Xiaoming Wei
- Papers
- 11
Cite
Notes
Only stored in your browser.
Authored papers
11Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory
arXiv 2026
WildActor: Unconstrained Identity-Preserving Video Generation
arXiv 2026
Forge-and-Quench: Enhancing Image Generation for Higher Fidelity in Unified Multimodal Models
arXiv 2026
ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?
arXiv 2026
Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
arXiv 2025
PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
arXiv 2025
LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding
CVPR 2025 1
LongCat-Image Technical Report
arXiv 2025
LongCat-Video Technical Report
arXiv 2025
Active Intelligence in Video Avatars via Closed-loop World Modeling
arXiv 2025
ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting
CVPR 2024 1
Affiliations
Frequent co-authors
10from 11 papers