Gang Hua

Regularizing Second-Order Influences for Continual Learning

2023 · arXiv (Cornell University)

Continual learning aims to learn on non-stationary data streams without catastrophically forgetting previous knowledge. Prevalent replay-based methods address this challenge by rehearsing on a small buffer holding the seen data, for which a delicate sample …

Diversity-Aware Meta Visual Prompting

2023

We present Diversity-Aware Meta Visual Prompting (DAM-VP), an efficient and effective prompting method for transferring pre-trained models to downstream tasks with frozen backbone. A challenging issue in visual prompting is that image datasets sometimes have …

SOAR: Scene-debiasing Open-set Action Recognition

2023

Deep learning models have a risk of utilizing spurious clues to make predictions, such as recognizing actions based on the background scene. This issue can severely degrade the open-set action recognition performance when the testing …

AgenticScholar: Agentic Data Management with Pipeline Orchestration for Scholarly Corpora

2026 · Proceedings of the ACM on Management of Data

Managing the rapidly growing scholarly corpus poses significant challenges in representation, reasoning, and efficient analysis. An ideal system should unify structured knowledge management, agentic planning, and interpretable execution to support diverse scholarly queries – from …