World-in-Context: Interactive Video World Modeling with In-Context Conditioning
Summary
World-in-Context introduces an interactive video world modeling framework that unifies view, action, and camera controls as explicit tokens within a shared self-attention space via In-Context Conditioning, along with Interaction-Transport RoPE for temporal continuity. Its 5B model matches the navigation performance of the 22B EchoWM on WBench while achieving a 93.8% perspective-switching success rate versus 18.8% for existing 5B baselines.
View Cached Full Text
Cached at: 10/28/26, 01:39 AM
Paper page - World-in-Context: Interactive Video World Modeling with In-Context Conditioning
Source: https://huggingface.co/papers/2610.33169
Abstract
World-in-Context unifies view, action, and camera controls via explicit tokens and interaction-aware positional encoding to improve interactive video generation and navigation.
Interactive video world models require coordinated control over viewing perspectives, character actions, and camera motion. Existing methods typically leave view modes implicit in text captions, conflate action with camera motion, and inject controls through fragmented architectural pathways that capture interdependencies only indirectly. In this work, we present World-in-Context, an interactive world modeling framework powered byIn-Context Conditioning(ICC). Rather than relying on specialized conditioning pathways, World-in-Context unifies view, action, and camera controls into explicit tokens contextualized directly within a sharedself-attentionspace. Our formulation reveals that (i) explicitview tokensdisentangle conflicting dynamics and unlock emergent view switching from single-view data, while (ii) action and camera inputs play complementary roles in governing local responsiveness and global stability. To preserve temporal continuity across execution intervals, we further introduceInteraction-Transport RoPE(IT-RoPE), parameterizing temporal attention with accumulated control transitions. On WBench, World-in-Context-5B achieves navigation performance on par with 22B EchoWM (81.5 vs. 81.6) and attains a 93.8% perspective-switching success rate, substantially outperforming existing 5B baselines (18.8%). Controlled analyses further demonstrate compounding advantages of World-in-Context under richer conditioning mixtures, favorable data efficiency, and natural applicability tocausal rollouts.
View arXiv pageView PDFProject pageGitHub23Add to collection
Get this paper in your agent:
hf papers read 2610\.33169
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2610.33169 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2610.33169 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2610.33169 in a Space README.md to link it from this page.
Collections including this paper2
Similar Articles
In-Context World Modeling for Robotic Control
This paper introduces In-Context World Modeling (ICWM), a framework that enables robot policies to infer system variables from self-generated interactions, allowing adaptation to novel configurations without parameter updates by treating system identification as an in-context adaptation problem. It outperforms standard VLA baselines on novel camera viewpoints in simulation and real-world experiments.
World in World: Explore the World with World Models
The paper presents World in World, a training-free interface that enables flexible camera and time control in frozen autoregressive video world models by using correspondence-guided queries and evidence-wise attention guidance.
Wonder: Video World Model Done Better
Wonder is a general-purpose video world model that enables real-time, camera-controllable world exploration from an image or conditional video. It introduces camera conditioning via dense coordinate fields, a sparse attention memory mechanism, and techniques to improve distillation, allowing minute-scale video generation at 16 FPS.
WorldAttention: An Efficient Attention Architecture for Interactive Video World Models
WorldAttention proposes an efficient attention architecture with Hybrid Sparse Attention and Hierarchical KV Cache for interactive video world models, achieving state-of-the-art performance on benchmarks like VBench-Long and InterVBench.
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
WorldCrafter is a video world model that learns a camera-queryable implicit 3D-aware memory for consistent and camera-controllable streaming scene exploration from a single image or text prompt.