Abstract: Semi-supervised learning can leverage both labeled and unlabeled samples simultaneously to improve performance. However, existing methods often present the following issues: (1) The emphasis ...
TraPO is a semi-supervised reinforcement learning framework that bridges unlabeled and labeled samples for training large reasoning models (LRMs). Built upon GRPO, TraPO leverages a small set of ...
Abstract: Conventional semi-supervised learning (SSL) encounters challenges in effectively addressing issues associated with long-tail datasets, primarily stemming from imbalances within a dataset.
Class imbalance remains a critical challenge in semi-supervised learning (SSL), especially when distributional mismatches between labeled and unlabeled data lead to biased classification. Although ...
How can a small model learn to solve tasks it currently fails at, without rote imitation or relying on a correct rollout? A team of researchers from Google Cloud AI Research and UCLA have released a ...
Introduction: Clinical monitoring of functional decline in amyotrophic lateral sclerosis (ALS) relies on periodic assessments, which may miss critical changes that occur between visits when timely ...
Automatic classification of interior decoration styles has great potential to guide and streamline the design process. Despite recent advancements, it remains challenging to construct an accurate ...
What is catastrophic forgetting in foundation models? Foundation models excel in diverse domains but are largely static once deployed. Fine-tuning on new tasks often introduces catastrophic forgetting ...
As semiconductor technologies advance, device structures are becoming increasingly complex. New materials and architectures introduce intricate physical effects requiring accurate modeling to ensure ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results