CORTEXA
← Browse
arxivcs.CVcs.AIcs.LG2026-07-17

Think, Plan, Paint: Layout-Aware Reasoning for Controllable Image Generation in Unified Models

Junhao Liu, Jian-Wei Zhang, Tao Huang, Miles Yang, Zhao Zhong, Liefeng Bo

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. To address this gap, we present ATLAS, a unified framework that equips MLLMs with a human-like "Think, Plan, and Paint" paradigm. We adopt layout as the shared representation that connects the three stages, enabling the model to reason about spatial requirements, plan explicit object arrangements, and render the final image. We further improve plan-to-image fidelity with reinforcement-learning-based layout alignment. We instantiate ATLAS at 7B and 80B scales, achieving state-of-the-art performance among MLLMs on image generation benchmarks and an average 65.31% improvement over existing layout-based unified MLLMs. On spatially related tasks, ATLAS obtains an average 23.06% gain over the base models. Through the same layout interface, ATLAS also supports instruction-guided editing and multimodal grounding. We further introduce ATLAS-Reasoning, a benchmark for evaluating generation under complex spatial instructions.

View free PDFSource page

Related papers

arxivcs.CVcs.AIcs.LG2026-07-02

Diagnosing Aerial-View Object Detectors with Foundational Image Generative Models

Stanislav Panev, Minhyek Jeon, Vaishnavi Khindkar, Ahish Deshpande, Celso M de Melo, Shuowen Hu, et al.

Recent advances in large-scale image generative models enable photorealistic scene synthesis with controllable attributes. Beyond data augmentation, their potential as diagnostic tools for trained vision systems remains unexplored in the aerial and remote sensing domains. We intr…

View free PDFSource page
arxivcs.CVcs.AIcs.LGcs.MMeess.IV2026-07-21

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Xinjie Zhang, Peng Zhang, Shicheng Zheng, Jinghao Guo, Zhaoyang Jia, Yifei Shen, et al.

Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to-image generation and instruction-based image editing. The stack is built from two co-designed compo…

View free PDFSource page
arxivcs.CVcs.AIcs.LG2026-07-07

ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation

Tianjiao Yu, Xinzhuo Li, Yifan Shen, Onkar Susladkar, Yuanzhe Liu, Xiaona Zhou, et al.

Unified 3D foundation models aspire to generate 3D assets and reason about them in language within a single backbone, but their text-3D interaction remains largely implicit. Existing methods concatenate text and 3D tokens into a flat sequence and rely on self-attention, collapsin…

View free PDFSource page
arxivcs.LGcs.AIcs.CV2026-07-16

Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation

Ku Onoda, Paavo Parmas, Hiroki Furuta, Soichiro Nishimori, Yuta Oshima, Shohei Taniguchi, et al.

Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes. This limits the diversity of images, and for person-centric prompts, can reflect or amplify demographi…

View free PDFSource page
arxivcs.CVcs.AIcs.GRcs.LG2026-06-28

GPC: Large-Scale Generative Pretraining for Transferable Motor Control

Yi Shi, Yifeng Jiang, Chen Tessler, Xue Bin Peng

Developing controllers capable of completing a wide range of tasks in a natural and life-like manner is a key challenge in enabling practical applications of physics-based character animation. In this work, we introduce Generative Pretrained Controllers (GPC), which leverage toke…

View free PDFSource page