GitHub

Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching

SVG with EasyCache on HunyuanVideo can achieve more than 3x speedup. Video generation models have demonstrated remarkable performance, yet their broader adoption remains constrained by slow inference ...
GitHub

This repository gives the official implementation of VFace: A Training-Free Approach for Diffusion-Based Video Face Swapping (WACV 2026)

We present a training-free, plug-and-play method, namely VFace, for high-quality face swapping in videos. It can be seamlessly integrated with image-based face swapping approaches built on diffusion ...

The AI child exploitation crisis is here

The National Center for Missing and Exploited Children said it received over a million reports tied to AI-generated child ...

Microsoft's new AI training method eliminates bloated system prompts without sacrificing model performance

Microsoft researchers have developed On-Policy Context Distillation (OPCD), a training method that permanently embeds ...
IEEE

Learning Beyond Time: Transformation-Aware Diffusion for Data-Augmented Soft-Sensor Modeling

Abstract: In industrial soft-sensor modeling, the scarcity and imbalance of process data often lead to overfitting and poor generalization of predictive models. To address these challenges, this ...