🌟Check out the first comprehensive review of SSM works ! It also offers experimental comparisons and analyses to better demonstrate SSM's features and advantages. link.springer.com/article/10… @SpringerEng #Statespacemodel

🚨Call for Papers: Special Issue on "Visual World Model"📊💡 Submit your work on new representation systems, architectures and algorithms, and cutting-edge techniques of visual world models for the SI！ Deadline: 31 December 2026 🔗link.springer.com/collection… @SpringerEng

🚨Call for Papers: Special Issue on "Visual World Model"📊💡 Submit your work on new representation systems, architectures and algorithms, and cutting-edge techniques of visual world models for the SI！ Deadline: 31 December 2026 🔗sciopen.com/journal/2097-333… @SciOpenTUP

🌟Authors from NVIDIA and Singapore Institute of Technology proposed PIGNN3D, a physics-informed graph neural network designed for fast and efficient 3D thermal field simulation in data centers. link.springer.com/article/10… @SpringerEng #datacenter #GNN

🔥 Now online! The authors from East China Normal University and ‌A*STAR proposed a structured adversarial attack framework for medical hyperspectral imaging. link.springer.com/article/10… #Medicalhyperspectral #Adversarialattack @SpringerEng

🔥The authors from Zhengzhou University and Institute of Automation, CAS, proposed cross-modal joint unlearning (CMJU) framework for balanced cross-modal unlearning in MLLMs under the modality-complete supervision setting. link.springer.com/article/10… #unlearning #MLLMs @SpringerEng

🔥The authors proposed the ProACT framework, which is a clinically grounded, prototype-guided, anchor-based TTA for stable, multi-center pneumoconiosis diagnosis using fully unlabeled target data. link.springer.com/article/10… #Pneumoconiosisdiagnosis @SpringerEng

Authors from Northwestern Polytechnical University introduce a robust learning-free estimator called MAC1toK To address the problem of performance degradation under extremely low inlier ratios. link.springer.com/article/10… #Pointcloudregistration @SpringerEng

Authors from ShanghaiTech University and The Chinese University of Hong Kong introduced MARMOT, a masked autoencoder for modeling transient imaging to facilitate NLOS applications in a self-supervised manner. link.springer.com/article/10… #MAE #NLOSimaging @SpringerEng @SciOpenTUP

Authors from The Hong Kong Polytechnic University proposed a diffusion-based underwater image enhancement method to support 3D Gaussian splatting-based novel views synthesis with high visual fidelity. link.springer.com/article/10… #underwaterimage #novelviewsynthesis @SpringerEng

Authors from Queensland Uni., RMIT, CSIRO, and Adelaide Uni. introduced a lightweight viewpoint-aware self-correction strategy that explicitly signals frame-of-reference changes and guides models to revise viewpoint-sensitive reasoning. link.springer.com/article/10… #LMM @SpringerEng

The authors from Southeast University proposed plausibility-aware motion diffusion (PAMD), a framework for generating dances that are both musically aligned and physically realistic. link.springer.com/article/10… #Dancegeneration @SpringerEng

✨Authors from Peking University and Peng Cheng Laboratory developed the symbolic-driven agentic reasoning (SDAR), a multimodal framework that bridges perception and cognition for event-level analysis. link.springer.com/article/10… #Agenticreasoning @SpringerEng

🔥Authors from Southern University of Science and Technology and Alibaba Group proposed DanceDiT, a lightweight and practical framework for pose-driven human image animation. link.springer.com/article/10… @SpringerEng #DiT #videogeneration

🔥Check out this large-scale, diverse, in-the-wild audio-visual dataset! Authors from Beijing University of Posts and Telecommunications presented their new method for the synthesis of lifelike 3D talking heads from audio. link.springer.com/article/10… @SpringerEng

🔥Check out this new paper on camouflaged object detection. the authors from Tsinghua University and University of California, Berkeley, proposed to simultaneously employ a group of diverse “predators” to seek out the target object. link.springer.com/article/10… @SpringerEng

To address the challenges of catastrophic forgetting, the authors from Shandong University proposed an integration of multi-modal graph with historical knowledge graph for continual robotic navigation. link.springer.com/article/10… @SpringerEng

🎉🎉🎉Visual Intelligence has achieved a Scopus Citescore of 10.9 for 2025, proudly ranking in the top 10% in three subfields: Signal Processing, #18/203, Computer Graphics and Computer-Aided Design #13/131, and Computer Vision and PR #18/183 @SpringerEng @SciOpenTUP

Prof. Yaonan Wang, an academician of the Chinese Academy of Engineering, and his team published a review in Visual Intelligence. It reviews pivotal technologies for intelligent robots. link.springer.com/article/10… @SpringerEng

🌟The authors from Anhui University proposed D-PETA, a novel source-free domain-adaptive framework for keypoint detection. D-PETA integrates dual-rate parameter-efficient tuning with adaptive augmentation strategies. link.springer.com/article/10… @SpringerEng #Keypointdetection