Nan Li's picture

Nan Li

chnln

·

nan-li-1100882a1

AI & ML interests

Computational Linguistics, Vision and Language Model, Model Interpretability

Recent Activity

upvoted a paper 1 day ago

VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors

liked a Space about 2 months ago

huggingface/ai-deadlines

liked a model 5 months ago

AnnaWegmann/Style-Embedding

View all activity

Organizations

upvoted a paper 1 day ago

VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors

Paper • 2604.02486 • Published 10 days ago • 9

upvoted a paper 5 months ago

Grounded Misunderstandings in Asymmetric Dialogue: A Perspectivist Annotation Scheme for MapTask

Paper • 2511.03718 • Published Nov 5, 2025 • 3

upvoted a paper 7 months ago

DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning

Paper • 2509.09524 • Published Sep 11, 2025 • 4

upvoted a paper 10 months ago

Can Vision Language Models Infer Human Gaze Direction? A Controlled Study

Paper • 2506.05412 • Published Jun 4, 2025 • 4