14 papers
CrossProjection: Geometric Grounding Beyond Viewpoint Change in Architectural Drawings
Kaho Li, Pengyu Zeng, Yuqin Dai +3
Architectural drawings violate the usual assumption behind multi-view reasoning: plans and sections are cuts, while elevations are facade projections, so corresponding components c…
PlanCraft: Sketch, Refine, and Furnish for Architect-Inspired Progressive 3D Residential Scene Generation
Pengyu Zeng, Yuqin Dai, Jun Yin +8
Two structural insights have been overlooked in automated residential floor plan generation. First, design is inherently progressive. Architects begin with rough strokes and refine…
Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping
Haoyuan Sun, Jing Wang, Yuxin Song +9
Recently, post-training methods based on reinforcement learning, with a particular focus on Group Relative Policy Optimization (GRPO), have emerged as the robust paradigm for furth…
Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement Learning
Yuqin Dai, Shuo Yang, Guoqing Wang +10
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating up-to-date external knowledge, yet real-world web environments present unique challenges.…
GreenPlanner: Practical Floorplan Layout Generation via an Energy-Aware and Function-Feasible Generative Framework
Pengyu Zeng, Yuqin Dai, Jun Yin +7
Building design directly affects human well-being and carbon emissions, yet generating spatial-functional and energy-compliant floorplans remains manual, costly, and non-scalable.…
EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes
Yuqin Dai, Guoqing Wang, Yuan Wang +13
Retrieval-Augmented Generation (RAG) has advanced open-domain question answering by incorporating external information into model reasoning. However, effectively leveraging externa…