About Me

Hi there! I’m a PhD student at KU Leuven, advised by Prof.Marie-Francine Moens and Prof.Tinne Tuytelaars. My current research interests lie in Vision and Language, Generative Models and Parameter-Efficient Fine-Tuning Methods. Feel free to contact me for questions and collaborations.

Before my PhD, I obtained my MSc. in Artificial Intelligence (2020) and Statistics (2019) from KU Leuven, and my BSc. in Applied Mathematics (2017) from Hebei University.

Selected Publications

TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models
Tingyu Qu, Mingxiao Li, Tinne Tuytelaars, Marie-Francine Mones
Preprint, Under Review
[Paper] [Code] [ModelScope Community]

Introducing Routing Functions to Vision-Language Parameter-Efficient Fine-Tuning with Low-Rank Bottlenecks
Tingyu Qu, Tinne Tuytelaars, Marie-Francine Moens
European Conference on Computer Vision (ECCV 2024)
[Paper] [Code]

Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
Mingxiao Li*, Tingyu Qu*, Ruicong yao, Wei Sun, Marie-Francine Moens
International Conference on Learning Representations (ICLR 2024)
[Paper] [Code (DDPM ver.)] [Code (ADM ver.)]

Visually-Aware Context Modeling for News Image Captioning
Tingyu Qu, Tinne Tuytelaars, Marie-Francine Moens
Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024)
[Paper] [Code]

Weakly Supervised Face Naming With Symmetry-Enhanced Contrastive Loss
Tingyu Qu, Tinne Tuytelaars, Marie-Francine Moens
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023)
[Paper] [Code]

Note: * indicates equal contribution

Service

Reviewer: CVPR, ACL, BMVC, NeurIPS, AAAI, ICLR, AISTATS, ICML, TPAMI