Data-Driven Simulator for Mechanical Circulatory Support with Domain Adversarial Neural Processby Sophia Sun, Wenyuan Chen,…
Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RLby Yu Luo, Tianying Ji,…
Learning diverse attacks on large language models for robust red-teaming and safety tuningby Seanie Lee,…
Learning from Uncertain Data: From Possible Worlds to Possible Modelsby Jiongli Zhu, Su Feng, Boris…
SGD method for entropy error function with smoothing l0 regularization for neural networksby Trong-Tuan Nguyen,…
Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexaminationby Zhiyao Luo, Yangchen Pan, Peter Watkinson,…
Scalable Surrogate Verification of Image-based Neural Network Control Systems using Composition and Unrollingby Feiyang Cai,…
Potential Field Based Deep Metric Learningby Shubhang Bhatnagar, Narendra AhujaFirst submitted to arxiv on: 28…
Counterfactual Explanations for Multivariate Time-Series without Training Datasetsby Xiangyu Sun, Raquel Aoki, Kevin H. WilsonFirst…
Low-rank finetuning for LLMs: A fairness perspectiveby Saswat Das, Marco Romanelli, Cuong Tran, Zarreen Reza,…