WOVEN: Weaving Visual World Modeling into Multimodal LLMs

arXiv:2610.12417 · cs.CV, cs.CL, cs.LG · Submitted 2026-10-08 · Read on arXiv

cs.CV, cs.CL, cs.LG

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/nvidia-cosmos/cosmos-predict2

Terminology

• Benchmark — 181× in this paper · explained in 2 episodes
• Accuracy — 171× in this paper · explained in 1 episode
• GRPO — 49× in this paper · explained in 6 episodes
• Robustness — 21× in this paper · explained in 5 episodes
• World Model — 17× in this paper · explained in 7 episodes
• Core — 13× in this paper · explained in 2 episodes
• Fine-Tuning — 9× in this paper · explained in 5 episodes
• Consistency — 7× in this paper · explained in 3 episodes
• Actor — 6× in this paper · explained in 3 episodes
• Generative Model — 6× in this paper · explained in 2 episodes
• Temporal Reasoning — 6× in this paper · explained in 2 episodes
• Benchmarking — 5× in this paper · explained in 3 episodes
• Downstream Tasks — 5× in this paper · explained in 2 episodes
• AUC — 4× in this paper · explained in 2 episodes
• Cosine Similarity — 4× in this paper · explained in 3 episodes
• Failure Modes — 4× in this paper · explained in 3 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Generative Models — 4× in this paper · explained in 2 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 3× in this paper
• Decoupling — 3× in this paper · explained in 2 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Zero-Shot Transfer — 3× in this paper · explained in 4 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Calibration — 2× in this paper · explained in 7 episodes
• Causal Reasoning — 2× in this paper · explained in 2 episodes
• Diffusion Model — 2× in this paper · explained in 8 episodes
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Fingerprinting — 2× in this paper · explained in 2 episodes
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Affordance — 1× in this paper · explained in 1 episode
• Agent Core — 1× in this paper · explained in 2 episodes
• CVF International Conference on Computer Vision — 1× in this paper
• Causal Inference — 1× in this paper · explained in 4 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Linear probe — 1× in this paper · explained in 2 episodes
• Physical Constraints — 1× in this paper · explained in 7 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Sample Efficiency — 1× in this paper · explained in 4 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments
• CG-World: A Large-Scale World-State Dataset and Protocol for World Models
• WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planning
• Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective
• PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding
• Video Language Planning
• 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding
• Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World
• DreamGen: Unlocking Generalization in Robot Learning through Video World Models
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models
• MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
• Scaling GUI Agents with Visual State Transitions
• Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain
• CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning
• Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
• Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models