5 papers
Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation
Hanwen Shen, Ting Ying, Jiajie Lu +1
Although debiased large language models (LLMs) excel at handling known or low-bias prompts, they often fail on unfamiliar and high-bias prompts. We demonstrate via out-of-distribut…
LiteUpdate: A Lightweight Framework for Updating AI-Generated Image Detectors
Jiajie Lu, Zhenkan Fu, Na Zhao +4
The rapid progress of generative AI has led to the emergence of new generative models, while existing detection methods struggle to keep pace, resulting in significant degradation…
Enhancing Scene Transition Awareness in Video Generation via Post-Training
Hanwen Shen, Jiajie Lu, Yupeng Cao +1
Recent advances in AI-generated video have shown strong performance on \emph{text-to-video} tasks, particularly for short clips depicting a single scene. However, current models st…
360-Degree Video Super Resolution and Quality Enhancement Challenge: Methods and Results
Ahmed Telili, Wassim Hamidouche, Ibrahim Farhat +12
Omnidirectional (360-degree) video is rapidly gaining popularity due to advancements in immersive technologies like virtual reality (VR) and extended reality (XR). However, real-ti…
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
Long Xing, Qidong Huang, Xiaoyi Dong +8
In large vision-language models (LVLMs), images serve as inputs that carry a wealth of information. As the idiom "A picture is worth a thousand words" implies, representing a singl…