 Can Layer-wise SSL Features Improve Zero-Shot ASR Performance for Children's Speech?IEEE Signal Processing Letters (IEEE SPL), 2025 |
 Zero-Shot KWS for Children's Speech using Layer-Wise Features from SSL ModelsPattern Recognition Letters (Pattern Recogn. Lett.), 2025 |
 PESTO: Real-Time Pitch Estimation with Self-supervised Transposition-equivariant ObjectiveTransactions of the International Society for Music Information Retrieval (TISMIR), 2025 |
 SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic SoundscapesInternational Conference on Learning Representations (ICLR), 2025 |
 Vision Generalist Model: A SurveyInternational Journal of Computer Vision (IJCV), 2025 |
 UAD: Unsupervised Affordance Distillation for Generalization in Robotic ManipulationIEEE International Conference on Robotics and Automation (ICRA), 2025 |
