4 papers
Exemplar2VQA: A Scalable Exemplar-Driven Visual Question Answering Generation Framework via Multi-Agent Coding
Jiayu Ying, Qijian Tian, Ruijie Xu +4
Advancing spatial intelligence in Multimodal Large Language Models (MLLMs) is bottlenecked by the scarcity of complex, scalable 3D question-answer (QA) data. While manual annotatio…
MUSE: Agentic 3D Scene Authoring via Memory-Grounded Incremental Requirement Satisfaction
Ruijie Xu, Xinnan Zhu, Jiayu Ying +3
Text-driven 3D scene generation is a promising technique for digital content creation, embodied AI simulation, and interactive design, yet practical workflows often require refinin…
JointEdit3D: Feed-Forward 3D Scene Editing in a Unified Latent Space
Xinnan Zhu, Ruijie Xu, Jiayu Ying +4
Existing 3D scene editing methods typically rely on per-scene optimization over explicit 3D representations or cascaded edit-and-reconstruct pipelines, resulting in high test-time…
FLEG: Feed-Forward Language Embedded Gaussian Splatting from Any Views via Compact Semantic Representation
Qijian Tian, Xin Tan, Jiayu Ying +3
We present FLEG, a feed-forward network that reconstructs language-embedded 3D Gaussians from arbitrary views. Previous feed-forward language-embedded Gaussian reconstruction metho…