Efficient Exploration in Deep Reinforcement Learning: A Novel Bayesian Actor-Critic Algorithmby Nikolai RozanovFirst submitted to…
Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learningby Sriyash Poddar, Yanming Wan, Hamish…
Federated Frank-Wolfe Algorithmby Ali Dadras, Sourasekhar Banerjee, Karthik Prakhya, Alp YurtseverFirst submitted to arxiv on:…
MASALA: Model-Agnostic Surrogate Explanations by Locality Adaptationby Saif Anwar, Nathan Griffiths, Abhir Bhalerao, Thomas PophamFirst…
TANGO: Clustering with Typicality-Aware Nonlocal Mode-Seeking and Graph-Cut Optimizationby Haowen Ma, Zhiguo Long, Hua MengFirst…
Perturb-and-Compare Approach for Detecting Out-of-Distribution Samples in Constrained Access Environmentsby Heeyoung Lee, Hoyoon Byun, Changdae…
PLUTUS: A Well Pre-trained Large Unified Transformer can Unveil Financial Time Series Regularitiesby Yuanjian Xu,…
Molecular Graph Representation Learning Integrating Large Language Models with Domain-specific Small Modelsby Tianyu Zhang, Yuxiang…
Learning Brave Assumption-Based Argumentation Frameworks via ASPby Emanuele De Angelis, Maurizio Proietti, Francesca ToniFirst submitted…
Robust spectral clustering with rank statisticsby Joshua Cape, Xianshi Yu, Jonquil Z. LiaoFirst submitted to…