Watch Before You Answer: Learning from Visually Grounded Post-Training Paper • 2604.05117 • Published 3 days ago • 15
Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editing Paper • 2601.05124 • Published Jan 8 • 6
AgentIAD: Tool-Augmented Single-Agent for Industrial Anomaly Detection Paper • 2512.13671 • Published Dec 15, 2025 • 1
Sample By Step, Optimize By Chunk: Chunk-Level GRPO For Text-to-Image Generation Paper • 2510.21583 • Published Oct 24, 2025 • 31