Sangmin Bae

13 papers · 2022–2025 · 9 conferences · across top CS/AI conferences

Achievements

+7 more ↓

🐝 Cross-Pollinator (12) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (9) 🌈 Renaissance Researcher (5)

🗺️ Taxonomy Completionist (29) 🌉 Interdisciplinary Bridge 🤝 Dynamic Duo (11) 🏆 Grand Slam ⚡ Prolific Year (5) 🗃️ Keyword Collector (60) 💎 Century Club (13)

Conferences

ICLR (3) CVPR (2) NIPS (2) AAAI (1) ACL (1) EMNLP (1) ICML (1) INTERSPEECH (1) NAACL (1)

Top co-authors

Se-Young Yun (11) Sungnyun Kim (5) SangMook Kim (2) Minchan Jeong (2) Adam Fisch (2) Jongwoo Ko (2) Namgyu Ho (2) Sungwoo Cho (2) Kangwook Jang (2) Gihun Lee (2)

Keywords

federated learning (2) representation learning (2) continual learning (2) transformer architecture (1) reinforcement learning (1) knowledge distillation (1) domain adaptation (1) autoregressive transformer (1) mutual information (1) hierarchical modeling (1) text classification (1) self-supervised learning (1) supervised learning (1) question answering (1) autoregressive generation (1) few-shot learning (1) distributed learning (1) fine-grained classification (1) contrastive learning (1) active learning (1)

Papers

Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation ICLR 2025 Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models ICLR 2025 Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA ICLR 2025 MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition ICML 2025 Block Transformer: Global-to-Local Language Modeling for Fast Inference NIPS 2024 Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL ACL 2024 Carpe diem: On the Evaluation of World Knowledge in Lifelong Language Models NAACL 2024 Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding EMNLP 2023 Self-Contrastive Learning: Single-Viewed Supervised Contrastive Framework Using Sub-network AAAI 2023 Coreset Sampling From Open-Set for Fine-Grained Self-Supervised Learning CVPR 2023 Re-Thinking Federated Active Learning Based on Inter-Class Diversity CVPR 2023 Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification INTERSPEECH 2023 Preservation of the Global Knowledge by Not-True Distillation in Federated Learning NIPS 2022