Recently, attention-based image captioning models, which are expected to ground correct
image regions for proper word generations, have achieved remarkable performance …

Learning with noisy labels (LNL) poses a significant challenge in training a well-generalized
model while avoiding overfitting to corrupted labels. Recent advances have achieved …

Humans learn from visual inputs at multiple timescales, both rapidly and flexibly acquiring
visual knowledge over short periods, and robustly accumulating online learning progress …

Distribution shift (eg, task or domain shift) in continual learning (CL) usually results in
catastrophic forgetting of previously learned knowledge. Although it can be alleviated by …

Learning from positive and unlabeled data is known as positive-unlabeled (PU) learning in
literature and has attracted much attention in recent years. One common approach in PU …

Existing subset selection methods for efficient learning predominantly employ discrete
combinatorial and model-specific approaches, which lack generalizability---for each new …

Minimax optimization has been central in addressing various applications in machine
learning, game theory, and control theory. Prior literature has thus far mainly focused on …

In deep learning, using larger training datasets usually leads to more accurate models.
However, simply adding more but redundant data may be inefficient, as some training …

We consider the problem of teaching via demonstrations in sequential decision-making
settings. In particular, we study how to design a personalized curriculum over …

Treating each training sample unequally is prevalent in many machine-learning tasks.
Numerous weighting schemes have been proposed. Some schemes take the easy-first …