WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipediaby Yufang Hou, Alessandra…
Can Low-Rank Knowledge Distillation in LLMs be Useful for Microelectronic Reasoning?by Nirjhor Rouf, Fin Amin,…
Optimizing Quantile-based Trading Strategies in Electricity Arbitrageby Ciaran O'Connor, Joseph Collins, Steven Prestwich, Andrea VisentinFirst…
An evidential time-to-event prediction model based on Gaussian random fuzzy numbersby Ling Huang, Yucheng Xing,…
Approximately Equivariant Neural Processesby Matthew Ashman, Cristiana Diaconu, Adrian Weller, Wessel Bruinsma, Richard E. TurnerFirst…
The Surprising Benefits of Base Rate Neglect in Robust Aggregationby Yuqing Kong, Shu Wang, Ying…
DRACO: Decentralized Asynchronous Federated Learning over Row-Stochastic Wireless Networksby Eunjeong Jeong, Marios KountourisFirst submitted to…
Scalable unsupervised alignment of general metric and non-metric structuresby Sanketh Vedula, Valentino Maiorca, Lorenzo Basile,…
In-Context In-Context Learning with Transformer Neural Processesby Matthew Ashman, Cristiana Diaconu, Adrian Weller, Richard E.…
Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Modelsby Guanting Dong, Keming Lu,…