Il-Min Kim

3 papers · 2025–2026 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13)

Venues

CVPR (2) ICCV (1)

Top co-authors

Yuchuan Li (2) Azadeh Motamedi (2) Chul B Park (1) Michael Greenspan (1) Jae-Mo Kang (1) Mahdiyar Molahasani (1) Hyock Ju Kwon (1) Ali Etemad (1)

Research topics

Artificial Intelligence (2) Deep Learning (2) Machine Learning (2) Core AI (2) Learning Types · Machine Learning (2) Computer Vision (1) Analysis (1) Application Areas (1) Core Methods (1) Learning Types · Deep Learning (1) Optimization & Theory (1) Techniques (1)

Keywords

vision-language model (2) out-of-distribution detection (2) spurious correlation (2) distribution shift (1) bias mitigation (1) open-set recognition (1) open-world learning (1) embedding projection (1) training data contamination (1) machine learning robustness (1) model-agnostic framework (1) contaminated training data (1) contrastive learning (1) sample proportion estimation (1) benchmark evaluation (1) object detection (1)

Papers

UNI-OOD: Unified Object- and Image-level Out-of-Distribution Detection via Cross-Context Attentive Vision-Language Modeling CVPR 2026 Beyond Clean Training Data: A Versatile and Model-Agnostic Framework for Out-of-Distribution Detection with Contaminated Training Data CVPR 2025 PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection ICCV 2025