arXiv:2609.01582v1 Announce Type: new
Abstract: Complex 3D spatial text to image generation requires models to convert natural language into stable visual geometry, not merely semantic appearance. Ex...
By Ziyun Qian, Zizhi Chen, Yizhou Liu, Mingyang Sun, Dingkang Yang, Lihua Zhang
arXiv:2607. 19344v1 Announce Type: cross Abstract: Controllable image generation remains challenging for creative professionals, who often require precise regional control over materials, object identities, and spatial arrangements that cannot be reliably achieved through text prompting alone.
By Rahul Sajnani, Yulia Gryaditskaya, Radom\'ir M\v{e}ch, Srinath Sridhar, Matheus Gadelha
Recent image generators have demonstrated impressive photorealism and instruction-following capabilities in single-image generation and editing. However, constrained by their architectures, they cannot achieve interleaved generation (text-image sequence), which has crucial applications in visual narratives, guidance, and embodied manipulation.
arXiv:2607. 16409v1 Announce Type: cross Abstract: Unified Multimodal Large Language Models (MLLMs) offer a promising paradigm for unifying visual understanding and generation, yet they still struggle to follow complex spatial instructions and logical constraints in controllable image generation.
By Junhao Liu, Jian-Wei Zhang, Tao Huang, Miles Yang, Zhao Zhong, Liefeng Bo
arXiv:2603. 08652v2 Announce Type: replace Abstract: Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning.
By Haodong Li, Chunmei Qing, Huanyu Zhang, Dongzhi Jiang, Yihang Zou, Hongbo Peng, Dingming Li, Yuhong Dai, ZePeng Lin, Juanxi Tian, Yi Zhou, Siqi Dai, Jingwei Wu, Pheng-Ann Heng
The paper introduces RoomWright, a code‑driven framework that generates 3D indoor scenes for embodied AI by focusing on functional usage rather than just visual layout. It performs usage‑driven object reasoning, treating anchors as task centers to select task‑required objects and their affordances, and compiles interactions into trigger‑condition‑effect rules that update object states. The system also addresses ambiguous object orientation through annotation‑guided usage cues, producing scenes that are executable, editable, and ready for simulation‑based policy learning.