Papers by Changhu Wang

2 papers
DANCE: Diversity-attended Dynamic Caching with Asymmetric Quantization for Test-time Adaptation of Vision-Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to test-time adaptation of vision-language models measure prediction entropy but these samples tend to approach prototypes with limited coverage of data distributions.
Approach: They propose a new approach for test-time adaptation of vision-language models . they construct a dynamic cache to store diversity-aware test samples .
Outcome: The proposed approach is more efficient than current methods on augmented visual models.
How Do Large Language Models Perform on PDE Discovery: A Coarse-to-fine Perspective (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to identify partial differential equations using large language models suffer from performance degradation under extreme data scarcity.
Approach: They propose a framework to use large language models to identify underlying partial differential equations out of very limited observations of a physical system.
Outcome: The proposed framework is based on a coarse-to-fine paradigm to discover PDEs out of very limited observations of a physical system.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations