Jonghyun Choi

Computer Science · Physical Sciences

24h-index4.1kcitations181works1.02yr 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(41), Multimodal Machine Learning Applications(36), Advanced Image and Video Retrieval Techniques(15), Advanced Neural Network Applications(12), Human Pose and Action Recognition(12)

Publications181 total

SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models
ArXiv.org·2026Open Access
SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models
arXiv (Cornell University)·2026Open Access
What Happens When: Learning Temporal Orders of Events in Videos
arXiv (Cornell University)·2025Open Access
Report on Eleutherococcus senticosus (Rupr. & Maxim.) Maxim. population distribution in the Sobaeksan National Park
Korea National Park Research Institute·2025
Online Generic Event Boundary Detection
arXiv (Cornell University)·2025Open Access
A Noninvasive Study of the Geographic Distribution of Maternal Lineages and Genetic Diversity in the Endangered Eurasian Flying Squirrel Population in the Sobaeksan National Park, South Korea
Journal of Animal Breeding and Genomics·2025
TTA-DAME: Test-Time Adaptation with Domain Augmentation and Model Ensemble for Dynamic Driving Conditions
arXiv (Cornell University)·2025Open Access
Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning
arXiv (Cornell University)·2025Open Access
ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO
Proceedings of the AAAI Conference on Artificial Intelligence·2025· 1 citedOpen Access
Multi-Modal Grounded Planning and Efficient Replanning for Learning Embodied Agents with a Few Examples
Proceedings of the AAAI Conference on Artificial Intelligence·2025· 2 citedOpen Access
MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity
Proceedings of the AAAI Conference on Artificial Intelligence·2025· 1 citedOpen Access
Large Language Models Still Exhibit Bias in Long Text
2025
Representation Bending for Large Language Model Safety
2025· 1 cited
Grid Decarbonization: Examination of Data-Driven Methods for Emission Factor Estimation
IFAC-PapersOnLine·2025Open Access
Moment-Aware Video Retrieval for Video Corpus Moment Retrieval
IEEE Access·2025Open Access
Multi-Modal Grounded Planning and Efficient Replanning For Learning Embodied Agents with A Few Examples
arXiv (Cornell University)·2024Open Access
ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments
Lecture notes in computer science·2024· 2 cited
Large Language Models Still Exhibit Bias in Long Text
arXiv (Cornell University)·2024Open Access
Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling
arXiv (Cornell University)·2024· 1 citedOpen Access
SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization
2024· 12 cited
page 1 of 10Next →

Frequent Co-authors

Larry S. Davis(14), Jung-Woo Ha(4), Mohammad Mostafavi(4), Kuk‐Jin Yoon(4), Jan Neumann(3), Jihwan Bang(3), Ali Farhadi(3), William Robson Schwartz(3), Huimin Guo(3), Kunal Pratap Singh(3), Moo‐Yeol Baik(3), Minjia Zhang(3), Myeongjae Jeon(3), Byeonghwi Kim(3), Mahmudul Hasan(2), Amit K. Roy–Chowdhury(2), Heesu Kim(2), Youngjoon Yoo(2), Aniruddha Kembhavi(2), Minjoon Seo(2)