Zobrazeno 1 - 10
of 148
pro vyhledávání: '"Lee, Yoonho"'
The effectiveness of large language models (LLMs) is not only measured by their ability to generate accurate outputs but also by their calibration-how well their confidence scores reflect the probability of their outputs being correct. While unsuperv
Externí odkaz:
http://arxiv.org/abs/2409.19817
Predicting and executing a sequence of actions without intermediate replanning, known as action chunking, is increasingly used in robot learning from human demonstrations. However, its effects on learned policies remain puzzling: some studies highlig
Externí odkaz:
http://arxiv.org/abs/2408.17355
Temporal Graph Neural Networks (TGNN) have the ability to capture both the graph topology and dynamic dependencies of interactions within a graph over time. There has been a growing need to explain the predictions of TGNN models due to the difficulty
Externí odkaz:
http://arxiv.org/abs/2406.13214
Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities. Yet, extending self-supervised learning to new modalities is non-trivial because the specifics of
Externí odkaz:
http://arxiv.org/abs/2402.14789
The standard way to teach models is by feeding them lots of data. However, this approach often teaches models incorrect ideas because they pick up on misleading signals in the data. To prevent such misconceptions, we must necessarily provide addition
Externí odkaz:
http://arxiv.org/abs/2402.03715
Foundation models encode rich representations that can be adapted to downstream tasks by fine-tuning. However, fine-tuning a model on one data distribution often degrades performance under distribution shifts. Current approaches to robust fine-tuning
Externí odkaz:
http://arxiv.org/abs/2401.10220
Effective machine learning models learn both robust features that directly determine the outcome of interest (e.g., an object with wheels is more likely to be a car), and shortcut features (e.g., an object on a road is more likely to be a car). The l
Externí odkaz:
http://arxiv.org/abs/2306.11120
In safety-critical applications of machine learning, it is often desirable for a model to be conservative, abstaining from making predictions on unknown inputs which are not well-represented in the training data. However, detecting unknown examples i
Externí odkaz:
http://arxiv.org/abs/2306.04974
Transfer learning with a small amount of target data is an effective and common approach to adapting a pre-trained model to distribution shifts. In some situations, target data labels may be expensive to obtain, so we may only have access to a limite
Externí odkaz:
http://arxiv.org/abs/2302.05441
The increasing fluency and widespread usage of large language models (LLMs) highlight the desirability of corresponding tools aiding detection of LLM-generated text. In this paper, we identify a property of the structure of an LLM's probability funct
Externí odkaz:
http://arxiv.org/abs/2301.11305