SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning Paper โข 2512.24330 โข Published 27 days ago โข 35
Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities Paper โข 2505.02567 โข Published May 5, 2025 โข 80
Absolute Zero: Reinforced Self-play Reasoning with Zero Data Paper โข 2505.03335 โข Published May 6, 2025 โข 189
Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought Paper โข 2504.05599 โข Published Apr 8, 2025 โข 85