InjectTST: A Transformer Method of Injecting Global Information into Independent Channels for Long Time Series…
An Adaptive Hydropower Management Approach for Downstream Ecosystem Preservationby C. Coelho, M. Jing, M. Fernanda…
SOFIM: Stochastic Optimization Using Regularized Fisher Information Matrixby Mrinmay Sen, A. K. Qin, Gayathri C,…
Precise Extraction of Deep Learning Models via Side-Channel Attacks on Edge/Endpoint Devicesby Younghan Lee, Sohee…
FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive Modelsby Younghan Lee, Yungi Cho, Woorim Han,…
A Note on High-Probability Analysis of Algorithms with Exponential, Sub-Gaussian, and General Light Tailsby Amit…
MathScale: Scaling Instruction Tuning for Mathematical Reasoningby Zhengyang Tang, Xingxing Zhang, Benyou Wang, Furu WeiFirst…
Revisiting Confidence Estimation: Towards Reliable Failure Predictionby Fei Zhu, Xu-Yao Zhang, Zhen Cheng, Cheng-Lin LiuFirst…
InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answersby Yakir Yehuda, Itzik Malkiel, Oren Barkan, Jonathan Weill,…
TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmaxby Tobias…