Title |
|---|
 |
 Wormhole Dynamics in Deep Neural NetworksIEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), 2025 |
 Learning with ConfidenceConference on Uncertainty in Artificial Intelligence (UAI), 2025 |
 Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision QuantizationInternational Joint Conference on Artificial Intelligence (IJCAI), 2025 |
Parameter Expanded Stochastic Gradient Markov Chain Monte CarloInternational Conference on Learning Representations (ICLR), 2025 |
 Plastic Learning with Deep Fourier FeaturesInternational Conference on Learning Representations (ICLR), 2024 |
 On the Crucial Role of Initialization for Matrix FactorizationInternational Conference on Learning Representations (ICLR), 2024 |
 Implicit Regularization of Sharpness-Aware Minimization for
Scale-Invariant ProblemsNeural Information Processing Systems (NeurIPS), 2024 |
 Towards Sharper Risk Bounds for Minimax ProblemsInternational Joint Conference on Artificial Intelligence (IJCAI), 2024 |
 Swing-by Dynamics in Concept Learning and Compositional GeneralizationInternational Conference on Learning Representations (ICLR), 2024 |
 Differentiation and Specialization of Attention Heads via the Refined
Local Learning CoefficientInternational Conference on Learning Representations (ICLR), 2024 |
 From Lazy to Rich: Exact Learning Dynamics in Deep Linear NetworksInternational Conference on Learning Representations (ICLR), 2024 |
 Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep
Graph Neural NetworksInternational Conference on Information and Knowledge Management (CIKM), 2024 |
