f-921a-bd699312e06b · outbound

This paper cites YaRN: Efficient Context Window Extension of Large Language Models.

Addressable Memory for Video World Models YaRN: Efficient Context Window Extension of Large Language Models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.914934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56cb717b-9da6-449f-b17c-be8f860716db · outbound

This paper cites Long-context state-space video world models.

Addressable Memory for Video World Models Long-context state-space video world models

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.918609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79e8cde5-5f8c-425a-ac7c-ea83f84bc309 · outbound

This paper cites Smith, and Mike Lewis.

Addressable Memory for Video World Models Smith, and Mike Lewis

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.921685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1443c73a-8bf6-4d74-96cb-d73da9750e97 · outbound

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

Addressable Memory for Video World Models Learning transferable visual models from natural language supervision

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.924869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 930ccfba-f3f9-4bc8-a89a-01a40f5b13ea · outbound

This paper cites Rae, Anna Potapenko, Siddhant M.

Addressable Memory for Video World Models Rae, Anna Potapenko, Siddhant M

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.928398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0aefec3a-6ed3-4e7c-b7a2-edc059d454c3 · outbound

This paper cites Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond.

Addressable Memory for Video World Models Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.931568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53088a46-4a55-42aa-bd86-9a3623203d8b · outbound

This paper cites Fast autoregressive video diffusion and world models with temporal cache compression and sparse attention.arXiv preprint arXiv:2602.01801, 2026.

Addressable Memory for Video World Models Fast autoregressive video diffusion and world models with temporal cache compression and sparse attention.arXiv preprint arXiv:2602.01801, 2026

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.935154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97763b1a-405f-4127-8696-1a6dd8e498d4 · outbound

This paper cites LongRoPE2: Near-lossless LLM context window scaling.

Addressable Memory for Video World Models LongRoPE2: Near-lossless LLM context window scaling

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.938252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 219c96eb-d2b2-44d7-ad62-c753a18d971a · outbound

This paper cites History-Guided Video Diffusion.

Addressable Memory for Video World Models History-Guided Video Diffusion

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.941856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8722fe6f-b7dc-4e9d-9be1-807e6a546a3b · outbound

This paper cites Multi-student Diffusion Distillation for Better One-step Generators.

Addressable Memory for Video World Models Multi-student Diffusion Distillation for Better One-step Generators

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.945440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb5f8c81-180b-4a75-aa0e-09ae3ecb1078 · outbound

This paper cites Composition of memory experts for diffusion world models.

Addressable Memory for Video World Models Composition of memory experts for diffusion world models

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.948895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22efbd61-f2aa-4b2c-b95f-ab977bbe44dc · outbound

This paper cites RoFormer: Enhanced transformer with rotary position embedding.Neurocomputing, 568:127063, 2024.

Addressable Memory for Video World Models RoFormer: Enhanced transformer with rotary position embedding.Neurocomputing, 568:127063, 2024

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.951728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ced6be5-c8ec-446c-b8be-33feb282cf57 · outbound

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

Addressable Memory for Video World Models WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.954581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcb9b390-15dd-4de5-96cd-15fd81384c7e · outbound

This paper cites Learning to (learn at test time): RNNs with expressive hidden states.

Addressable Memory for Video World Models Learning to (learn at test time): RNNs with expressive hidden states

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.957468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e61fcb2-60a9-41fe-b00d-cac9563f47a0 · outbound

This paper cites A Length-Extrapolatable Transformer.

Addressable Memory for Video World Models A Length-Extrapolatable Transformer

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.960146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 924e2455-efe2-417e-a089-a8c83e870d69 · outbound

This paper cites Advancing Open-source World Models.

Addressable Memory for Video World Models Advancing Open-source World Models

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.963230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df4eb73f-d4b9-4344-aaf1-80db9dbf98d8 · outbound

This paper cites KeepKV: Achieving periodic lossless KV cache compression for efficient LLM inference.

Addressable Memory for Video World Models KeepKV: Achieving periodic lossless KV cache compression for efficient LLM inference

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.966146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5e1beab-7c38-4a85-8e41-2c2aa5a3315e · outbound

This paper cites Diffusion models are real-time game engines.

Addressable Memory for Video World Models Diffusion models are real-time game engines

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.968987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6859384-b193-442f-9602-689ba0412c20 · outbound

This paper cites an unresolved cited work.

Addressable Memory for Video World Models Unresolved cited work

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.971985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 878363cd-acd2-4c73-8f18-0e636e4ee5fd · outbound

This paper cites Fast transformers with clustered attention.

Addressable Memory for Video World Models Fast transformers with clustered attention

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.974974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 140f24d8-7ecf-4516-941f-a07656c5dd05 · outbound

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

Addressable Memory for Video World Models Wan: Open and Advanced Large-Scale Video Generative Models

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.977937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1dd92ba-2805-4c71-b625-635ae12b24d6 · outbound

This paper cites When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training.

Addressable Memory for Video World Models When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.980988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50d18257-3043-4ec0-a6c0-2fd075c40d31 · outbound

This paper cites Linformer: Self-Attention with Linear Complexity.

Addressable Memory for Video World Models Linformer: Self-Attention with Linear Complexity

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.983926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44e33ebc-3b39-4e69-bb25-391ef2aca2a3 · outbound

This paper cites LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models.

Addressable Memory for Video World Models LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.987484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81426352-910e-48fa-85ad-b2c179e619bd · outbound

This paper cites Bovik, Hamid R.

Addressable Memory for Video World Models Bovik, Hamid R

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.991027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c11f2c74-cb6f-4071-8458-ab4a9998adef · outbound

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

Addressable Memory for Video World Models Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.994602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf6b92ab-aa87-4a59-8ff8-96e0a87c7b1b · outbound

This paper cites VideoRoPE: What Makes for Good Video Rotary Position Embedding?.

Addressable Memory for Video World Models VideoRoPE: What Makes for Good Video Rotary Position Embedding?

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:51.998314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45019931-55ad-42dd-9581-576a360adc4c · outbound

This paper cites Video World Models with Long-term Spatial Memory.

Addressable Memory for Video World Models Video World Models with Long-term Spatial Memory

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:52.002085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a0e4fff-a6e0-4dda-822e-60fcaf2c95d5 · outbound

This paper cites Corgi: Cached memory guided video generation.

Addressable Memory for Video World Models Corgi: Cached memory guided video generation

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:52.005790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7563504e-80c6-4111-a504-757d267ce84f · outbound

This paper cites Motion attribution for video generation.

Addressable Memory for Video World Models Motion attribution for video generation

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:52.009046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dff48ed-dcf2-486a-93ee-30cedd49be66 · outbound

This paper cites Rabe, DeLesley Hutchins, and Christian Szegedy.

Addressable Memory for Video World Models Rabe, DeLesley Hutchins, and Christian Szegedy

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:52.012470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc0d617b-5107-4687-b585-3c4dbbe1e106 · outbound

This paper cites Efficient streaming language models with attention sinks.

Addressable Memory for Video World Models Efficient streaming language models with attention sinks

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:52.015881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7be016b-15e7-4e9c-a3dd-2d7e75e1965e · outbound

This paper cites DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads.

Addressable Memory for Video World Models DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:52.019067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9d48c43-e88a-44e5-9b91-b8019f21f757 · outbound

This paper cites WorldMem: Long-term consistent world simulation with memory.

Addressable Memory for Video World Models WorldMem: Long-term consistent world simulation with memory

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-10T05:06:52.022607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers