Posts by Collection

Pose-Motion Video Anomaly Detection via Memory-Augmented Reconstruction and Conditional Variational Prediction

Weilin Wan, Weizhong Zhang, Cheng Jin

Published in ICME, 2023

This paper presents a skeleton-based video anomaly detection framework (PoMo) that combines memory-augmented pose reconstruction and conditional variational motion prediction to effectively identify spatial and temporal anomalies.

Download Paper

Out-of-distribution detection using neural activation prior

Weilin Wan, Weizhong Zhang, Quan Zhou, Fan Yi, Cheng Jin

arXiv preprint arXiv:2402.18162, 2024

This paper introduces Neural Activation Prior (NAP), a parameter-free post-hoc framework that effectively detects out-of-distribution samples by exploiting the distinct “signal-to-noise” activation patterns within feature channels without requiring retraining.

Download Paper

Computational Budget Should Be Considered in Data Selection

Weilin Wan, Weizhong Zhang, Cheng Jin

Published in NeurIPS, 2025

This paper challenges the assumption that data importance is budget-independent and proposes CADS, a computation-aware data selection framework that dynamically optimizes training subsets under explicit computational constraints.

Download Paper

Advanced Black-Box Tuning of Large Language Models with Limited API Calls

Zhikang Xie, Weilin Wan, Peizhu Gong, Weizhong Zhang, Cheng Jin

Published in AAAI, 2026

This paper proposes Advanced Black-Box Tuning (ABBT), a framework that reduces API calls by an order of magnitude in LLM optimization through instruction-aware initialization and Langevin dynamics-based evolution.

Download Paper

Explore and Establish Synergistic Effects Between Weight Pruning and Coreset Selection in Neural Network Training

Weilin Wan, Fan Yi, Weizhong Zhang, Quan Zhou, Cheng Jin

Published in AAAI, 2026

This paper investigates the interplay between weight pruning and coreset selection, proposing a synergistic training mechanism (SWaST) that alternately optimizes both to improve efficiency and accuracy while preventing critical information loss.

Download Paper

Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization

Weilin Wan, Jingtao Han, Weizhong Zhang, Cheng Jin

arXiv preprint arXiv:2603.21862, 2026

This paper establishes the first holistic framework for global MoE architectural optimization, reducing the intractable 16-dimensional search space to a two-phase sequential procedure via mathematical constraints and rank-preserving properties.

Download Paper

Introduction to Computer Systems (ICS), AIE210006.01

Undergraduate course, Fudan University, College of Computer Science and Artificial Intelligence, 2024

This course provides an introduction to the internal operation of modern computer systems, covering topics such as data representation, assembly language, memory hierarchy, linking, and exceptional control flow.