papers

Publications (241)

cs.CV2025

When Deepfake Detection Meets Graph Neural Network:a Unified and Lightweight Learning Framework

Haoyu Liu, Chaoyu Gong, Mengke He +3

The proliferation of generative video models has made detecting AI-generated and manipulated videos an urgent challenge. Existing detection approaches often fail to generalize acro…

cs.LG2021

ReNAS:Relativistic Evaluation of Neural Architecture Search

Yixing Xu, Yunhe Wang, Kai Han +4

An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS). To save computational cost, most of existing…

cs.CV2021

Augmented Shortcuts for Vision Transformers

Yehui Tang, Kai Han, Chang Xu +4

Transformer models have achieved great progress on computer vision tasks recently. The rapid development of vision transformers is mainly contributed by their high representation a…

physics.app-ph2025

Investigation of the Physical Mechanism behind Retention Loss in FeFETs with MIFIFIS Gate Structure

Tao Hu, Zeqi Chen, Runhao Han +19

A Metal-Gate Blocking Layer (GBL)- Ferroelectric-Tunnel Dielectric Layer (TDL)-Ferroelectric -Channel Insulator (Ch.IL)-Si (MIFIFIS) structure is proposed to achieve a larger MW fo…

cs.CV2021

Vision Transformer Pruning

Mingjian Zhu, Yehui Tang, Kai Han

Vision transformer has achieved competitive performance on a variety of computer vision applications. However, their storage, run-time memory, and computational demands are hinderi…

cs.LG2026

Near-Policy: Accelerating On-Policy Distillation via Asynchronous Generation and Selective Packing

Miao Rang, Zhenni Bi, Hang Zhou +6

Standard knowledge distillation for autoregressive models often suffers from distribution mismatch. While on-policy methods mitigate this by leveraging student-generated outputs, t…