Jian Wang

6 papers Snap Inc.

• 4KAgent: Agentic Any Image to 4K Super-Resolution
• CF-VLM：CounterFactual Vision-Language Fine-tuning
• GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning
• Latent Chain-of-Thought for Visual Reasoning
• SnapMoGen: Human Motion Generation from Expressive Texts
• Tri-MARF: A Tri-Modal Multi-Agent Responsive Framework for Comprehensive 3D Object Annotation