MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook Paper • 2509.14142 • Published Sep 17, 2025 • 10
MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models Paper • 2509.14651 • Published Sep 18, 2025
From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning Paper • 2511.23031 • Published Nov 28, 2025 • 1
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience Paper • 2601.15876 • Published 1 day ago • 62
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience Paper • 2601.15876 • Published 1 day ago • 62