Asia
SeeA: Efficient Exploration-Enhanced A Search by Selective Sampling
Three sampling techniques are presented for comparative investigations.
Adversarial Training from Mean Field Perspective
We also show that the network width alleviates these issues.
Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing
Due to their size, the capability of these networks has increased tremendously, but this has come at the cost of a significant increase in necessary compute.
Fine-Grained Dynamic Framework for Bias-Variance Joint Optimization on Data Missing Not at Random
Some existing estimators and regularizers attempt to achieve unbiased estimation to improve the predictive performance.
DIFFER: Decomposing Individual Reward for Fair Experience Replay in Multi-Agent Reinforcement Learning
The code is available in https://github.com/cathyhxh/DIFFER.
Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition
Long-tailed visual recognition has received increasing attention recently.
GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell Genomics
Single-cell genomics has significantly advanced our understanding of cellular behavior, catalyzing innovations in treatments and precision medicine.
Mixture of Tokens: Continuous MoE through Cross-Example Aggregation
Most widely adopted MoE models are discontinuous with respect to their parameters - often referred to as sparse .