Latent diffusion models (LDMs) achieve state-of-the-art image synthesis, yet their reconstruction-style denoising objective provides only indirect semantic supervision: high-level semantics emerge slowly, requiring longer training and limiting sample quality. Recent works inject semantics from Vision Foundation Models (VFMs) either externally via representation alignment or internally by jointly modeling only a narrow slice of VFM features inside the diffusion process, under-utilizing the rich, nonlinear, multi-layer spatial semantics available. We introduce REGLUE (Representation Entanglement with Global-Local Unified Encoding), a unified latent diffusion framework that jointly models (i) VAE image latents, (ii) compact local (patch-level) VFM semantics, and (iii) a global (image-level) [CLS] token within a single SiT backbone. A lightweight convolutional semantic compressor nonlinearly aggregates multi-layer VFM features into a low-dimensional, spatially structured representation, which is entangled with the VAE latents in the diffusion process. An external alignment loss further regularizes internal representations toward frozen VFM targets. On ImageNet 256x256, REGLUE consistently improves FID and accelerates convergence over SiT-B/2 and SiT-XL/2 baselines, as well as over REPA, ReDi, and REG. Extensive experiments show that (a) spatial VFM semantics are crucial, (b) non-linear compression is key to unlocking their full benefit, and (c) global tokens and external alignment act as complementary, lightweight enhancements within our global-local-latent joint modeling framework. The code is available at https://github.com/giorgospets/reglue .
Narrating For You: Prompt-guided Audio-visual Narrating Face Generation Employing Multi-entangled Latent Space
Machine Intelligence Group, Department of CS&IS, BITS Pilani, Hyderabad Campus, India(机器智能组,计算机科学与信息学系,比斯汉学院海得拉巴校区,印度);Georgia Institute of Technology, USA(佐治亚理工学院,美国)
Style Intervention: How to Achieve Spatial Disentanglement with Style-based Generators?
Center for Research on Intelligent Perception and Computing, CASIA(中国科学院自动化研究所智能感知与计算研究中心);National Laboratory of Pattern Recognition, CASIA(中国科学院自动化研究所模式识别国家重点实验室);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
Multi-task SAR Image Processing via GAN-based Unsupervised Manipulation
School of Electronic Engineering, Xidian University(西安电子科技大学电子工程学院);Kunshan Innovation Institute of Xidian University(西安电子科技大学昆山创新研究院);University of Montenegro(黑山大学)
MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
Tsinghua University(清华大学);Westlake University(西湖大学);Zhejiang University(浙江大学);Hong Kong University of Science and Technology(香港科学与技术大学);OPPO;Shanghai AI Lab(上海人工智能实验室)
Sketch2Human: Deep Human Generation with Disentangled Geometry and Appearance Control
School of Creative Media, City University of Hong Kong(香港城市大学创意媒体学院);Department of Computer Science & Engineering, HKUST(香港科技大学计算机科学与工程学系);Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)深圳大数据研究院)
Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling
Hong Kong University of Science and Technology(香港科学与技术大学);Zhejiang University(浙江大学);National University of Singapore(新加坡国立大学);The Chinese University of Hong Kong(香港中文大学);Peking University(北京大学);Independent Researcher(独立研究者)
Next state prediction gives rise to entangled, yet compositional representations of objects
Max Planck Institute for Biological Cybernetics(马克斯·普朗克生物控制论研究所);Institute for Human-Centered AI, Helmholtz Computational Health Center(亥姆霍兹计算健康中心以人为本人工智能研究所)
Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering
University of New South Wales(新南威尔士大学);Australian Artificial Intelligence Institute, University of Technology Sydney(澳大利亚人工智能研究所,技术悉尼大学);Stanford University(斯坦福大学);School of Computing and Information Technology of University of Wollongong Australia(沃林根澳大利亚大学计算与信息科技学院);Sun Yat-sen University(中山大学);University of Science and Technology of China(中国科学技术大学)
Affine-Equivariant Kernel Space Encoding for NeRF Editing
Poznan University of Technology, Institute of Robotics and Machine Intelligence(波兹南技术大学机器人与机器智能研究所);Jagiellonian University, Faculty of Mathematics and Computer Science(雅盖隆大学数学与计算机科学学院);IDEAS Research Institute(IDEAS研究所)
Disentanglement of Biological and Technical Factors via Latent Space Rotation in Clinical Imaging Improves Disease Pattern Discovery
Computational Imaging Research Lab, Department for Biomedical Imaging and Image-guided Therapy(生物医学成像与影像引导治疗部门计算成像研究实验室);Comprehensive Center for Artificial Intelligence in Medicine(医学人工智能综合中心);Division of General and Pediatric Radiology, Department for Biomedical Imaging and Image-guided Therapy(普通放射科与儿科放射科,生物医学成像与影像引导治疗部门);Medical University of Vienna(维也纳医学大学)
Beyond Spatial Compression: Interface-Centric Generative States for Open-World 3D Structure
DSC ScaDS.AI, Leipzig University(DSC ScaDS.AI,莱比锡大学);Institute for Cancer Genetics and Informatics (ICGI), Oslo, Norway(癌症遗传学与信息学研究所(ICGI),奥斯陆,挪威);ICT Cluster, Singapore Institute of Technology, Singapore(信息科技集群,新加坡理工学院,新加坡)