Spatially Grounded Image Generation

Latest papers

8 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

FlashControl: One-Step Controllable Generator via Distillation-Friendly Single-Stream Teachers
Oct 15, 2026Ngan Nguyen, Dung Nguyen, Quan Dao +4Spatially Grounded Image Generation Controllable Image Generation
Qualcomm AI Research · Rutgers University · Adelaide University +1
Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text
Jul 23, 2026Xu Wang, Kaixiang Yao, Miao Pan +4Spatially Grounded Image Generation Spatial Reasoning Benchmarks
OmniAI Group of ZJU ACES Lab
AsyncPatch Diffusion: spatially-flexible image generation
Jun 5, 2026Samuele Papa, Valentin De Bortoli, Guillaume Couairon +3Spatially Grounded Image Generation Diffusion Model Guidance
Google DeepMind · University of Amsterdam · The Netherlands Cancer Institute
UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation
May 20, 2026Jiayun Wang, Yu Wang, Weijie Gan +2Spatially Grounded Image Generation Image Generation
Center for Advanced AI, Accenture
GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis
Apr 9, 2026Yishen Liu, Hongcang Chen, Pengcheng Zhao +8Spatially Grounded Image Generation Synthetic Anomaly Generation
Beijing Institute of Technology · Beijing Jiaotong University · Li Auto +1
Agentic Flow Steering and Parallel Rollout Search for Spatially Grounded Text-to-Image Generation
Mar 19, 2026Ping Chen, Daoxuan Zhang, Xiangming Wang +3Spatially Grounded Image Generation T2I Generation
Harbin Institute of Technology, Shenzhen, China
From "What" to "How": Constrained Reasoning for Autoregressive Image Generation
Mar 3, 2026Ruxue Yan, Xubo Liu, Wenya Guo +3Spatially Grounded Image Generation Autoregressive Image Generation
College of Computer Science, Nankai University · Baidu Inc.
Sparsely Supervised Diffusion
Feb 2, 2026Wenshuai Zhao, Zhiyuan Li, Yi Zhao +5Spatially Grounded Image Generation Diffusion-Based Image Generation
Department of Computer Science, Aalto University, Finland · Department of Electrical Engineering and Automation, Aalto University, Finland.

Oct 15, 2026J/K move · Enter open · S save

FlashControl: One-Step Controllable Generator via Distillation-Friendly Single-Stream Teachers

Ngan Nguyen, Dung Nguyen, Quan Dao, Dimitris N. Metaxas+3

Qualcomm AI Research · Rutgers University · Adelaide University+1

Spatially Grounded Image Generation Controllable Image Generation Conditional Image Generation One-Step Generative Modeling Diffusion Model Fine-Tuning Diffusion Model Distillation

Open paper AskPDF arXiv

Diffusion models have become a leading approach in visual generative modeling, particularly effective in text-to-image and controllable generation. Their main drawback is slow inference as it requires many sampling steps. While recent distillation methods enable one-step text-to-image generation, extending these techniques to controllable generation is still challenging. Existing controllable models, such as ControlNet, rely on dual-branch design that make distillation difficult. In this work, we adopt a simpler strategy. Instead of adding extra conditional branches, we finetune a selected subset of layers in the original text-to-image diffusion model to directly enable controllable generation. This results in DeltaControl, a single-flow, multi-step diffusion model capable of supporting spatial-condition generation while matching the performance of dual-branch approaches. Building on this teacher model, we further apply step-distillation to obtain FlashControl, a one-step model capable of spatial controllable generation with a single forward pass.