cs.CV · 2026-07-22 · No. 61
Computer Vision and Pattern Recognition, 2026-07-22.
19 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
19 entries-
01
Appearance Pointers -- Multimodal Region Control of Diffusion Transformers
Rahul Sajnani, Yulia Gryaditskaya, Radomír Měch, Srinath Sridhar, Matheus Gadelha
cs.CV · cs.AI · cs.GR
Controllable image generation remains challenging for creative professionals, who often require precise regional control over materials, object identities, and spatial arrangements that cannot be reliably achieved through text prompting alone. Diffusion Transformers (DiTs) can natively ingest heterogeneous tokens stemming from texts and images, but they lack mechanisms for determining where and how these tokens should influence the output. We...
-
02
PathAgentBench: Benchmarking Evidence-Seeking Vision-Language Models on Whole-Slide Pathology Image
Dankai Liao, Tianyi Zhang, Yufeng Wu, Xinyue Zhang, Qiaochu Xue, Zeyu Liu, Dachun Zhao, Linghan Cai, Yueming Jin
cs.CV · cs.AI
Whole-slide image (WSI) diagnosis requires identifying diagnostically relevant regions, examining them across magnifications, and integrating multi-scale evidence. However, most existing pathology benchmarks evaluate models on pre-cropped patches or pre-extracted slide features, leaving their ability to acquire evidence directly from gigapixel WSIs largely untested. We introduce PathAgentBench, a benchmark for evaluating evidence-seeking...
-
03
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
Fan Jiang, Zhaoxu Sun, Mengchao Wang, Ziyu Zhu, Chiyu Wang, Yunpeng Zhang, Wenlin Liu, Yun Wang, Xue Zheng, Rui Sun,...
cs.CV · cs.AI · cs.LG
We present ABot-World-0, an action-conditioned video world model for real-time, long-horizon closed-loop interaction, supported by a multi-source data infrastructure spanning AAA games, simulation engines, and internet videos to learn controllable world dynamics. WorldExplorer performs agent-driven collection guided by training feedback, while a unified pipeline applies 14 deterministic quality checks, VLM-based assessment, and synchronized...
-
04
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
Xinjie Zhang, Peng Zhang, Shicheng Zheng, Jinghao Guo, Zhaoyang Jia, Yifei Shen, Xun Guo, Yuxuan Luo, Jiahao Li,...
cs.CV · cs.AI · cs.LG · cs.MM · eess.IV
Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to-image generation and instruction-based image editing. The stack is built from two co-designed components: Mage-VAE, a lightweight high-fidelity latent tokenizer, and a Native-Resolution Multimodal Diffusion Transformer trained with rectified flow matching. Mage-VAE...
-
05
Now You See the Hate: Adaptive View Retrieval for Hidden Hateful Illusions
Qianpu Chen, Derya Soydaner
cs.CV · cs.AI
Hateful optical illusions expose a serious gap in current multimodal safety systems. On original-view hateful illusions, previous work shows that six moderation classifiers achieve at most 20.9 to 24.5% accuracy and nine state-of-the-art VLMs remain at or below 10.2% with illusion-aware prompting, leaving most hidden hate undetected. We formulate hidden hateful illusion detection as a perceptual retrieval problem and propose Adaptive View...
-
06
FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling
Jialong Zuo, Haotong Zuo, Shiwei Zhang, Xiang Wang, Chen Li, Nong Sang, Changxin Gao, Xiang Bai
cs.CV · cs.AI
Translating novels into films poses a grand challenge for generative artificial intelligence, requiring conversion of abstract literary prose into long-form, multi-scene visual narratives. While current video generation models excel at short, single-scene clips within narrow temporal and spatial contexts, novel-to-film generation operates in a more complex regime, demanding long-duration content across diverse scenes with dynamically evolving...
-
07
CoGoal3D: Collaborative 3D Object Detection with 3D-Aware Fusion and Refinement
Zhihao Yang, Zhiyu Xiang, Peng Xu, Tianyu Pu, Kai Wang, Eryun Liu, Dongping Zhang, Yong Ding
cs.CV · cs.AI
V2X collaborative object detection features overcoming the limitations of single-vehicle systems by aggregating environmental features from multiple collaborative agents. However, existing mainstream V2X perception methods mainly focus on 2D BEV object detection. When 3D detection task is concerned, inferior results are obtained because they ignore the 3D spatial misalignment caused by differing height and attitude among the collaborators. In...
-
08
Benchmarking Deep Learning Approaches for AEC Engineering Drawing Layout Detection and Information Extraction
Tianyang Huang, Alessio Lombardi, Ahmed Elnagar, Ahmed Zalouk, George Paul, Sepehr Najjarpour, Arvid Sigurdsson,...
cs.CV · cs.CE · cs.LG
Information Extraction (IE) from Architecture, Engineering, and Construction (AEC) drawings remains hindered by manual inefficiency, while Layout Detection, a vital 'middleware' organizing graphical and textual hierarchies, is underexplored. General document layout models, optimized for text-centric content, lack validation on engineering drawings. This study constructs a custom AEC-specific layouts dataset and benchmarks five deep learning...
-
09
SWITi: Quantifying and Reducing Tiling Artifacts with Sliding Window Inner Tiling
Federico Carrara, Aman Kukde, Melisande Croft, Joran Deschamps, Florian Jug
cs.CV · cs.AI
SWITi is a test-time method for reducing artifacts in tiled predictions, particularly for neural networks that learn posterior distributions from which solutions are sampled at inference time. Tiled predictions are unavoidable for large image data, and artifacts arise whenever tiles are smaller than a network's receptive field and when tiles are independent posterior samples. SWITi averages overlapping sliding-window predictions, so...
-
10
Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model
Sibo Wang, Jie Zhang, Shiguang Shan, Xilin Chen, Wen Gao
cs.CV · cs.AI
While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks. Existing defense methods predominantly target single-task scenarios (e.g., zero-shot classification) and consequently lack generalizability across various multimodal tasks. To address this limitation, we propose a dual...
-
11
Local Label-Informed Feature Transfer for Generating Ground-Truth Medical Images: A Comparison of GAN- and Diffusion-Based Approaches
Rick Wilming, Irem Ozseker, Luca Matteo Cornils, Ahcène Boubekki, Benedict Clark, Danny Panknin, Stefan Haufe
cs.CV · cs.LG
Validating Explainable Artificial Intelligence (XAI) methods in medical imaging requires ground-truth data with known locations of informative features. However, current approaches rely on expert annotations, which are prone to labeling errors, or on hand-crafted artificial perturbations superimposed onto healthy images to mimic lesions or malignant features, which lack clinical realism. We present Local Label-Informed Feature Transfer...
-
12
OPD-IAD: From Language Judgment to Industrial Anomaly Detection via On-Policy Self-Distillation
Shuimu Chen, Jing Jin, Nan Su, Hongbo Xu, Zebang Cheng, Wenming Yang, Fei Ma, Guijin Wang
cs.CV · cs.AI
Large vision-language models (LVLMs) have recently shown strong potential for industrial anomaly detection (IAD) by providing image-level anomaly judgments and interpretable defect reasoning. However, current LVLM-based IAD methods still struggle to produce precise pixel-level anomaly maps from generated language judgments. We aim to achieve precise pixel-level localization while using language as guidance rather than letting it dominate the...
-
13
Bounding Boxes to Improve Small Language Model Performance on Vision-Based Grading Tasks
Lachlan McGinness
cs.CV · cs.AI · cs.CL
The deployment of Small Language Models (SLMs) in educational settings offers significant advantages in terms of privacy, cost, and scalability. However, SLMs often struggle with complex vision-based tasks, such as grading handwritten student exams, due to the high computational cost of processing large images and the visual distractions present on a full page. In this paper, we investigate whether cropping student responses using bounding...
-
14
Decoupled Pipeline with Proposal Reranking and Score Fusion for Positive-Unlabeled Marine Species Detection
Robert James Brock, Sebastian Maximilian Krupa, Jason Kahei Tam
cs.CV · cs.AI · cs.LG
The FathomNetCLEF 2026 competition combines underwater object detection and fine-grained marine species classification under a positive-unlabeled evaluation setting. The provided training labels are sparse, while the hidden test set is out-of-distribution relative to the training imagery, creating both annotation incompleteness and source-shift challenges. We describe DS@GT ARC's multi-stage system developed for this setting while keeping...
-
15
Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Models
Gautam Rajendrakumar Gare, Jia Shi, Zhiqiu Lin, Deepak Pathak, John Galeotti, Deva Ramanan
cs.CV · cs.AI · cs.LG · eess.IV
A popular route to interpretable zero-shot classification asks a large language model (LLM) to describe each class name and prompts CLIP with the resulting descriptors. We show that these descriptors carry little visual evidence of their own: removing the class name from the prompt collapses ImageNet accuracy from 59.5% to 15.5%. The diagnosis is that the descriptors are conditioned on the label rather than on the images, so they describe the...
-
16
Cross-Dataset Generalization in Breast MRI Tumor Classification via Class-Wise Dataset Mixing
Mohammad Ali Dadrast, Hamid Usefi
cs.CV · cs.LG
Breast MRI is highly sensitive for detecting breast tumors, but exams contain many slices and require substantial reading time. Deep learning models often perform well on internal splits but can fail across institutions because of domain shift and dataset-origin bias. We study this failure mode for binary breast MRI tumor classification. EfficientNet-B3 and WaveViT-Small are trained using Duke Breast Cancer MRI and fastMRI, and evaluated only...
-
17
Deep Learning Estimation of Sex, Age, Height, and Weight from CT-derived Digitally Reconstructed Radiographs
Tomohiro Kikuchi, Kohei Yamamoto, Yukihiro Nomura, Yosuke Yamagishi, Takeharu Yoshikawa, Toshiaki Akashi, Jun...
cs.CV · cs.AI
Purpose: To develop and validate a deep learning ensemble for estimating adult sex, age, height, and weight from coronal digitally reconstructed radiographs (DRRs) generated from diagnostic CT. Materials and Methods: This retrospective study included 128,621 CT examinations from 80,004 adults at nine institutions in Japan. Three multitask models-ConvNeXt-Base, ViT-Base/16, and MaxViT-Base-were fine-tuned using coronal DRRs and combined by...
-
18
Norm or Direction? Decoding Vision Mambas for High-Resolution Vision
Jin Yu, Juyoun Park
cs.CV · cs.AI
Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones. However, MambaOut demonstrates that a Gated CNN block can match or exceed VMamba on image classification, questioning the necessity of SSMs for vision. This raises a fundamental question: do VMamba and MambaOut encode visual information differently at the representation level? To investigate,...
-
19
Recti-Q: Feature-Space Rectification for Out-of-Distribution-Robust Quantized Perception in Edge Robotics
Hamidreza Yaghoubi Araghi, Parastoo Pilevar, Ming C. Lin
cs.CV · cs.LG · cs.RO
Robotic perception pipelines increasingly rely on large vision backbones deployed on SWaP-constrained edge platforms, making post-training quantization (PTQ) attractive for real-time inference. However, while PTQ often preserves clean in-distribution accuracy, we show that it can substantially degrade reliability under deployment-relevant distribution shifts (e.g., sensor noise, severe weather, and novel operating environments), creating a...
This edition is part of The Daily Abstract — cs.CV archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.