Jindong Wang

A new framework enhances out-of-distribution detection in time series analysis.

This article examines challenges and solutions related to noisy labels in training data.

A new method enhances security of Vision Transformers against adversarial attacks.

A new framework improves learning from incomplete data labels.

This paper discusses the role of LLMs in time series analysis.

New method enhances reliability of model predictions in real-world applications.

A new approach to integrate diverse cultural insights into language models.

New benchmark tests MLLMs on social media tasks like misinformation and hate speech.

Introducing a fresh approach to assess large language models effectively.

KIEval offers interactive evaluation to address data contamination in language models.

NPHardEval4V assesses reasoning capabilities of multimodal large language models.

Examining how noise in pre-training data impacts model performance.

A system to improve cultural representation in AI through simulated dialogues.

Investigating how small errors in training data enhance AI-generated content.

Study assesses seven LLMs on sentiment analysis in mixed-language WhatsApp chats.

Examining the issues and potential improvements in academic peer review.

ADC streamlines dataset creation, improving speed and accuracy in machine learning.

This article reviews time series analysis methods and their application in education.

Research shows that quirky questions can enhance language model training.

Discover how SoftVQ-VAE enhances image creation with efficiency and quality.