Real-world dark images commonly exhibit not only low visibility and contrast but also complex noise and blur, posing significant restoration challenges. Existing methods often rely on paired data or fail to model dynamic illumination and blur characteristics, leading to poor generalization. To tackle this, we propose a generative framework based on visual autoregressive (VAR) modeling, guided by perceptual priors from the vision-language model (VLM). Specifically, to supply informative conditioning cues for VAR models, we deploy an adaptive curve estimation scheme to modulate the diverse illumination based on VLM-derived visibility scores. In addition, we integrate dynamic and spatial-frequency-aware Rotary Positional Encodings (SF-RoPE) into VAR to enhance its ability to model structures degraded by blur. Furthermore, we propose a recursive phase-domain modulation strategy that mitigates blur-induced artifacts in the phase domain via bounded iterative refinement guided by VLM-assessed blur scores. Our framework is fully unsupervised and achieves state-of-the-art performance on benchmark datasets.
UHD Image Deblurring via Autoregressive Flow with Ill-conditioned Constraints
Shandong Normal University（山东师范大学）；Qilu University of Technology（齐鲁工业大学）；Nanjing University of Science and Technology（南京理工大学）；National University of Defense Technology（国防科学技术大学）；Shandong University（山东大学）
Xidian University（西安电子科技大学）；The Hong Kong Polytechnic University（香港理工大学）；McMaster University（麦克马斯特大学）
As a powerful statistical image modeling technique, sparse representation has been successfully used in various image restoration applications. The success of sparse representation owes to the development of l1-norm optimization techniques, and the fact that natural images are intrinsically sparse in some domain. The image restoration quality largely depends on whether the employed sparse domain can represent well the underlying image. Considering that the contents can vary significantly across different images or different patches in a single image, we propose to learn various sets of bases f…
DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models
Tuebingen AI Center University of Tuebingen（图宾根人工智能中心图宾根大学）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；MIT-IBM Watson AI Lab（麻省理工-IBM沃森人工智能实验室）；IBM Research（IBM研究院）
When LLaVA Meets Objects: Token Composition for Vision-Language-Models
Tuebingen AI Center/University of Tuebingen（图宾根人工智能中心/图宾根大学）；Max Planck Institute for Informatics, SIC（马克斯·普朗克信息学院，SIC）；MIT-IBM Watson AI Lab（麻省理工-IBM沃森人工智能实验室）
Geometric Similarity in VLM Low-Level Vision Representations
Duke University（杜克大学）；Texas A&M University（德克萨斯A&M大学）；Florida State University（佛罗里达州立大学）；UC San Diego（加州大学圣迭戈分校）；University of Pennsylvania（宾夕法尼亚大学）；UNC Chapel Hill（北卡罗来纳大学教堂山分校）
Towards Joint Quantization and Token Pruning of Vision-Language Models
VCIP, College of Computer Science, Nankai University（VCIP，计算机科学学院，南开大学）；School of Computer Science and Engineering, Tianjin University of Technology（计算机科学与工程学院，天津工业大学）；OPPO Research Institute（OPPO研究院）；Academy for Advanced Interdisciplinary Studies, Nankai University（先进跨学科研究院，南开大学）；Nankai International Advanced Research Institute, Shenzhen Futian（南开国际先进研究 institutes，深圳福田）；Department of Computing, Hong Kong Polytechnic University（计算学院，香港理工大学）
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed
XPeng Inc.（小鹏汽车）；Peking University（北京大学）；The University of Hong Kong（香港大学）；University of California, Berkeley（加州大学伯克利分校）；Princeton University（普林斯顿大学）；National University of Singapore（新加坡国立大学）；HKUST (GZ)（香港科技大学（广州））
