Summary of Pushing the Limits Of Large Language Model Quantization Via the Linearity Theorem, by Vladimir Malinovskii et al.
Pushing the Limits of Large Language Model Quantization via the Linearity Theoremby Vladimir Malinovskii, Andrei…
Pushing the Limits of Large Language Model Quantization via the Linearity Theoremby Vladimir Malinovskii, Andrei…
A generalised novel loss function for computational fluid dynamicsby Zachary Cooper-Baldock, Paulo E. Santos, Russell…
On adaptivity and minimax optimality of two-sided nearest neighborsby Tathagata Sadhukhan, Manit Paul, Raaz DwivediFirst…
Making Sigmoid-MSE Great Again: Output Reset Challenges Softmax Cross-Entropy in Neural Network Classificationby Kanishka Tyagi,…
Exogenous Randomness Empowering Random Forestsby Tianxing Mei, Yingying Fan, Jinchi LvFirst submitted to arxiv on:…
Enhancing Risk Assessment in Transformers with Loss-at-Risk Functionsby Jinghan Zhang, Henry Xie, Xinhao Zhang, Kunpeng…
Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecastingby Zongjiang Shang, Ling Chen, Binqing wu,…
Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model Systemby Julian Collado,…
Fourier Amplitude and Correlation Loss: Beyond Using L2 Loss for Skillful Precipitation Nowcastingby Chiu-Wai Yan,…
CODES: Benchmarking Coupled ODE Surrogatesby Robin Janssen, Immanuel Sulzer, Tobias BuckFirst submitted to arxiv on:…