Skip to content
conftrace_

Sungrack Yun

22 papers · 2012–2026 · 9 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 ↓
+10 more ↓ πŸ—ΊοΈ Taxonomy Completionist (52) 🌍 Conference Polyglot Β· Silver πŸƒ Academic Marathon Β· Half πŸŒ‰ Interdisciplinary Bridge Β· Silver 🐣 Hot Topic Early Bird
πŸ† Grand Slam πŸ† Keyword Champion 🧭 Keyword Pioneer 🧬 Topic Evolution πŸ’Ž Century Club Β· Bronze ⚑ Prolific Year Β· Productive πŸ”₯ Unstoppable Β· Bronze 🌈 Renaissance Researcher (5) πŸ—ƒοΈ Keyword Collector (120) πŸ“ˆ Trend Setter

Venues

ICCV (5) CVPR (4) ECCV (3) Interspeech (3) ICLR (2) NeurIPS (2) AAAI (1) ICML (1) WACV (1)

Top co-authors

Seokeon Choi (8) Hyunsin Park (6) Fatih Porikli (6) Debasmit Das (6) Seunghan Yang (5) Hyoungwoo Park (5) Munawar Hayat (4) Jun-Tae Lee (4) Mihir Jain (4) Sunghyun Park (3)

Research topics

Machine Learning (16) Deep Learning (12) Application Areas (11) Learning Types Β· Machine Learning (10) Artificial Intelligence (8) Learning Types Β· Deep Learning (7) Computer Vision (6) Core Methods (6) Learning Paradigms (5) Models (5) Speech & Audio (4) Core AI (4) Analysis (3) Architectures (3) Generation (3)

Keywords

diffusion model (3) knowledge distillation (3) domain generalization (3) action recognition (3) domain adaptation (2) text-to-image generation (2) speaker verification (2) model compression (2) cross-attention mechanism (2) weakly supervised learning (2) few-shot learning (2) transfer learning (1) feature learning (1) variational inference (1) multi-task learning (1) representation learning (1) image generation (1) temporal modeling (1) catastrophic forgetting (1) attention mechanism (1)

Papers

Ar2Can: An Architect and an Artist Leveraging a Canvas for Multi-Human Generation CVPR 2026 Memory-Efficient Fine-Tuning Diffusion Transformers via Dynamic Patch Sampling and Block Skipping CVPR 2026 ConsNoTrainLoRA: Data-driven Weight Initialization of Low-rank Adapters using Constraints ICCV 2025 Steering Guidance for Personalized Text-to-Image Diffusion Models ICCV 2025 Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning CVPR 2025 Feature Diversification and Adaptation for Federated Domain Generalization ECCV 2024 FedHide: Federated Learning by Hiding in the Neighbors ECCV 2024 Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models NeurIPS 2024 Few-Shot Common Action Localization via Cross-Attentional Fusion of Context and Temporal Dynamics ICCV 2023 Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts ICCV 2023 Progressive Random Convolutions for Single Domain Generalization CVPR 2023 ConFeSS: A Framework for Single Source Cross-Domain Few-Shot Learning ICLR 2022 Domain Agnostic Few-shot Learning for Speaker Verification Interspeech 2022 Improving Test-Time Adaptation via Shift-Agnostic Weight Regularization and Nearest Source Prototypes ECCV 2022 Leaky Gated Cross-Attention for Weakly Supervised Multi-Modal Temporal Action Localization WACV 2022 Multi-Head Modularization to Leverage Generalization Capability in Multi-Modal Networks AAAI 2022 Cross-Attentional Audio-Visual Fusion for Weakly-Supervised Action Localization ICLR 2021 Efficient Action Recognition via Dynamic Knowledge Propagation ICCV 2021 Federated Learning of User Verification Models Without Sharing Embeddings ICML 2021 An End-to-End Text-Independent Speaker Verification Framework with a Keyword Adversarial Network Interspeech 2019 Speaker Clustering by Iteratively Finding Discriminative Feature Space and Cluster Labels Interspeech 2017 Phoneme Classification using Constrained Variational Gaussian Process Dynamical System NeurIPS 2012