Learning the Regularization Strength for Deep Fine-Tuning via a Data-Emphasized Variational Objectiveby Ethan Harvey, Mikhail…
Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimizationby Ryan Park, Darren J.…
Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learningby Shentong Mo, Shengbang TongFirst submitted to arxiv…
Congestion Forecast for Trains with Railroad-Graph-based Semi-Supervised Learning using Sparse Passenger Reportsby Soto Anno, Kota…
Enhancing Robustness and Efficiency of Least Square Twin SVM via Granular Computingby M. Tanveer, R.…
Exploring RL-based LLM Training for Formal Language Tasks with Programmed Rewardsby Alexander G. Padula, Dennis…
An Effective Theory of Bias Amplificationby Arjun Subramonian, Samuel J. Bell, Levent Sagun, Elvis DohmatobFirst…
Small Contributions, Small Networks: Efficient Neural Network Pruning Based on Relative Importanceby Mostafa Hussien, Mahmoud…
Implicit Regularization for Tubal Tensor Factorizations via Gradient Descentby Santhosh Karnik, Anna Veselovska, Mark Iwen,…
On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Boundsby Matteo Vilucchio,…