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
On Evaluating Methods vs. Evaluating Models
The Measure of All Measures: Quantifying LLM Benchmark Quality
LLMs Show Surface-Form Brittleness Under Paraphrase Stress Tests
Detecting Training Data of Large Language Models via Expectation Maximization