cs.CV · 2026-10-20 · No. 149

Computer Vision and Pattern Recognition, 2026-10-20.

11 new papers in cs.CV. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

11 entries
  1. 01

    Reinforcement Learning with Visually Attributable On-Policy Self-Distillation

    Shiao Xie, Siyu Chen, Jianwei Lv, Xiandong Li, Yujin Wang

    cs.CV · cs.AI

    Multimodal reinforcement learning with verifiable rewards (RLVR) provides reliable task-level supervision, yet offers limited guidance for localizing errors in visual reasoning. On-policy self-distillation (OPSD) complements this supervision with dense token-level corrections from a privileged teacher equipped with an evidence-centered visual view. However, the resulting corrections may conflate visual evidence with non-visual shifts induced...

    arxiv.org/abs/2610.26856 · PDF

  2. 02

    Mise-en-Video: Fine-Grained 3D Control for Multi-Shot Video Generation

    Yingshuang Zou, Xiaoyu Shi, Yawen Luo, Ziang Li, Qinghe Wang, Mengfei Li, Chengfeng Zhao, Xintao Wang, Pengfei Wan,...

    cs.CV · cs.AI

    Recent advances in text-to-video generation have enabled high-fidelity single-shot synthesis, yet practical storytelling creation requires multi-shot videos with both strong inter-shot consistency and fine-grained controllability. Existing multi-shot video generation approaches achieve strong consistency but still fall short in controllability. In this paper, we propose Mise-en-Video (MeV), a highly controllable multi-shot video generation...

    arxiv.org/abs/2610.26801 · PDF

  3. 03

    LaMER: Language-Conditioned Multi-Expert Routing for Weakly Supervised Referring Expression Comprehension

    Yu Yu Chang, Tzu-Hsuan Weng, Youssef Mohamed Amin, Mohaned Ahmed Elsayed, Hung-Hsuan Chen, Min-Te Sun, Sherine Shawky

    cs.CV · cs.CL · cs.LG

    Referring Expression Comprehension (REC) localizes the image region described by a natural language expression, underpinning applications such as autonomous navigation, human-robot interaction, and medical image analysis. Under weak supervision, REC is challenged by the visual-linguistic semantic gap and the difficulty of inferring region-text correspondences from coarse image-level signals alone. Moreover, no single visual encoder captures...

    arxiv.org/abs/2610.26404 · PDF

  4. 04

    TriScore: Post-Hoc Out-of-Distribution Detection with Energy, Boundary Probes, and Transform Consistency

    Ege Gursoy, Nicolas Mansard

    cs.CV · cs.LG

    Post-hoc out-of-distribution detection usually relies on a single signal extracted from a frozen classifier, such as confidence, energy, features, or gradients. This dependence becomes fragile under classifier-level adversarial shift, where the shift can preserve the detector's chosen cue while changing the model's decision behavior. We investigate whether this failure mode can be mitigated by combining complementary detection criteria...

    arxiv.org/abs/2610.26323 · PDF

  5. 05

    MCDA: Multi-View Graph Contrastive Learning with Dynamic Topology Augmentation for Functional MRI Analysis

    Hao Zhang, Xiaoyun Liu, Shuo Huang, Yue Ma, Liang Cao, Mingxia Liu, Li Zhang

    cs.CV · cs.AI

    Resting-state fMRI (rs-fMRI) is a vital non-invasive tool for diagnosing brain disorders and uncovering pathological mechanisms. However, existing graph contrastive learning (GCL) methods often underexploit augmentation histories across training epochs and the relationships among different augmented views. In this paper, we introduce a topology-guided Multi-view graph Contrastive learning framework with Dynamic graph topology Augmentation...

    arxiv.org/abs/2610.26322 · PDF

  6. 06

    RECAP: Reciprocal Sparse Attention and Hierarchical Caching for Efficient Video Diffusion

    Tiange Xu, Kai Liu, Linghe Kong, Yulun Zhang

    cs.CV · cs.LG

    Diffusion transformers generate high-quality videos but remain computationally expensive. Sparse attention and temporal caching reduce computation within and across denoising steps, respectively, offering a natural composition. However, predictions produced with sparse attention become sources for temporal reuse, coupling their errors along the sampling trajectory. We observe that improving the accuracy of these sources recovers fidelity...

    arxiv.org/abs/2610.26244 · PDF

  7. 07

    GeoEdit: Adversarial De-Evidencing for Silent Geoprivacy Protection via Image Editing

    Yu Yan, Shengjia Cheng, Fei Ma, Zhe Wang, Peng Chen

    cs.CV · cs.AI

    Recent efforts have demonstrated the strong capabilities of Multimodal Large Reasoning Models (MLRMs) in geographic reasoning. By jointly analyzing subtle visual cues, these models can infer the locations of photos, thus enabling doxing even by non-expert adversaries. Existing defense methods struggle to balance the shareability of photos with effective protection, and often fail to sufficiently disrupt the implicit geo-evidence chains...

    arxiv.org/abs/2610.26194 · PDF

  8. 08

    How Robust Are Prognostic Radiomic Features? Comparing Selection Techniques on Pooled Glioblastoma Cohorts

    Yannick Sodonougbo, Marlene Schnieders, Alexia Rizoudis, Santiago Cepeda, Frank Kramer, Dominik Müller

    cs.CV · cs.AI · q-bio.QM

    Radiomic survival studies in glioblastoma report heterogeneous prognostic features, but how much of this stems from the methodology itself is rarely examined. We analysed the association of 463 radiomic, anatomical and clinical features from pre-treatment MRI with overall survival in 705 IDH-wildtype glioblastoma patients from three public cohorts, using three techniques: a log-rank test after median split, univariate Cox regression (both...

    arxiv.org/abs/2610.26095 · PDF

  9. 09

    Not All Similarity Is Leakage: Distribution-Aware Identity Leakage Assessment in Synthetic Face Datasets

    Paweł Borsukiewicz, Daniele Lunghi, Wendkûuni C. Ouédraogo, Fadi Boutros, Jacques Klein, Tegawendé F. Bissyandé

    cs.CV · cs.AI

    Synthetic data provides the means for more ethical and less biased facial recognition. Nonetheless, the limitations of generative models and the conditioning process they rely on pose a risk of identity leakage, resulting in synthetic samples that are overly similar to those seen in a generator's training set, mitigating privacy benefits. In this work, we show that previously proposed approaches are affected by two key limitations: high...

    arxiv.org/abs/2610.26077 · PDF

  10. 10

    TamedFlow: Trajectory-Aware Distillation\\for Teacher-Assisted Diffusion Sampling

    Shuaiqi Cheng, Jiahao Zhang, Boyuan Gu, Siyu You, Yuxi Chen, Haiying Xu, Zexin Lu, Huiyu Zhou, Xuming Hu

    cs.CV · cs.AI

    Diffusion Transformers (DiTs) deliver high-fidelity image and video generation, but inference requires many sequential model evaluations. Two acceleration strategies are increasingly important: model compression makes each evaluation cheaper, while adaptive inference avoids selected teacher computation through reuse, forecasting, or speculative execution. Their combination, however, is brittle: directly applying the evaluated adaptive methods...

    arxiv.org/abs/2610.26025 · PDF

  11. 11

    FrameGRPO: Incentivizing Video Reasoning via Multi-Frame Rollouts and Temporal Credit

    Jiaxuan Sun, Biao Wang, Shuai Li

    cs.CV · cs.AI

    Reinforcement learning with verifiable rewards, particularly Group Relative Policy Optimization (GRPO), has improved video reasoning in multimodal large language models. However, standard video GRPO varies only linguistic trajectories while conditioning every rollout in a group on the same sampled frames, which can produce homogeneous rewards and weaken group-relative learning when the shared visual evidence is insufficient or distracting. We...

    arxiv.org/abs/2610.26022 · PDF

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.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.