EMNLP 2025: Accepted Papers

We are thrilled to announce that our lab will be presenting two papers at this year's Conference on Empirical Methods in Natural Language Processing (EMNLP 2025) in Suzhou, China!

• Does Acceleration Cause Hidden Instability in Vision Language Models?
  Yizheng Sun, Hao Li, Chang Xu, Hongpeng Zhou, Chenghua Lin, Riza Batista-Navarro, Jingyuan Sun

• Natural Context Drift Undermines the Natural Language Understanding of Large Language Models
  Yulong Wu, Viktor Schlegel, Riza Batista-Navarro

We’re excited to join the global NLP community in Suzhou this November to share our findings and engage in vibrant discussions about the future of language and multimodal AI.

We hope to see you in Suzhou in November!