Accepted Papers

Out of 244 submissions in total, 188 of them have been accepted for a poster presentation. Check them out in OpenReview.

5 submissions have been selected for a contributed talk. Check them out in OpenReview and below (ordered randomly):

• Physics Supernova: AI Agent Matches Elite Gold Medalists at IPhO 2025 

Jiahao Qiu, Jingzhe Shi, Xinzhe Juan, Zelin Zhao, Jiayi Geng, Shilong Liu, Hongru WANG, Sanfeng Wu, Mengdi Wang

• !!!Best Paper!!! On Evaluating Methods vs. Evaluating Models 

Olawale Elijah Salaudeen, Florian E. Dorner, Peter Hase

• !!!Best Paper!!! The Measure of All Measures: Quantifying LLM Benchmark Quality 

Jihan Yao, Peter Jin, Ke Bao, Qiaolin Yu, Khushi Bhardwaj, Chang Su, Jialei Wang, YIKAI ZHU, Sugam Devare, Damon Mosk-Aoyama, Zhen Dong, Venkat Krishna Srinivasan, Yineng Zhang, Oleksii Kuchaiev, Jiantao Jiao, Banghua Zhu

• LLMs Show Surface-Form Brittleness Under Paraphrase Stress Tests 

Juan Miguel Navarro Carranza

• Detecting Training Data of Large Language Models via Expectation Maximization 

Gyuwan Kim, Yang Li, Evangelia Spiliopoulou, Jie Ma, Miguel Ballesteros, William Yang Wang