conftrace_
← Authors

Sungnyun Kim

11 papers · 2022–2025 · 8 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+5 more ↓ 🐝 Cross-Pollinator (15) πŸ—ΊοΈ Taxonomy Completionist (26) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (8)
🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge πŸ† Grand Slam 🀝 Dynamic Duo (10) πŸ’Ž Century Club (11)

Conferences

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

Top co-authors

Se-Young Yun (10) Sangmin Bae (5) Jongwoo Ko (3) Kangwook Jang (3) Sungwoo Cho (3) Tianyi Chen (2) Stefano Soatto (1) Peng Tang (1) Changwan Ha (1) Hyerim Baek (1)

Keywords

multimodal learning (2) representation learning (2) knowledge distillation (2) contrastive learning (1) domain adaptation (1) self-supervised learning (1) transfer learning (1) open-set learning (1) supervised learning (1) facial animation (1) fine-grained classification (1) flow matching (1) speaker verification (1) mutual information (1) fine-grained recognition (1) supervised classification (1) zero-shot learning (1) latent space (1) self-supervised pretraining (1) model compression (1)

Papers

MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition ICML 2025 DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs ICML 2025 MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation ICCV 2025 Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation ICLR 2025 DistiLLM: Towards Streamlined Distillation for Large Language Models ICML 2024 DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models EMNLP 2024 Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification INTERSPEECH 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 Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation INTERSPEECH 2023 Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty NIPS 2022