cs.CV · 2026-07-28 · No. 67
Computer Vision and Pattern Recognition, 2026-07-28.
21 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
21 entries-
01
ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
Hangjie Yuan, Yichen Qian, Zhiwei Tang, Xianzhe Xu, Lirong Wu, Sicheng Yang, Jinwang Wang, Pengju Wang, Zhitao Zeng,...
cs.CV · cs.AI · cs.CL
Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundamentally a vision-centric challenge: models must absorb knowledge from heterogeneous 2D and 3D medical images, and evaluation protocols must align with radiologists' clinical practice and provide an accurate, fine-grained and factualness-driven assessment. In this paper, we introduce ClinFusion,...
-
02
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
Bingnan Li, Haozhe Wang, Haozhong Xiong, Fangtai Wu, Jinpeng Yu, Yang Shi, Jiaming Liu, Ruihua Huang
cs.CV · cs.AI · cs.LG
On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guidance (CFG), a default component of modern diffusion systems, remains poorly understood. Existing OPD methods naturally extend velocity matching to the CFG-composed prediction, directly matching teacher and student guided velocities. We show that this objective is...
-
03
KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability
Krithi Shailya, Ananya Lakshmi Ravi, Venkatanathan K. V., Sowmya S. Sundaram, Gokul S. Krishnan, Aditi Anand,...
cs.CV · cs.AI
Computer vision models have become highly effective for medical applications, yet their black-box nature continues to undermine clinician trust. In clinical workflows, chest X-ray classifiers are increasingly paired with Vision-Language Models (VLMs) to generate natural-language explanations. However, these systems add linguistic fluency without addressing the underlying opacity of the visual model. With the emergence of Kolmogorov-Arnold...
-
04
Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification
Francisco Mena, Dino Ienco, Roberto Interdonato, Cassio F. Dantas, Simon Besnard
cs.CV · cs.AI · cs.LG
Multi-modal classification leverages complementary information across diverse data sources to enhance predictive performance. However, real-world scenarios subject to operational constraints, such as sensor failures or privacy restrictions, lead to inconsistent modality availability between training and inference times. To handle missing modalities, prior studies have mainly covered bimodal data setups and focused on designing robust fusion...
-
05
MMOE: Modernizing Diffusion Transformers with Efficient Expert Design
Yanhao Jia, Jiepeng Wang, Haibin Huang, Chi Zhang, Erik Cambria, Xuelong Li
cs.CV · cs.GR · cs.LG
Modern large language models scale successfully by pairing capacity growth with efficiency, keeping per-token and deployment costs under control as capacity grows. AIGC Foundation Models (AFMs), especially diffusion-transformer backbones, have begun to adopt sparse experts, but recent efforts mostly enlarge total parameter counts and sparsity ratios without importing the efficiency mechanisms that made LLM scaling practical, so generation...
-
06
CADER: Confidence-Aware Dynamic Evidence Reasoning for Long-Video Understanding
Jinlong Yang, Wenhao Zhang, Kuanwei Lin, Sijie Cheng
cs.CV · cs.AI
Long-video understanding increasingly relies on large vision-language models and tool-augmented reasoning, but most systems apply the same inference procedure to every example regardless of difficulty. This uniform strategy invokes unnecessary tool-assisted processing for easy questions and provides limited control when difficult questions require fine-grained temporal evidence. We propose CADER (Confidence-Aware Dynamic Evidence Reasoning),...
-
07
The Visual Bottleneck: Sparse-Frame Adaptation of MLLMs for Joint Spatial-Temporal Video Grounding
Jiameng Zhang, Srikanth Madikeri
cs.CV · cs.AI
Large-scale video platforms process millions of uploads hourly, requiring moderation systems that can localize when and where policy violations occur within each video. Processing every frame is infeasible at scale, so systems are constrained to sparse inputs of 8 to 16 frames per video. Yet state-of-the-art multimodal large language models (MLLMs) are pretrained on dense sequences of hundreds of frames, creating a fundamental mismatch...
-
08
EgoPlay: Event-Triggered Video Editing for Egocentric Streams
Jinjie Mai, Gordon Guocheng Qian, Willi Menapace, Arpit Sahni, Chaoyang Wang, Ashkan Mirzaei, Runjia Li, Sergey...
cs.CV · cs.AI
We introduce EgoPlay, an event-triggered video-to-video editor for egocentric streams, obtained by fine-tuning a pretrained V2V diffusion transformer on event-conditioned data built primarily from Ego4D. Given a monocular video and an event-triggered prompt of the form "when X happens, do Y," EgoPlay infers whether and when event X occurs, preserves pre-event frames, and applies edit Y only to the post-event continuation. Rather than...
-
09
DecoupleMix: Decoupled Ratio Search and Convex Allocation for Scalable VLM Data Recipes
Jiahao Xie, Zhongbin Guo, Qianle Wang, Ruiqi Lu, Dongling Xiao, Wanxuan Sun, Cheng Yang
cs.CV · cs.AI
While data curation for Vision Language Models (VLMs) is increasingly active, public practice for constructing pretraining mixtures remains largely heuristic: practitioners stack datasets that pass quality filters, set cross-domain ratios by intuition, and lack a principled, attributable criterion for admitting new data, while frontier recipes remain undisclosed. We formulate data construction as a systematic mixture-optimization problem and...
-
10
ESRVS: Extreme Semi-Supervised Retinal Vessel Segmentation with a Single Annotated Image
Mingzhi Xu, Yizhe Zhang
cs.CV · cs.AI · cs.LG
Learning from minimal human supervision is a long-standing goal in medical image analysis, where dense expert annotations are costly. We study retinal vessel segmentation in an extreme semi-supervised setting with one annotated image and a pool of unlabeled images. We propose ESRVS, which selects a representative reference image for manual annotation and transfers vessel cues using target-domain-adapted DINOv3 features. ESRVS constructs a...
-
11
Bigger or Cheaper? Scale and Quantization Effects on Uncertainty Signals in Vision-Language Models Under Image Degradation
M M Asif Ferdous
cs.CV · cs.CL · cs.LG
Vision-language models (VLMs) deployed on consumer hardware must decide when to answer and when to defer, and that decision depends on having a confidence signal that tracks correctness. A practitioner with a fixed memory budget faces a choice between a small model at full precision, the same small model quantized, and a larger model quantized into the same footprint -- three configurations that push the confidence signal in opposing...
-
12
FilmBench: A Film-Grade Benchmark for Cinematic Video Generation
Shengyi Wang, Niantong Li, Guangzheng Hu, Hong Qi, Fei Ding, Weixu Qiao, Jinlin Wang, Xiaotong Lv, Peng Han, Zimeng...
cs.CV · cs.AI
Progress in video generation keeps narrowing the visual gap between AI-generated and professionally produced footage, yet most benchmarks still draw prompts from web sources or LLM templates and score them with untrained, generic multimodal models. More fundamentally, their evaluation taxonomies remain rudimentary (overall visual quality, coarse text alignment and temporal smoothness) rather than the professional Cinematic Language criteria...
-
13
BeyondFusion: Self-Aligned Latent Diffusion for Calibration-Free Infrared Super-Resolution and Infrared-Visible Fusion
Minchong Chen, Xiaoyun Yuan, Minyu Cao, Jianing Zhang, Jun Zhang, Shuyang Liu, Xiaokang Yang
cs.CV · cs.LG · physics.optics
Mobile infrared-visible imaging typically pairs a compact infrared sensor with a high-resolution visible camera for complementary perception. While cross-sensor misalignment caused by different optics, viewpoints, fields of view, and exposure timings hinders practical deployment. In this paper, we propose BeyondFusion, a unified latent diffusion framework for calibration-free visible-guided infrared super-resolution and infrared-visible...
-
14
LU-500: A Logo Benchmark for Concept Unlearning
Keyu Li, Jin Gao, Jialing Zhang, Dequan Wang
cs.CV · cs.AI
Concept unlearning is increasingly used to limit the reproduction of protected or unsafe visual concepts in text-to-image models. Existing evaluations, however, mostly study targets that dominate the whole image, such as styles, broad object categories, or portrait-like identities, leaving company logos comparatively underexamined. Logos create a different failure mode: a small localized mark can carry the entire protected concept, must be...
-
15
When Low CER is Not Enough: An Analysis of Hallucinations in Vision-Language OCR Systems on Historical Uruguayan Documents
Marina Gardella, Camilo Mari{ñ}o, Diego Belzarena, Ignacio Ram{í}rez, Gregory Randall, Jean-Michel Morel
cs.CV · cs.LG · eess.IV
Optical Character Recognition (OCR) is a key component in the digitization of historical archives. Recently, Vision-Language Models (VLMs) have emerged as strong alternatives to traditional OCR systems, achieving state-of-the-art performance on standard benchmarks. However, their suitability for archival transcription remains insufficiently understood. In this work, we benchmark traditional OCR systems and VLM-based approaches on the Berrutti...
-
16
MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning
Tuan-An To, Yuk-Kwan Wong, Tuan-Anh Vu, Ziqiang Zheng, Sai-Kit Yeung
cs.CV · cs.AI
Recent Vision-Language Models (VLMs) have achieved remarkable success in visual understanding, driven by the growing availability of high-quality image-text pairs. However, the performance of VLMs often degrades in the video domain due to the essential need for temporal understanding and the scarcity of large-scale annotated video data. In this work, we focus on marine video understanding, which brings further challenges: first, it requires...
-
17
Disentangling Semantic Attention from Structural Bias in the Attention Manifold
Pengkun Jiao, Bin Zhu, Jingjing Chen, Yu-gang Jiang
cs.CV · cs.AI
The empirical success of attention mechanism in Multimodal Large Language Models (MLLMs) often obscures its inherent, subtle flaws. Specifically, MLLMs consistently exhibit disproportionate attention toward certain semantically uninformative visual tokens, a phenomenon termed "register" or "Visual Attention Sinks." While existing inference intervention methods attempt to identify these sink tokens and redistribute their attention weights,...
-
18
Multimodal Semantic-Probabilistic Objectness for Open World Object Detection
Weijun Tian, Rui Liu
cs.CV · cs.AI
Open-world object detection (OWOD) requires a detector to recognize known categories, discover unnamed objects from unseen categories, and incrementally learn newly annotated classes. PROB improves unknown discovery by modeling class-agnostic probabilistic objectness in the decoder-query space. However, visual objectness alone cannot determine whether an object-like query corresponds to a hard known instance, an unseen-category object, or...
-
19
DuoAD: Leveraging [CLS] Dual Characteristics for Training-Free Few-Shot Anomaly Detection
Jyun-Ze Tang, Po-Han Huang, Ming-Ching Chang, Chih-Fan Hsu, Jeng-Lin Li
cs.CV · cs.AI
Vision foundation models have enabled strong training-free anomaly detection (AD). However, most existing approaches rely primarily on independent local patch features, leaving the global contextual information encoded by Vision Transformers (ViTs) underexploited. In this work, we identify the dual characteristics of the ViT [CLS] token: its embedding provides anomaly-invariant global semantic representation, while its attention maps...
-
20
SimBEV2X: A Large-Scale Dataset and Data Generation Tool for Multi-Task Vehicle-to-Everything Cooperative Perception
Goodarz Mehr, Sepideh Gohari, Montasir Abbas, Azim Eskandarian
cs.CV · cs.LG · cs.MA · cs.RO
Cooperative perception through vehicle-to-everything (V2X) communication can overcome the inherent physical limitations of individual autonomous vehicles, such as occlusions and limited sensor range. However, the development of robust V2X algorithms, particularly those relying on unified spatial representations like bird's-eye view (BEV) representation, is hampered by the lack of large-scale, multi-modal, multi-task datasets. Moreover,...
-
21
Long-Tailed Medical Image Classification
Nathanael Ren, Saagar Arya
cs.CV · cs.LG
In this paper, we examine the difficulties of using standard techniques for medical image classification due to long-tailed distributions (wherein rarer conditions have very few samples) resulting in bias towards diagnosing common diseases and away from rarer diseases. We then discuss and implement deep learning models with techniques such as augmentation to minimize error, especially from rarer diseases. We evaluate various different models...
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.