3 papers
cs.CV2025
DreamScene: 3D Gaussian-based End-to-end Text-to-3D Scene Generation
Haoran Li, Yuli Tian, Kun Lan +4
Generating 3D scenes from natural language holds great promise for applications in gaming, film, and design. However, existing methods struggle with automation, 3D consistency, and…
q-bio.NC2025
Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience
Zinan Liu, Haoran Li, Jingyi Lu +6
Autonomous AI is no longer a hard-to-reach concept, it enables the agents to move beyond executing tasks to independently addressing complex problems, adapting to change while hand…
cs.CV2025
Text-to-3D Generation by 2D Editing
Haoran Li, Yuli Tian, Yonghui Wang +4
Distilling 3D representations from pretrained 2D diffusion models is essential for 3D creative applications across gaming, film, and interior design. Current SDS-based methods are…