1
Humans possess a remarkable ability to assign novel interpretations to linguistic expressions, enabling them to learn new words and …
Data augmentation is a widely used technique to address the problem of
text classification when there is a limited amount of training …
TK-KNN: A Balanced Distance-Based Pseudo Labeling Approach for Semi-Supervised Intent Classification
The ability to detect intent in dialogue systems has become increasingly important in modern technology.
These systems often generate a …
Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, …
Handling out-of-distribution (OOD) samples has become a major stake in the real-world deploy- ment of machine learning systems. This …
Embodied agents face significant challenges when tasked with performing actions in diverse environments, particularly in generalizing …
Equivariant networks are specifically designed to ensure consistent behavior with respect to a set of input transformations, leading to …
Empirical risk minimization (ERM) is sensitive to spurious correlations present in training data, which poses a significant risk when …
Block coordinate descent (BCD) methods are widely used for large-scale numerical optimization because of their cheap iteration costs, …
Controlling artificial agents from visual sensory data is an arduous task. Reinforcement learning (RL) algorithms can succeed but …