cs.CV · 2026-10-12 · No. 141

Computer Vision and Pattern Recognition, 2026-10-12.

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

    Hide and Seek: HIDE Concepts to SEEK explanations for black box models

    Bhanu Tokas, Rahul Nair, Rockwell Jackson, Hannah Kerner

    cs.CV · cs.AI · cs.LG

    Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods interpret models using human-understandable concepts. Existing concept-based methods can only interpret classification and regression models. They require access to model weights or large concept-annotated datasets, and most methods cannot provide image-level attribution. We propose Hide and Seek...

    arxiv.org/abs/2610.13935 · PDF

  2. 02

    SpatialASM: Internalizing Active Mentalization for Spatial Reasoning

    Yuhong Liu, Shenxi Wu, Junyi Chi, Beichen Zhang, Xuanlang Dai, Jiaqi Wang, Yuhang Zang, Dahua Lin

    cs.CV · cs.AI

    When solving complex spatial reasoning tasks, ordinary humans naturally revisit the scenes from task-relevant viewpoints and mentally reconstruct the spatial layouts from those viewpoints. But can Large Vision-Language Models (LVLMs) proactively think in the same way? We term this ability Active Spatial Mentalization (ASM), an intrinsic component of visual intelligence that remains substantially underdeveloped in current LVLMs. To bridge this...

    arxiv.org/abs/2610.13832 · PDF

  3. 03

    Shortcut Learning in Geospatial Foundation Model Embeddings for Cross-Disaster Damage Assessment

    Ali Shibli, Andrea Nascetti, Yifang Ban

    cs.CV · cs.LG

    Geospatial foundation models can support disaster damage assessment, but high accuracy on familiar disasters may hide shortcut learning: prediction from event or scene characteristics rather than evidence that transfers to a new disaster. We study embeddings from TerraMind, Prithvi-EO-2.0, DOFA, and DINOv3 on the multi-disaster datasets xView2 and BRIGHT. Holding out an entire disaster, instead of randomly splitting image tiles, reduces mean...

    arxiv.org/abs/2610.13766 · PDF

  4. 04

    LAPT-Scale: Scaling Embodied Policies with Latent Action Pre-Training on Human Videos

    Zhiyuan Xiang, Peidong Liu, Mingyang Li, Jiawei Li, Wenhow Li, Wenbo Ding, Xiang Deng

    cs.CV · cs.AI · cs.RO

    Scaling generalist robotic policies is limited by the high cost of collecting embodied interaction data. Large-scale egocentric human videos offer a rich alternative, but they lack robot action labels, and existing action annotation methods are often noisy under real-world visual complexity and diverse manipulation dynamics. We introduce LAPT-Scale, a scalable latent action pre-training paradigm with two components: LAPT-Scale-LAM learns...

    arxiv.org/abs/2610.13732 · PDF

  5. 05

    X-AVDD: Cross-Attentive Audio-Visual Dataset Distillation

    Saumyaranjan Mohanty, Aravind Reddy, Konda Reddy Mopuri

    cs.CV · cs.LG · cs.SD

    Audio-visual dataset distillation aims to synthesize a small dataset from a large paired audio-visual dataset, while nearly preserving the training utility for neural networks. Existing approaches such as DM and AVDD face two critical limitations: 1) they are memory-intensive, making them difficult to scale to complex architectures and higher samples-per-class (SPC) settings, and 2) they often fail to preserve strong cross-modal semantic...

    arxiv.org/abs/2610.13687 · PDF

  6. 06

    S-Space: Exploring Spatial Workspace in Multimodal Language Models

    Zhiyuan Shi, Xiang Li, Xingzhuo Guo, Shangchen Miao, Weiliang Chen, Qiyu Dai, Jinshan Ren, Jiangran Lyu, Fangfu Liu,...

    cs.CV · cs.CL · cs.LG

    Multimodal language models (MLLMs) exhibit promising spatial reasoning capabilities, yet the internal mechanisms supporting them remain poorly understood. We uncover S-Space, a linear representation subspace in which object-token representations encode continuous coordinates along horizontal, vertical, and distance axes. Although we identify these axes by differentiating spatial-answer scores with respect to object-token activations, S-Space...

    arxiv.org/abs/2610.13527 · PDF

  7. 07

    When MLLMs miss what humans read: diagnosing and learning to read squint text

    Chen Peng, Shan Huang, Jianbo Huang, Linrui Qin, Qibo Sun, Mengwei Xu

    cs.CV · cs.AI

    Multimodal LLMs can fail to read text embedded in an image's coarse structure (text a human recovers by squinting) and report that no text is present. We name this class Squint Text and study it as a recognition deficiency, motivated by cases from a production moderation pipeline. We introduce SquintBench, comprising 1076 production-derived moderation images, and SquintCtrl, a controlled synthetic suite for mechanism diagnosis. Frozen-weight...

    arxiv.org/abs/2610.13465 · PDF

  8. 08

    Sonic-AMG: Streaming Human Motion Generation from Spatial Audio

    Jingcheng Ni, Zekun Li, Zhiyang Dou, Xiaoyan Cong, Ziyao Zeng, Hongyang Du, Randall Balestriero, Taku Komura, Srinath Sridhar

    cs.CV · cs.GR · cs.LG · cs.RO · cs.SD

    Modeling human reactions to spatial audio requires understanding both what is heard and where it comes from. Prior work generates motion offline from complete acoustic and spatial input sequences. Humans, however, react to sounds without knowing what they will hear next. We present Sonic-AMG, to our knowledge the first framework for streaming human motion generation from spatial audio. The model encodes acoustic content and body-relative...

    arxiv.org/abs/2610.13300 · PDF

  9. 09

    Decoding Register Tokens Preserves Global Scene Details

    David Jacob Drexlin, Julius Hense, Jonas Dippel

    cs.CV · cs.LG

    Pretrained vision transformers learn structured image representations spanning spatial patch tokens and non-spatial tokens. Recent analyses suggest that non-spatial register tokens encode global scene properties such as illumination, blur, and style. Yet patch-based image decoders discard these outputs, leaving the decoder to recover image appearance from patches alone. We investigate whether retaining register features improves decoding when...

    arxiv.org/abs/2610.13299 · PDF

  10. 10

    CV-OPD: Contrastive Vision On-policy Distillation

    Haowei Wang, Hao Lin, Qi Zhu, Jiayi Ji, Deyi Ji, Liujuan Cao, Rongrong Ji

    cs.CV · cs.LG · cs.MM

    On-policy distillation (OPD) reveals versatility and convenience during VLM post-training, providing dense supervision for student from teacher. However, we observed an anomaly that the distilled VLM could still answer the questions accurately even when the related visual regions were masked or replaced with noise. Building on this observation, our quantitative and qualitative experiments demonstrate that OPD, which uses the answer as a hint,...

    arxiv.org/abs/2610.13264 · PDF

  11. 11

    Golden Anchor for Video Generation

    Jinyuan Xu, Shitong Shao, Lichen Bai, Zikai Zhou, Guoxi Huang, Nantheera Anantrasirichai, Zeke Xie

    cs.CV · cs.LG

    Video generation supports digital content creation, with applications in virtual avatars, AI-driven filmmaking, interactive game engines, and world models. State-of-the-art systems achieve controllability primarily through image-to-video (I2V) generation, in which an injected anchor image determines the identity, composition, and style of the resulting video. In modern pipelines, this anchor is synthesized by a text-to-image (T2I) generator....

    arxiv.org/abs/2610.13217 · 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.