Sanghyuk Chun

Computer Science · Physical Sciences

22h-index7.1kcitations83works2.42yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

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

Research Topics

Domain Adaptation and Few-Shot Learning(31), Multimodal Machine Learning Applications(26), Advanced Neural Network Applications(25), Advanced Image and Video Retrieval Techniques(17), Generative Adversarial Networks and Image Synthesis(12)

Publications83 total

Reinforced Fast Weights with Next-Sequence Prediction
arXiv (Cornell University)·2026Open Access
Reinforced Fast Weights with Next-Sequence Prediction
ArXiv.org·2026Open Access
Mitigating Cross-Image Information Leakage in LVLMs for Multi-Image Tasks
ArXiv.org·2025Open Access
Emergence of Text Readability in Vision Language Models
arXiv (Cornell University)·2025Open Access
Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning
arXiv (Cornell University)·2025Open Access
Read, Watch and Scream! Sound Generation from Text and Video
Proceedings of the AAAI Conference on Artificial Intelligence·2025· 8 citedOpen Access
LongProLIP: A Probabilistic Vision-Language Model with Long Context Text
arXiv (Cornell University)·2025Open Access
RoCOCO: Robustness Benchmark of MS-COCO to Stress-Test Image-Text Matching Models
Lecture notes in computer science·2025· 1 cited
Similarity of Neural Architectures Using Adversarial Attack Transferability
Lecture notes in computer science·2024· 1 cited
FairDRO: Group fairness regularization via classwise robust optimization
Neural Networks·2024· 5 cited
HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts
Lecture notes in computer science·2024· 5 cited
Learning with Unmasked Tokens Drives Stronger Vision Learners
Lecture notes in computer science·2024
Probabilistic Language-Image Pre-Training
arXiv (Cornell University)·2024Open Access
Read, Watch and Scream! Sound Generation from Text and Video
arXiv (Cornell University)·2024Open Access
Language-only Efficient Training of Zero-shot Composed Image Retrieval
2024· 27 cited
An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval
arXiv (Cornell University)·2024Open Access
HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts
arXiv (Cornell University)·2024Open Access
Toward Interactive Regional Understanding in Vision-Large Language Models
arXiv (Cornell University)·2024Open Access
Toward Interactive Regional Understanding in Vision-Large Language Models
2024Open Access
Do Counterfactually Fair Image Classifiers Satisfy Group Fairness? -- A Theoretical and Empirical Study
2024
page 1 of 5Next →

Frequent Co-authors

Sangdoo Yun(20), Seong Joon Oh(19), Dongyoon Han(13), Byeongho Heo(11), Junsuk Choe(10), Wonjae Kim(9), Junbum Cha(7), Jung-Woo Ha(6), Hyunjung Shim(6), Youngjung Uh(5), Minz Won(4), Youngjoon Yoo(3), Jaejun Yoo(3), Seungho Lee(3), Zeynep Akata(3), Kyungjae Lee(3), Song Park(3), Xavier Serra(3), Taesup Moon(3), Byeongkyu Kang(2)