conftrace_

Taejong Joo

4 papers · 2020–2024 · 3 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓

+1 more ↓

🧭 Keyword Pioneer 🌍 Conference Polyglot (3) 🐝 Cross-Pollinator (15) 🌉 Interdisciplinary Bridge 🐣 Hot Topic Early Bird

📈 Trend Setter

Conferences

ICML (2) ICLR (1) NIPS (1)

Top co-authors

Diego Klabjan (2) Byunghoon Kim (1) Min-Gwan Seo (1) Uijung Chung (1) Donggu Kang (1)

Keywords

bayesian inference (1) uncertainty quantification (1) model calibration (1) label smoothing (1) distribution shift (1) uncertainty estimation (1) pseudo label (1) categorical probability (1) temporal ensemble (1)

Papers

Improving self-training under distribution shifts via anchored confidence with theoretical guarantees NIPS 2024 IW-GAE: Importance weighted group accuracy estimation for improved calibration and model selection in unsupervised domain adaptation ICML 2024 Regularizing activations in neural networks via distribution matching with the Wasserstein metric ICLR 2020 Being Bayesian about Categorical Probability ICML 2020