LongLive-RAG formulates long video generation as retrieval-augmented generation by treating self-generated latents as a dynamic searchable history and adding a Window Temporal Delta Loss for better retrieval.
hub
Infinite-World: Scaling interactive world models to 1000-frame horizons via pose-free hierarchical memory
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
years
2026 13roles
background 4polarities
background 4representative citing papers
MBench is a new benchmark that quantifies long-term memory in video world models via three hierarchical consistency dimensions evaluated on curated real videos.
WBench is a benchmark with 289 test cases and 1,058 turns for evaluating interactive world models using 22 automated metrics validated against human judgments.
Incantation is the first video world model to use per-frame natural language conditioning for simultaneous multi-entity control and concept-level cross-entity transfer in interactive video generation.
MultiWorld is a scalable framework for multi-agent multi-view video world models that improves controllability and consistency over single-agent baselines in game and robot tasks.
GIM-World adds a camera-queryable geometry distillation head and pruning rule to implicit memory in video world models, claiming better long-horizon geometric consistency on the MIND benchmark than explicit and implicit baselines.
DAWN couples a world predictor with a world-conditioned action denoiser in latent space so that each refines the other recursively, yielding strong planning and safety results on autonomous driving benchmarks.
INSPATIO-WORLD is a real-time framework for high-fidelity 4D scene generation and navigation from monocular videos via STAR architecture with implicit caching, explicit geometric constraints, and distribution-matching distillation.
SANA-WM is a 2.6B-parameter efficient world model that synthesizes minute-scale 720p videos with 6-DoF camera control, trained on 213K public clips in 15 days on 64 H100s and runnable on single GPUs at 36x higher throughput than prior open baselines.
A preview system demonstrates real-time controllable world modeling at 14-15 FPS on RTX 4090 by adapting open video backbones with action pathways for keyboard/mouse control and multimodal features.
Coherence-first rendering with 15 FPS anchors plus FSR4 upsampling to 30 FPS preserves scene geometry and identity longer than native 30 FPS generation across tested forest, sword, desert, and snow scenes, with LPIPS favoring the coherence branch.
This survey reviews trends, challenges, benchmarks, and future directions in action-conditioned interactive world modeling for video and 3D generation.