NLP

SSNLP 2026: WING Members Present Three Posters
SSNLP 2026: WING Members Present Three Posters
21 Jan, 2026 Singapore University of Technology and Design
SSNLP 2026: WING Members Present Three Posters
WING Members Present at NUS AI Seminar at the Computer Science Department
WING at NUS AI Seminar at the Computer Science Department
19 Nov, 2025 NUS Computing Seminar Room 21
Project Project Project
WING Members Present at NUS AI Seminar at the Computer Science Department
WING Members Present at NUS Computing's Inaugural AI-X: Industry Day
WING at Computing’s AI-X Industry Day
18 Nov, 2025 NUS Shaw Foundation
Project Project
WING Members Present at NUS Computing's Inaugural AI-X: Industry Day
Discourse and LLMs
We measure and enhance LLMs’ discourse understanding, focusing on faithfulness and mechanistic interpretability.
PDF Code Slides
Discourse and LLMs
Summarizing Scientific Content with Social Media Language
Translating complex scientific content into accessible language for social media platforms.
Navigating Ethical Challenges in NLP: Hands-on strategies for students and researchers (Tutorial at ACL '25)
Navigating Ethical Challenges in NLP
27 Jul, 2025 Austria Center Vienna
PDF Slides
Navigating Ethical Challenges in NLP: Hands-on strategies for students and researchers (Tutorial at ACL '25)
Min's invited talk on prompting at the the IT:U Austria Summer School
Min participated in the interdisciplinary panel on AI in Education, then gave an invited talk the next day on prompting.
25 Jul, 2025 Austria Center Vienna
Project
A Comparative Analysis of Representation Flow in State-Space and Transformer Architectures
We study the feature flow across layers in state-space models compared to Transformers.
ChatCRS: Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systems
We incoporate external knowledge and goals for better CRS.
PDF Code
ChatCRS: Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systems
Assessing the AI Scientist
We find positive use cases, but also weaknesses that need much handholding from human scientists.
PDF
Assessing the AI Scientist