ISPA reduces KV cache size by up to 50% in AR video models by transitioning layers to local attention and applying instance-specific least-squares weight modulation to compensate for lost history.
hub Canonical reference
Advancing Open-source World Models
Canonical reference. 79% of citing Pith papers cite this work as background.
60
Pith papers citing it
Background
79% of classified citations
abstract
We present LingBot-World, an open-sourced world simulator stemming from video generation. Positioned as a top-tier world model, LingBot-World offers the following features. (1) It maintains high fidelity and robust dynamics in a broad spectrum of environments, including realism, scientific contexts, cartoon styles, and beyond. (2) It enables a minute-level horizon while preserving contextual consistency over time, which is also known as "long-term memory". (3) It supports real-time interactivity, achieving a latency of under 1 second when producing 16 frames per second. We provide public access to the code and model in an effort to narrow the divide between open-source and closed-source technologies. We believe our release will empower the community with practical applications across areas like content creation, gaming, and robot learning.
hub tools
citation-role summary
background 12
baseline 2
citation-polarity summary
years
2026 60representative citing papers
None of ten tested video-generation models reliably remembers objects after occlusion in dynamic scenes; static-camera videos inflate consistency scores.
PhysEditWorld is a new dataset of over 60 million frames from 12 UE5 cinematic scenes with synchronized multimodal signals and explicit gravity labels, built via replay to support physics-editable world models.
VSTAT benchmark shows state-of-the-art MLLMs perform far below humans and only modestly above answer-prior baselines on visual state tracking, failing at visual perception despite correct textual reasoning.
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.
Per-frame natural-language action prompts enable simultaneous multi-entity control and cross-entity action transfer in interactive video world models, outperforming discrete action-index interfaces.
Being-H0.7 adds future-aware latent reasoning to direct VLA policies via dual-branch alignment on latent queries, matching world-model benefits at VLA efficiency.
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.
DreamDojo is a foundation world model pretrained on the largest human video dataset to date that uses continuous latent actions to transfer interaction knowledge and achieves controllable physics simulation after robot post-training.
WCog-VLA couples Game-CoT semantic reasoning with an aligned decoupled diffusion transformer to generate joint multi-agent trajectories and reaches 92.9 PDMS on NAVSIM.
EO-WM is a diffusion transformer that adds physically separated baseline-anomaly and cumulative-stress conditioning to probabilistic EO forecasting and validates it on two new weather-response benchmarks, reporting 5.63% and 7.80% relative gains on NDVI decline metrics.
Causal-rCM unifies teacher-forcing and self-forcing distillation for autoregressive video diffusion, delivering a 2-step model with VBench-T2V score 84.63 and enabling interactive world models on Cosmos 3 using only synthetic data.
CaR uses attention with viewpoint positional encoding and context compression for flexible memory retrieval in video world models, backed by a new SceneFly dataset, and reports SOTA results with open-domain generalization.
Current world models fail to evolve internal state when unobserved and instead resume scenes at the last observed state, as diagnosed by the new WRBench benchmark across 23 models and 9600 videos.
ActWorld extends navigation-centric world models to support mid-rollout object interactions via chunk-autoregressive generation, action-aware memory routing, and a persistent memory bank, backed by a 100K annotated interaction dataset.
MoVerse generates real-time interactive video world models from single narrow-FOV images via panoramic diffusion expansion, Gaussian scaffold lifting, and distillation of a bidirectional diffusion teacher into a causal autoregressive renderer.
A controlled study finds that block-wise state-space recurrence outperforms other memory designs for open-domain scene return in action-conditioned video models, and that standard replay metrics do not adequately measure memory quality.
Prisma-World is a diffusion-based multi-agent video model that uses joint full-attention, multi-agent RoPE, and relative camera geometry injection plus curriculum training to produce consistent cross-view videos from flexible agent counts.
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.
SCOPE adds per-pixel action conditioning to pretrained video diffusion models and releases the CrossFPS multi-game dataset to support cross-game FPS world model simulation with zero-shot transfer.
A curiosity-based 3D exploration policy that pairs persistent online 3D reconstruction with episodic sequence modeling over RGB to outperform active-mapping baselines on HM3D and transfer zero-shot to Gibson and synthetic worlds.
WorldKV enables persistent world memory in autoregressive video diffusion models by selectively retrieving and compressing KV-cache chunks, matching full-cache fidelity at roughly twice the throughput without training.
FlowLong generates videos several times longer than native model windows by blending adjacent predictions with Tweedie matching to enforce manifold and temporal consistency while using stochastic noise injection early and deterministic sampling later.
citing papers explorer
-
Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption
ISPA reduces KV cache size by up to 50% in AR video models by transitioning layers to local attention and applying instance-specific least-squares weight modulation to compensate for lost history.
-
MemoBench: Benchmarking World Modeling in Dynamically Changing Environments
None of ten tested video-generation models reliably remembers objects after occlusion in dynamic scenes; static-camera videos inflate consistency scores.
-
PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models
PhysEditWorld is a new dataset of over 60 million frames from 12 UE5 cinematic scenes with synchronized multimodal signals and explicit gravity labels, built via replay to support physics-editable world models.
-
Benchmarking Visual State Tracking in Multimodal Video Understanding
VSTAT benchmark shows state-of-the-art MLLMs perform far below humans and only modestly above answer-prior baselines on visual state tracking, failing at visual perception despite correct textual reasoning.
-
MBench: A Comprehensive Benchmark on Memory Capability for Video World Models
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: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation
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: Natural Language as the Action Interface for Multi-Entity Video World Models
Per-frame natural-language action prompts enable simultaneous multi-entity control and cross-entity action transfer in interactive video world models, outperforming discrete action-index interfaces.
-
Being-H0.7: A Latent World-Action Model from Egocentric Videos
Being-H0.7 adds future-aware latent reasoning to direct VLA policies via dual-branch alignment on latent queries, matching world-model benefits at VLA efficiency.
-
MultiWorld: Scalable Multi-Agent Multi-View Video World Models
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.
-
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
DreamDojo is a foundation world model pretrained on the largest human video dataset to date that uses continuous latent actions to transfer interaction knowledge and achieves controllable physics simulation after robot post-training.
-
WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving
WCog-VLA couples Game-CoT semantic reasoning with an aligned decoupled diffusion transformer to generate joint multi-agent trajectories and reaches 92.9 PDMS on NAVSIM.
-
EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting
EO-WM is a diffusion transformer that adds physically separated baseline-anomaly and cumulative-stress conditioning to probabilistic EO forecasting and validates it on two new weather-response benchmarks, reporting 5.63% and 7.80% relative gains on NDVI decline metrics.
-
Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models
Causal-rCM unifies teacher-forcing and self-forcing distillation for autoregressive video diffusion, delivering a 2-step model with VBench-T2V score 84.63 and enabling interactive world models on Cosmos 3 using only synthetic data.
-
Compression and Retrieval: Implicit Memory Retrieval for Video World Models
CaR uses attention with viewpoint positional encoding and context compression for flexible memory retrieval in video world models, backed by a new SceneFly dataset, and reports SOTA results with open-domain generalization.
-
Current World Models Lack a Persistent State Core
Current world models fail to evolve internal state when unobserved and instead resume scenes at the last observed state, as diagnosed by the new WRBench benchmark across 23 models and 9600 videos.
-
ActWorld: From Explorable to Interactive World Model via Action-Aware Memory
ActWorld extends navigation-centric world models to support mid-rollout object interactions via chunk-autoregressive generation, action-aware memory routing, and a persistent memory bank, backed by a 100K annotated interaction dataset.
-
MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold
MoVerse generates real-time interactive video world models from single narrow-FOV images via panoramic diffusion expansion, Gaussian scaffold lifting, and distillation of a bidirectional diffusion teacher into a causal autoregressive renderer.
-
Echo-Memory: A Controlled Study of Memory in Action World Models
A controlled study finds that block-wise state-space recurrence outperforms other memory designs for open-domain scene return in action-conditioned video models, and that standard replay metrics do not adequately measure memory quality.
-
Prisma-World: Camera-Controllable Multi-Agent Video World Model
Prisma-World is a diffusion-based multi-agent video model that uses joint full-attention, multi-agent RoPE, and relative camera geometry injection plus curriculum training to produce consistent cross-view videos from flexible agent counts.
-
Geometry-Aware Implicit Memory for Video World Models
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.
-
SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models
SCOPE adds per-pixel action conditioning to pretrained video diffusion models and releases the CrossFPS multi-game dataset to support cross-game FPS world model simulation with zero-shot transfer.
-
Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration
A curiosity-based 3D exploration policy that pairs persistent online 3D reconstruction with episodic sequence modeling over RGB to outperform active-mapping baselines on HM3D and transfer zero-shot to Gibson and synthetic worlds.
-
WorldKV: Efficient World Memory with World Retrieval and Compression
WorldKV enables persistent world memory in autoregressive video diffusion models by selectively retrieving and compressing KV-cache chunks, matching full-cache fidelity at roughly twice the throughput without training.
-
FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching
FlowLong generates videos several times longer than native model windows by blending adjacent predictions with Tweedie matching to enforce manifold and temporal consistency while using stochastic noise injection early and deterministic sampling later.
-
GeoWorld-VLM: Geometry from World Models for Vision-Language Models
GeoWorld-VLM aligns VLM image features with intermediate representations from camera-conditioned world models via fine-tuning only the encoder and projector, yielding ~4% gains on What'sUp and VSR spatial benchmarks across two VLM backbones.
-
HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation
HorizonDrive is a new anti-drifting autoregressive training and distillation method that enables minute-scale stable driving video rollouts by making the teacher model rollout-capable via scheduled rollout recovery and teacher rollout DMD.
-
ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control
ExoActor uses exocentric video generation to implicitly model robot-environment-object interactions and converts the resulting videos into task-conditioned humanoid control sequences.
-
Infrastructure-Centric World Models: Bridging Temporal Depth and Spatial Breadth for Roadside Perception
Infrastructure-centric world models use roadside sensors' temporal depth to complement vehicle spatial breadth for better traffic simulation and prediction.
-
Human Cognition in Machines: A Unified Perspective of World Models
The paper introduces a unified framework for world models that fully incorporates all cognitive functions from Cognitive Architecture Theory, highlights under-researched areas in motivation and meta-cognition, and proposes Epistemic World Models as a new category for scientific discovery agents.
-
From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation
Interpolating only the video frames between synchronized exo and ego clips already turns discontinuous cross-view generation into continuous sequence modeling and measurably improves diffusion-based Exo2Ego synthesis.
-
INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling
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.
-
SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing
SpatialEdit provides a benchmark, large synthetic dataset, and baseline model for precise object and camera spatial manipulations in images, with the model beating priors on spatial editing.
-
UNICA: A Unified Neural Framework for Controllable 3D Avatars
UNICA unifies motion planning, rigging, physical simulation, and rendering into a single skeleton-free neural framework that produces next-frame 3D avatar geometry from action inputs and renders it with Gaussian splatting.
-
Native Video-Action Pretraining for Generalizable Robot Control
A video-action foundation model pretrained natively with a causal diffusion transformer and semantic visual-action tokenizer reports improved few-shot robot manipulation and 225 Hz asynchronous closed-loop control.
-
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
LingBot-Video is an open-source MoE video foundation model for embodied intelligence that scales to 120B parameters, integrates robot data, and uses multi-dimensional RL to improve physical plausibility.
-
Infinite Worlds with Versatile Interactions
An open-source causal video world model sustains hour-long, 720p/60fps interactive generation without visual drift, paired with a VLM-based director-pilot agentic harness for rich, open-ended interaction.
-
WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory
A video world model framework that uses LLM-orchestrated 3D trajectories as control signals for generation to achieve persistent dynamic object memory and viewpoint freedom.
-
Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control
A decoupled-control autoregressive video model using Fast-Slow Memory training, dynamic projection, and staged camera control to produce stable long-horizon outputs with human and viewpoint guidance.
-
WorldOlympiad: Can Your World Model Survive a Triathlon?
WorldOlympiad is a new benchmark decomposing world-model evaluation into physical, geometry, and interaction tracks using segmentation, MLLM judges, Gaussian splatting, and action prompts on diverse scenarios.
-
AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
AnchorWorld proposes a simulation framework that adds exogenous viewpoint supervision for full-body grounding and anchor-view text customization for dynamic world evolution in egocentric settings.
-
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
OmniDreams turns the Cosmos video-diffusion model into a real-time, action-conditioned driving simulator and shows that its internal representations can be fine-tuned into a competitive driving policy.
-
EigeNet: Geometry-Informed Multi-Modal Learning for Few-shot Novel View RIR Prediction
EigeNet applies a cross-view alternate-attention transformer with geometry modulation for few-shot novel-view RIR prediction, reporting SOTA results on simulated and real data.
-
PhyWorld: Physics-Faithful World Model for Video Generation
PhyWorld improves temporal consistency and physical plausibility in video world models via flow matching fine-tuning followed by DPO on physics preference pairs, with reported gains on VBench and a custom physical-faithfulness benchmark.
-
Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
Focused Forcing is a training-free per-frame KV selection method that combines attention scores with diversity metrics and head-importance estimation to accelerate autoregressive video diffusion up to 1.48x while improving quality.
-
Nano World Models: A Minimalist Implementation of Future Video Prediction
Nano World Models supplies a unified minimalist codebase and evaluation framework for studying diffusion forcing in video prediction across control, games, and robot domains.
-
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
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.
-
OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence
OrbiSim builds a differentiable physics engine from world models to support gradient-based policy optimization and contact modeling in robotics.
-
Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models
Action-state consistency in World Action Models distinguishes successful from failed imagined futures and supports value-free selection of better rollouts via consensus among predictions.
-
Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms
In twisted bilayer nodal d-wave superconductors, interlayer hopping creates nodes on the C2 axis and Bogoliubov flat bands when the single-layer Berry connection is parallel to that axis.
-
InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model
InSpatio-WorldFM is a frame-independent generative model that uses explicit 3D anchors and spatial memory to deliver real-time multi-view consistent spatial intelligence via a three-stage training pipeline from pretrained diffusion models.