Summary of Gemma Scope: Open Sparse Autoencoders Everywhere All at Once on Gemma 2, by Tom Lieberum et al.
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2by Tom Lieberum, Senthooran…
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2by Tom Lieberum, Senthooran…
Kolmogorov-Arnold Network for Online Reinforcement Learningby Victor Augusto Kich, Jair Augusto Bottega, Raul Steinmetz, Ricardo…
Unveiling the Power of Sparse Neural Networks for Feature Selectionby Zahra Atashgahi, Tennison Liu, Mykola…
Deeploy: Enabling Energy-Efficient Deployment of Small Language Models On Heterogeneous Microcontrollersby Moritz Scherer, Luka Macan,…
Bayes-optimal learning of an extensive-width neural network from quadratically many samplesby Antoine Maillard, Emanuele Troiani,…
Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Samplingby Jian Xu, Zhiqi…
Simultaneous and Meshfree Topology Optimization with Physics-informed Gaussian Processesby Amin Yousefpour, Shirin Hosseinmardi, Carlos Mora,…
Malicious Internet Entity Detection Using Local Graph Inferenceby Simon Mandlik, Tomas Pevny, Vaclav Smidl, Lukas…
Attention is all you need for an improved CNN-based flash flood susceptibility modeling. The case…
Why Rectified Power Unit Networks Fail and How to Improve It: An Effective Theory Perspectiveby…