Haitong Liu — accepted AI-conference papers

2025

Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations

Haitong Liu, Kuofeng Gao, Yang Bai, Jinmin Li, Jinxiao Shan, Tao Dai +1

CVPR 2025poster

Recently, video-based large language models (video-based LLMs) have achieved impressive performance across various video comprehension tasks. However, this rapid advancement raises significant privacy and security concerns, particularly regarding the unauthorized use of personal video data in automa…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2024

Two-timescale Derivative Free Optimization for Performative Prediction with Markovian Data

Haitong LIU, Qiang LI, Hoi To Wai

ICML 2024poster

This paper studies the performative prediction problem where a learner aims to minimize the expected loss with a decision-dependent data distribution. Such setting is motivated when outcomes can be affected by the prediction model, e.g., in strategic classification. We consider a state-dependent set…

Cited by 3 Source ↗PDF ↗Scholar ↗