Advanced Sensor and Control Systems

Derniers papiers

• A Light Bilevel Refinement Aligns Self-Supervised Representations for Stronger Task-Specific Learning

  Gustav Wagner Zakarias, Zheng-Hua Tan · 29 septembre 2026

  Self-supervised pretraining learns representations that are broadly transferable across downstream tasks, yet direct fine-tuning can be suboptimal due to misalignment between self-supervised and downstream task objectives, potentially degrading pretrained features beneficial to the downstream task. …

• A New First-Order Meta-Learning Algorithm with Convergence Guarantees

  El Mahdi Chayti, Martin Jaggi · 13 août 2026

  Learning new tasks by leveraging prior experience is a fundamental trait of intelligent systems. While Model-Agnostic Meta-Learning (MAML) is a leading approach, it suffers from significant computational and memory overhead due to the requirement of computing second-order meta-gradients. We propose …

• Self-Supervised Learning Using Nonlinear Dependence

  M. Hadi Sepanj, Benyamin Ghojogh, Paul Fieguth · 18 novembre 2025

  Self-supervised learning has gained significant attention in contemporary applications, particularly due to the scarcity of labeled data. While existing SSL methodologies primarily address feature variance and linear correlations, they often neglect the intricate relations between samples and the no…