The paper introduces the Wide-area Spatio-temporal Scene Understanding (WSTU) problem, which demands simultaneous wide-area coverage, per-target resolution, and temporal continuity—capabilities lacking in existing datasets. To address this, the authors present HARD, an ultra‑high‑resolution (12768×9564) UAV dataset annotated for object detection, multi‑object tracking, and scene‑level visual question answering. They also propose a latency‑aware metric, streaming‑HOTA (s‑HOTA), and show through baseline experiments that high resolution and processing latency significantly impact detection, tracking, and VQA performance, revealing gaps in current methods for WSTU.
By Yuhang Zhu, Meiyi Zhu, Yunkai Dang, Zhangnan Li, Yuxuan Wang, Wenbin Li, Hongbing Pan
arXiv:2609.13617v2 Announce Type: replace
Abstract: OpenAI released ChatGPT Images 2.5 on 8 September 2026, advertising more precise local edits, better consistency across edits, more faithful refere...
By Ankit Raj, Yuxin Zhang, Kidus Zewde, Tommy Duong, Jiaqi Gan, Xingyu Shen, Yuchen Zhou, Huaiyu Guo, Siyu Zhang, Simiao Ren
PDA++ is a unified, environment‑aware object insertion framework for remote sensing imagery that improves few‑shot and long‑tail recognition. It operates in three stages: Planning, which selects scene‑compatible poses using an affordance field; Decoupling, which conditions the background on pose to preserve object identity while adapting to the scene; and Assimilation, which aligns multi‑scale texture distributions via optimal transport to enhance local coherence. The method achieves a whole‑image FID of 6.28 and boosts average few‑shot recognition mAP50 by 17.69 points on optical data, while also improving ship detection on SAR imagery and maintaining performance under cross‑dataset transfer and amorphous‑target insertion.
By Xianchi Dong, Yingyan Hou, Chao Ren, Wanxuan Lu, Zihan Wei, Hongfeng Yu, Yixiao Wang, Chubo Deng, Xian Sun
The article examines how Byte‑Pair Encoding (BPE) tokenization handles Polish, an inflectional language, and finds that BPE tends to stabilize frequent surface fragments of grammatical exponents rather than true grammatical categories. It introduces the concept of grammatical form anchoring, showing that certain Polish verb forms can signal the speaking subject without an explicit pronoun, and highlights that language models may lack a stable grammatical "I" and can shift gender or mirror user forms. The study proposes Roclawski’s segmentation‑flexional forms as a diagnostic framework and suggests that more stable Polish modeling would require sublexical stabilization, anchoring grammatical form in the inflectional system, and maintaining the grammatical "I" in dialogue.
By Elzbieta Dawidek (University of Lower Silesia DSW Ideis)
arXiv:2607.20116v2 Announce Type: replace
Abstract: Global visual localization of unmanned aerial vehicles (UAVs) using remote-sensing reference maps has attracted increasing attention. However, diff...
By Xin Li, Siyuan Duan, Shang Wang, Zhimin Mao, Bingliang Hu, Geng Zhang
The paper introduces LDE, a framework that uses collaborative perception (CP) to generate high‑quality pseudo‑labels for unsupervised model adaptation in autonomous driving. It tackles communication limits, field‑of‑view mismatches, and label unreliability through selective feature sharing, FoV filtering, and curriculum learning. Experiments on 3D object detection show LDE surpasses pre‑trained models and existing adaptation methods.
By Yanan Ma, Yihang Tao, Zhengru Fang, Zihan Fang, Yiqin Deng, Xianhao Chen, Yuguang Fang
The paper introduces ThoughtMed-1M, a large-scale medical visual question answering dataset built from de‑identified images and clinician‑generated commentaries, designed to capture structured clinical reasoning and image‑text alignment. Using this dataset, the authors train FOLTMed, a foundational large language model that achieves state‑of‑the‑art performance on 42 medical VQA benchmarks, with a macro accuracy of 85.4% and improved factuality and similarity metrics over existing models.
By Lingxuan Hou, Yuhua Xie, Yue Hu, Yan Zhuang, Junqi Li, Chengzhi Xia, Binh Phu Nguyen, Abubakar Siddique, Minh Nguyen, Yao Hou, Yanju Bao, Kexin Liu, Ke Chen, Jianjun Sun, Zeqi Li, Trung Nguyen, Jiangli Lin
The paper introduces a benchmark for evaluating open‑source instruction‑tuned large language models (LLMs) on key‑value pair extraction from documents under both clean‑text and noisy OCR conditions. It tests decoder‑only models such as Gemma, Mistral, Qwen2.5, LLaMA 3, and DeepSeek on FUNSD, CORD, and SROIE datasets, using OCR outputs from PaddleOCR, EasyOCR, and Tesseract. Results show that while modern LLMs perform well on high‑quality text, their performance drops sharply with OCR noise, and the main determinants of success are semantic reasoning and textual fidelity, with larger models offering diminishing returns under noisy inputs.
By Zahra Anvari, Vassilis Athitsos
arXiv:2607.23238v3 Announce Type: replace
Abstract: Masked image modeling has become a dominant paradigm for SAR pre-training, yet the design of the reconstruction target remains fundamentally unsett...
By Weijie Li, Yafei Song, Yongxiang Liu, Bowen Peng, Jie Zhou, Jingyuan Xia, Wei Yang, Tianpeng Liu, Zhen Liu, Li Liu
arXiv:2609.17749v1 Announce Type: new
Abstract: A lot of expectations have been put for years on integrating domain expert knowledge in image classification models. Several approaches have been explo...
By Dieu-Donn\'e Fangnon, Diane Lingrand, Aur\'elie Liard, Marco Corneli, Antoine Pasqualini, Fr\'ed\'eric Precioso
arXiv:2609.07939v2 Announce Type: replace
Abstract: We address the problem of discovering repeated elements from a single image. In contrast to existing approaches that depend on large annotated data...
By Syrine Kalleli, Alexei A. Efros, Mathieu Aubry
arXiv:2609.19042v1 Announce Type: cross
Abstract: In medical imaging, developing robust deep learning models requires data from various domains. However, regulatory policies protecting patient privac...
By Karan R. Bagri, Tarun K. Garg, Vaanathi Sundaresan
arXiv:2609.06074v2 Announce Type: replace
Abstract: Sparse optical flow provides stable inter-frame correspondence, playing a key role in Visual Odometry (VO) and Visual-Inertial Odometry (VIO). Clas...
By Yicheng Lin, Zhipeng Fei, Yuxiu Xu, WenDong Chen, Cong Li, Bin Han
The paper investigates why large vision‑language models sometimes misclassify harmful memes, attributing failures to either missing internal evidence or poor routing of evidence to the output. Using sparse autoencoders, role‑conditioned probes, and causal interventions on Gemma‑3 and Qwen3.5, the authors show that sparse readouts consistently outperform native predictions across six harmful content benchmarks, revealing a readout gap that is largely due to routing rather than representation. The study also demonstrates that calibration‑only routing recovers most of the performance gap and that the issue persists across languages and is not solely driven by OCR signals.
By Girish A. Koushik, Diptesh Kanojia, Helen Treharne
arXiv:2609.18493v1 Announce Type: new
Abstract: Semantic labels for indoor mobile laser scanning (MLS) frames remain largely absent from current point cloud semantic segmentation benchmarks, which ma...
By Haiyang Wu, Muhammad Affan, George Vosselman, Ville Lehtola
arXiv:2609.18542v1 Announce Type: new
Abstract: 4D radar has emerged as a promising next-generation sensor for improving the robustness of autonomous driving perception systems because of its stable...
By Woo-Jin Jung, Dong-Hee Paek, Jeong-Su Park, Seung-Hyun Kong
TwinMark is a watermarking scheme that embeds a single SHAKE128 secret into a vision model using two complementary linear functionals of model-output summaries: a covariance projector (cov‑Feat) and a class‑conditional Fisher‑aligned linear carrier (cc‑FALC). These readouts cover both classifier APIs attacked by KL knowledge distillation and representation‑only hosts attacked by feature‑matching distillation, each providing a teacher‑measurable a posteriori certificate. Across 13 attacks on datasets such as CIFAR‑10, CIFAR‑100, and Mini‑ImageNet, TwinMark remains detectable on every post‑attack model that retains task utility, survives cross‑architecture distillation onto ResNet‑18/50, VGG‑16, and MobileNet‑V3, and can be ported to GNSS few‑shot, VOC detection, ISIC segmentation, and STL‑10 SimCLR.
By Redwanul Karim, Tobias Feigl, Christopher Mutschler, Felix Ott
arXiv:2609.18773v1 Announce Type: new
Abstract: Long-range infrared imaging frequently confronts dense target clusters whose diffraction-limited signatures merge into a single indistinguishable blob,...
By Mengze Xu, Zhu Liu, Weidong Sheng, Boyang Li, Yimian Dai, Ming-Ming Cheng, Jian Yang
The paper presents provable guarantees for a spectral method that recovers binary node labels on signed graphs with edge‑flip noise. It provides graph‑structure‑agnostic bounds on approximate inference accuracy and maximum angle deviation, using matrix concentration and eigenvector perturbation techniques. The results connect to the Cheeger constant and are validated with synthetic experiments, marking the first theoretical analysis of this spectral approach.
By Violet Zheng, Jean Honorio
arXiv:2609.18430v1 Announce Type: new
Abstract: Modeling physical dynamics, including how objects move, interact, and change state, is central to video world models for embodied AI. We present StrucP...
By WM Team, Enhui Ma, Kaiwen Guo, Tingrui Zhang, Wei Song, Yingshui Tan, Jianhua Xu, Tong Zhang, Kaicheng Yu