Publications

Under Review | ICML 2026

Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation

Dahee Kwon, Haeun Lee and Jaesik Choi

Generative AI, Representation Learning, Diverse Image Generation, Computer Vision

DAVE is a training-free intervention that mitigates lock-in behavior and improves sample diversity.

Under Review | ICML 2026

Causal Path Tracing in Transformers

Won Jo, Dahee Kwon, Jongeun Baek, Cheongwoong Kang and Jaesik Choi

Causal Path Discovery, Actual Cause, LLM, Transformers

We propose a framework to trace how information causally flows through transformer internals for a given decision.

Under Review | ECCV 2026

SPICE: Simple Polysemantic Feature Interpretation via Clustering-based Explanations

Sehyun Lee, Dahee Kwon, Damin Lee and Jaesik Choi

Polysemanticity, Representation Learning, Interpretability, Vision

We study how to disentangle visual concept clusters across diverse recognition architectures and analyze polysemanticity systematically.

Preprint

MAC: Memory-Augmented Contrastive Learning for Time Series Anomaly Detection

Dahee Kwon, Enver Menadjiev, Qin Xie and Jaesik Choi

Unsupervised Anomaly Detection, Contrastive Learning, Memory Augmentation, Multivariate Time-Series

MAC improves anomaly detection with dynamic memory augmentation, contrastive learning, and end-to-end reconstruction.

Preprint

Dual Masking for Domain Generalization

Dahee Kwon and Jaesik Choi

Domain Generalization, Representation Learning, Image Classification

DMDG improves robust representation learning by attenuating non-generalizable domain-specific features.