Yongqin Xian

Google (United States) — United States

Computer Science · Physical Sciences

18h-index5.8kcitations68works2.72yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Domain Adaptation and Few-Shot Learning(37), Multimodal Machine Learning Applications(33), COVID-19 diagnosis using AI(14), Advanced Neural Network Applications(9), Human Pose and Action Recognition(8)

Publications68 total

MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning
arXiv (Cornell University)·2025Open Access
Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos
2025· 3 cited
LogiCzsl: Exploring Logic-induced Representation for Compositional Zero-shot Learning
2025· 3 cited
Active Data Curation Effectively Distills Large-Scale Multimodal Models
2025· 1 cited
LIME: Localized Image Editing via Attention Regularization in Diffusion Models
2025· 1 cited
UIP2P: Unsupervised Instruction-based Image Editing via Edit Reversibility Constraint
arXiv (Cornell University)·2024Open Access
Active Data Curation Effectively Distills Large-Scale Multimodal Models
arXiv (Cornell University)·2024Open Access
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
arXiv (Cornell University)·2024· 1 citedOpen Access
SILC: Improving Vision Language Pretraining with Self-distillation
Lecture notes in computer science·2024· 11 cited
Text-Conditioned Resampler For Long Form Video Understanding
Lecture notes in computer science·2024· 4 cited
PALM: Predicting Actions through Language Models
Lecture notes in computer science·2024· 11 cited
Toward a Diffusion-Based Generalist for Dense Vision Tasks
arXiv (Cornell University)·2024Open Access
I2DFormer+: Learning Image to Document Summary Attention for Zero-Shot Image Classification
International Journal of Computer Vision·2024· 4 cited
LocCa: Visual Pretraining with Location-aware Captioners
arXiv (Cornell University)·2024· 1 citedOpen Access
LocCa: Visual Pretraining with Location-aware Captioners
2024
Text-Conditioned Resampler For Long Form Video Understanding
arXiv (Cornell University)·2023Open Access
LIME: Localized Image Editing via Attention Regularization in Diffusion Models
arXiv (Cornell University)·2023Open Access
PALM: Predicting Actions through Language Models
arXiv (Cornell University)·2023· 1 citedOpen Access
SILC: Improving Vision Language Pretraining with Self-Distillation
arXiv (Cornell University)·2023· 1 citedOpen Access
Learning Prototype Classifiers for Long-Tailed Recognition
2023· 12 citedOpen Access
page 1 of 4Next →

Frequent Co-authors

Zeynep Akata(30), Bernt Schiele(22), Muhammad Ferjad Naeem(11), Federico Tombari(11), Luc Van Gool(10), Massimiliano Mancini(7), Jiuniu Wang(4), Fabio Cermelli(4), Barbara Caputo(4), Wenjia Xu(3), Anurag Das(3), Alessio Tonioni(3), Christoph H. Lampert(2), Tobias Lorenz(2), Matthias Hein(2), Saurabh Sharma(2), A. Sophia Koepke(2), Ying Shan(2), Muhammad Gul Zain Ali Khan(2), Muhammad Zeshan Afzal(2)