Shuchen Weng

RefMover: Diffusion-Based Single Image Reflection Removal With Language and Region Guidance.

RefMover is introduced, a multi-instruction diffusion framework for SIRR that bridges the semantic-spatial gap by combining language and region guidance and features a pipeline with a streamlined conditional architecture that mitigates condition conflicts and preserves details.

SPW-Nav: A Streaming Panoramic World Model for Language-Guided Navigation

Language-guided panoramic video generation benefits various downstream applications, such as interactive 3D scene exploration, virtual reality experiences, and embodied agent training. Existing panoramic generators follow predefined trajectories, and interactive world models act through low-level actions in perspective...

UniColorFlow: A Unified Framework for Multimodal-Guided Video Colorization with Consistency Flow

FlowDance: Music-Driven Dance Video Generation with Parallel Pose and RGB Streams

Music-driven dance video synthesis aims to animate a reference person according to a given music clip. The task is challenging because it requires a model to jointly learn music-to-motion correspondence, identity-preserving human animation, temporal coherence, and visually realistic video generation. We present FlowDan...

StreamAV-Bench: A Comprehensive Benchmark for Streaming Audio-Video Generation

Recent advancements in generative models are pushing video generation toward unbounded streaming audio-video generation for real-time interactive worlds. However, existing benchmarks primarily evaluate completed sequences and struggle to capture streaming properties. To bridge this gap, we introduce StreamAV-Bench, the...

MASS: Multiplayer World Models with Authoritative Shared State

The results show that explicit, authoritative state modeling provides a practical foundation for scalable and consistent multi-agent world simulation.

Video Generation Models Are Inherent Lighting Estimators

V-LITE (Video generation models are inherent lighting estimators), a framework that unlocks internal knowledge by reframing lighting estimation as a guided video inpainting task, is introduced, revealing that modern video diffusion models are not merely synthesizers but also powerful, inherently capable estimators of p...