Simple Hack for Transformers against Heavy Long-Text Classification on a Time- and Memory-Limited GPU Serviceby…
Better Understandings and Configurations in MaxSAT Local Search Solvers via Anytime Performance Analysisby Furong Ye,…
Zero-shot cross-lingual transfer in instruction tuning of large language modelsby Nadezhda Chirkova, Vassilina NikoulinaFirst submitted…
UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Modelsby Yijiang River Dong,…
Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decodingby Yuu Jinnai, Kaito AriuFirst submitted to arxiv…
Generalizing in Net-Zero Microgrids: A Study with Federated PPO and TRPOby Nicolas M Cuadrado Avila,…
EXAdam: The Power of Adaptive Cross-Momentsby Ahmed M. AdlyFirst submitted to arxiv on: 29 Dec…
EEG-Reptile: An Automatized Reptile-Based Meta-Learning Library for BCIsby Daniil A. Berdyshev, Artem M. Grachev, Sergei…
HyperQ-Opt: Q-learning for Hyperparameter Optimizationby Md. Tarek HasanFirst submitted to arxiv on: 23 Dec 2024CategoriesMain:…
Empirical evaluation of normalizing flows in Markov Chain Monte Carloby David Nabergoj, Erik ŠtrumbeljFirst submitted…