Jun Zhu

Comparing full-precision and quantized forward passes, and identifying two mechanisms that characterize pretrained quantization robustness, these mechanisms explain why quantization error that passes through numerous layers can still produce only small output changes, and are verified across models and quantization settings.

Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing, a real-time video editing model, is presented and the feasibility of real-time spatial video generation for both Vidu S2-Avatar and Vidu S2-Editing is explored.

SR-Edit achieves unprecedented image editing fidelity by refining region separation and preserving non-edit areas without introducing new artifacts.

A closed-loop world model that learns from both successes and failures could revolutionize dexterous manipulation in robotics.

Adversarial clothing can successfully evade thermal person detectors with over 80% effectiveness, exposing critical security flaws in AI-driven surveillance systems.

Achieving a staggering 54.67× speedup in text-to-video-audio generation without sacrificing quality could revolutionize real-time multimedia applications.

Achieving unprecedented accuracy in divertor heat-flux reconstruction, SafeDivertor outperforms traditional methods by directly utilizing plasma-state signals during discharge.

HCC-STAR not only surpasses leading models in treatment accuracy but also offers a significant survival advantage, highlighting the potential of AI in precision oncology.

Voice-controlled video generation just got a major upgrade with Vidu S1, achieving real-time performance without visual distortion.

Making interactive video world models real-time just got easier: minWM offers a full-stack, open-source pipeline to convert existing diffusion models into controllable, low-latency generators.