4 papers
PART: Learning 3D Part Assembly and Retrieval with Transformers
Ruchao Bao, Wenzheng Wu, Chucheng Xiang +5
3D assembly is fundamental to modern manufacturing and digital content creation. In this paper, we present PART, a unified transformer-based framework for 3D part retrieval and ass…
HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads
Juyuan Wang, Chenxing Wang, Yuchen Fang +8
Decoding-free reranking methods that read relevance signals directly from LLM attention weights offer significant latency advantages over autoregressive approaches, yet suffer from…
Co-Layout: LLM-driven Co-optimization for Interior Layout
Chucheng Xiang, Ruchao Bao, Biyin Feng +4
We present a novel framework for automated interior design that combines large language models (LLMs) with grid-based integer programming to jointly optimize room layout and furnit…
Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation
Xiaoming Zhu, Xu Huang, Qinghongbing Xie +8
Generating artistic and coherent 3D scene layouts is crucial in digital content creation. Traditional optimization-based methods are often constrained by cumbersome manual rules, w…