8 papers
FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restoration
Jingren Liu, Shuning Xu, Qirui Yang +3
All-in-One Image Restoration (AIO-IR) aims to develop a unified model that can handle multiple degradations under complex conditions. However, existing methods often rely on task-s…
Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding
Yun Wang, Long Zhang, Jingren Liu +9
Video Large Language Models (Video-LLMs) have shown strong video understanding, yet their application to long-form videos remains constrained by limited context windows. A common w…
Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective
Jingren Liu, Zhong Ji, YunLong Yu +4
Parameter-efficient fine-tuning for continual learning (PEFT-CL) has shown promise in adapting pre-trained models to sequential tasks while mitigating catastrophic forgetting probl…
TeleEgo: Benchmarking Egocentric AI Assistants in the Wild
Jiaqi Yan, Ruilong Ren, Jingren Liu +13
Egocentric AI assistants in real-world settings must process multi-modal inputs (video, audio, text), respond in real time, and retain evolving long-term memory. However, existing…
CCD: Continual Consistency Diffusion for Lifelong Generative Modeling
Jingren Liu, Shuning Xu, Yun Wang +2
While diffusion-based models have shown remarkable generative capabilities in static settings, their extension to continual learning (CL) scenarios remains fundamentally constraine…
Infinite Video Understanding
Dell Zhang, Xiangyu Chen, Jixiang Luo +6
The rapid advancements in Large Language Models (LLMs) and their multimodal extensions (MLLMs) have ushered in remarkable progress in video understanding. However, a fundamental ch…