Energy
COSMIC: Compress Satellite Images Efficiently via Diffusion Compensation
Our insight is that satellite's earth observation photos are not just images
Identification of Analytic Nonlinear Dynamical Systems with Non-asymptotic Guarantees
We provide non-asymptotic convergence rates for LSE and SME under i.i.d.
Federated Learning over Connected Modes Dennis Grinwald
In each communication round, each client uniformly samples points in the neighborhood of their projected point (top-right plot), and jointly train the solution simplex.
Understanding and Minimising Outlier Features in Transformer Training Bobby He
Despite their widespread use, our understanding of deep neural networks (NNs) and their training dynamics is very much incomplete.
The Value of Reward Lookahead in Reinforcement Learning
In reinforcement learning (RL), agents sequentially interact with changing environments while aiming to maximize the obtained rewards.
TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks
While tabular classification has traditionally relied on from-scratch training, a recent breakthrough called prior-data fitted networks (PFNs) challenges this approach. Similar to large language models, PFNs make use of pretraining and in-context learning to achieve strong performance on new tasks in a single forward pass.