Xiaoyu Zhang

Switching document formats can lead to accuracy drops of over 53%, revealing a hidden vulnerability in LLM workflows that demands urgent attention.

Private Face Distillation not only enhances face recognition performance but also significantly mitigates the risk of linking proxies to real identities.

RGD reshapes the decoding process in generative recommendation, ensuring high-value candidates are prioritized without retraining the model.

General-purpose computer vision MLLMs can outperform specialized remote sensing models on key tasks, challenging the notion of domain-specific superiority.

GitHub abuse is more widespread and varied than previously thought, demanding a unified detection approach to safeguard software supply chains.