Junha Song

Orcid: 0009-0000-6308-1299

According to our database1, Junha Song authored at least 11 papers between 2018 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2025
RL makes MLLMs see better than SFT.
CoRR, October, 2025

One More Glance with Sharp Eyes: Rethinking Lightweight Captioning as a Practical Visual Specialist.
CoRR, August, 2025

Using Large Language Models to Simulate History Taking: Implications for Symptom-Based Medical Education.
Inf., 2025

2024
Is User Feedback Always Informative? Retrieval Latent Defending for Semi-supervised Domain Adaptation Without Source Data.
Proceedings of the Computer Vision - ECCV 2024, 2024

2023
Test-Time Adaptation in the Dynamic World With Compound Domain Knowledge Management.
IEEE Robotics Autom. Lett., November, 2023

A Survey on Masked Autoencoder for Visual Self-supervised Learning.
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023

EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
CD-TTA: Compound Domain Test-time Adaptation for Semantic Segmentation.
CoRR, 2022

A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond.
CoRR, 2022

2020
Correction of Missing-Wedge Artifacts in Filamentous Tomograms by Template-Based Constrained Deconvolution.
J. Chem. Inf. Model., 2020

2018
A Pattern Recognition Tool for Medium-Resolution Cryo-EM Density Maps and Low-Resolution Cryo-ET Density Maps.
Proceedings of the Bioinformatics Research and Applications - 14th International Symposium, 2018


  Loading...