Profiles2022-2026
Chang D Yoo
Korea Advanced Institute of Science and Technology (KAIST)
15Papers
15Last author
15Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers15
- TESSAR: Geometry-Aware Active Regression via Dynamic Voronoi TessellationAuthor 8 of 8ICLR 2026
- A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion ModelsAuthor 7 of 7NeurIPS 2025 · 1 citation
- ITA-MDT: Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-OnAuthor 6 of 6CVPR 2025
- C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature DispersionAuthor 7 of 7ICLR 2024 · 84 citations
- TPC: Test-time Procrustes Calibration for Diffusion-based Human Image AnimationAuthor 4 of 4NeurIPS 2024 · 16 citations
- TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human FeedbackAuthor 10 of 10ACL Findings 2024 · 3 citations
- Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLMAuthor 7 of 7EMNLP Findings 2024
- A Theory of Unsupervised Speech RecognitionAuthor 3 of 3ACL 2023 · 4 citations
- INTapt: Information-Theoretic Adversarial Prompt Tuning for Enhanced Non-Native Speech RecognitionAuthor 5 of 5ACL Findings 2023 · 3 citations
- HEAR: Hearing Enhanced Audio Response for Video-grounded DialogueAuthor 6 of 6EMNLP Findings 2023 · 2 citations
- Listen, Decipher and Sign: Toward Unsupervised Speech-to-Sign Language RecognitionAuthor 9 of 9ACL Findings 2023 · 1 citation
- Forget-free Continual Learning with Winning SubnetworksAuthor 8 of 8ICML 2022 · 159 citations
- Information-Theoretic Text Hallucination Reduction for Video-grounded DialogueAuthor 5 of 5EMNLP 2022 · 10 citations
- Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech RecognitionAuthor 4 of 4ACL 2022 · 5 citations
- SMSMix: Sense-Maintained Sentence Mixup for Word Sense DisambiguationAuthor 6 of 6EMNLP Findings 2022 · 4 citations
