cs.CV · 2026-11-14 · No. 171

Computer Vision and Pattern Recognition, 2026-11-14.

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
  1. 01

    Unbundling Multimodal Vision Encoding

    Ellis Brown, Chris Hoang, Shengyi Qian, Shang-Wen Li, Mike Lewis, Marjan Ghazvininejad, Luke Zettlemoyer, Lucas...

    cs.CV · cs.LG

    How multimodal language models should encode visual input remains up for debate. Most models use a pretrained vision encoder, while some recent recipes train the encoder from scratch with the language model or remove it entirely. Vision encoders bundle together three design choices: a visual prior from upstream pretraining, dedicated vision capacity, and pre-fusion placement of that capacity (i.e., before the multimodal backbone). Because...

    arxiv.org/abs/2611.17334 · PDF

  2. 02

    FLEX-LBP: Learning Local Binary Patterns with Exact Binary Inference for Texture Classification

    Mohamed Alimoussa, Amal El Kaid

    cs.CV · cs.LG

    Local Binary Patterns (LBP) remain among the most widely used texture descriptors, from industrial inspection to medical imaging. Yet their radius, sampling angles, color transform and thresholds are fixed by hand for each dataset. We present FLEX-LBP, which learns these parameters by backpropagation while every forward pass computes exact binary codes and hard histogram counts. A straight-through estimator acts only in the backward pass, so...

    arxiv.org/abs/2611.17302 · PDF

  3. 03

    Consistent Video-to-Video Translation via Explicit Correspondences

    Gaurav Parmar, Zhengqi Li, Richard Zhang, Jun-Yan Zhu, Srinivasa Narasimhan, Eli Shechtman, Yotam Nitzan

    cs.CV · cs.AI · cs.GR · cs.LG

    Interactive video-to-video applications require real-time generation while maintaining long-range temporal consistency. However, recent methods achieve speed by restricting attention to a fixed-length causal window. This limits long-range consistency whenever relevant history falls outside the context window. To address this limitation, we introduce vid2vid-long, a correspondence-based approach grounded in a simple observation. Video-to-video...

    arxiv.org/abs/2611.17298 · PDF

  4. 04

    MALNISI-Infused Graph Construction and Weighted Contrastive Loss based GAT for Unsupervised Representation Learning in HSI

    Soumi Sarkar, Subhadip Boral, Sarbani Palit, Ashish Ghosh

    cs.CV · cs.AI

    Hyperspectral images (HSI) possess discriminating spectral characteristics with respect to land utilization due to high-dimensional information. Recently, unsupervised representation learning using graph neural networks has unveiled these utilization-specific complex spectral relations. This article has three main contributions. First, it proposes an index, the Mean Absolute Local Neighborhood Inverse Spectral Index (MALNISI), which measures...

    arxiv.org/abs/2611.17199 · PDF

  5. 05

    STeP-C: Real-Time Neural Compression for Distributed Fiber-Optic Sensing at Scale

    Tingfeng Li, Ming-Fang Huang, Shaobo Han, Yue Tian

    cs.CV · cs.LG

    Distributed fiber-optic sensing (DFOS) technologies such as Distributed Acoustic Sensing (DAS) generate continuous, high-resolution spatio-temporal data at rates exceeding hundreds of megabytes per second, creating severe challenges for real-time storage and transmission. While neural compression methods can achieve strong rate-distortion performance on sensing data, prior approaches either require per-segment retraining incompatible with...

    arxiv.org/abs/2611.17126 · PDF

  6. 06

    Predicting Ethanol Drinking Status from Nonhuman Primate Liver Histology: A Proof of Concept for Parameter-efficient Fine-tuning in Few-Shot Vision-Language Modeling

    Amirmohammad Mohammadi, Rupak Khadka, Kathleen A. Grant, Mary Lauren Benton, Joshua Peeples

    cs.CV · cs.AI

    Combining vision-language models (VLMs) with parameter-efficient fine-tuning (PEFT) offers a promising approach to few-shot whole-slide image (WSI) classification in computational pathology. This study evaluates this approach for predicting ethanol drinking status from nonhuman primate liver histology. Adapters are evaluated against non-PEFT configurations on a subset of the Monkey Alcohol Tissue Research Resource (MATRR). All evaluated PEFT...

    arxiv.org/abs/2611.17105 · PDF

  7. 07

    Joint Null-Space Projection for Data-Free Model Merging

    Tian Xia

    cs.CV · cs.LG

    Merging independently fine-tuned checkpoints into a single multi-task model requires no data, no labels, and no gradient steps. In practice the task vectors of different tasks interfere, and the standard remedies--averaging, magnitude pruning, sign election--operate entry by entry, ignoring that each delta induces a low-dimensional update on the hidden features it acts upon. We recast merging as a subspace interference problem. For every...

    arxiv.org/abs/2611.17103 · PDF

  8. 08

    AURA 2.0: From User-Driven Responses to Model-Initiated Conversations in Streaming Video

    Shuhan Li, Huankang Guan, Xintong Guo, Yang Bo, Yuyang He, Dunyuan Xu, Jingyan Chen, Fang Liu, Tsz Kin Wan, Jinpeng...

    cs.CV · cs.AI

    Most AI assistants respond only when prompted, remaining silent even when events in the video stream offer meaningful opportunities for conversation. To move beyond purely user-driven interaction, we present AURA 2.0, a streaming video large language model that introduces three core upgrades to AURA. The key advance is Model-Initiated Conversation (MIC), which enables the model to identify topics worth discussing in the evolving visual stream...

    arxiv.org/abs/2611.17048 · PDF

  9. 09

    ElasticDino: Dense Semantic Features Using Elastic Deformations

    Ulysse Mizrahi, Sean Zaretzky, Dov Danon, Amit H. Bermano

    cs.CV · cs.AI

    Vision transformers (ViTs) serve as the backbone for countless vision tasks, including dense prediction tasks, such as segmentation and depth estimation, even though the quadratic complexity of self-attention severely limits feature resolution and induces spatial artifacts. In this work, we introduce ElasticDino, a lightweight adapter which produces high-resolution feature maps, adhering to the fine details of the input image. As a key...

    arxiv.org/abs/2611.16984 · PDF

  10. 10

    Evaluating Video LLMs' Understanding of Corner Cases in Autonomous Driving

    Gabriel Manalu, Minh Son Hoang, Hyeontaek Hwang, Jaesung Lee, Hyojin Choi, Tran Tuan Phong, Seon Kwon Kim, Saad...

    cs.CV · cs.AI

    Natural language explanations promised by modern Video Large Language Models (Video LLMs) offer autonomous driving systems a path toward detailed scene description and interpretable decision making on the road. While recent benchmarks have begun assessing these models on driving scenes, they mainly target routine traffic conditions and general comprehension tasks based on existing driving datasets and therefore fail to evaluate model...

    arxiv.org/abs/2611.16767 · PDF

  11. 11

    ORCA:Orthogonal Residual Consensus Alignment for Multi-View Clustering

    Xiaojian Ding, Xian Li, Xiaoying Zhu, Lin Zhao, Kaixiang Wang

    cs.CV · cs.AI

    Deep multi-view clustering often suffers from redundant information accumulation during fusion and indiscriminate alignment across representation levels. We propose Orthogonal Residual Consensus Alignment (ORCA) to address these challenges. Its semantic incremental recurrent fusion module extracts cross-view orthogonal residuals as non-redundant increments and adaptively weights recurrent states through divergence-guided gating. Its...

    arxiv.org/abs/2611.16749 · PDF

  12. 12

    PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models

    Yuxuan Chen, Xiaojie Li, Hao Chen, Juncheng Ma, Kewei Zhang, Zhongjing Du, Guoqiang Wei, Fangfang Wang, Zhen Dong,...

    cs.CV · cs.AI

    Video generation models produce visually realistic videos but still struggle with physical dynamics and causal consistency. Learning from generated videos requires fine-grained physical supervision, yet reliable quality judgments, correction pairs, and controlled variations are difficult to obtain. Large language models (LLMs) possess physical knowledge, but struggle to reliably guide video generation models in producing their training...

    arxiv.org/abs/2611.16748 · PDF

  13. 13

    From Foundation VLM to Versatile Driving VLM: A Triplet Incremental Training Approach

    Shengtao Wu, Zichao Dong, Weixuan Qiao, Xiaolu Liu, Xin Zhan, Junbo Chen, Jianke Zhu

    cs.CV · cs.AI

    Adapting general Vision-Language Models (VLMs) to Autonomous Driving (AD) is thought to require heavy 3D spatial priors or intrusive architectural overhauls to compensate for a lack of spatial grounding. In this work, we present a counterintuitive pilot study: off-the-shelf general VLMs already exhibit remarkable adaptability across diverse driving tasks, while precise metric depth remains the primary missing link, a bottleneck readily...

    arxiv.org/abs/2611.16727 · PDF

  14. 14

    When Chekhov's Gun Fires Anyway: Over-Realization in Text-to-Image Models

    Jiahao Huang, Kon Woo Kim, Song-Duo Ma, Yuka Kitamura, Felix Wagner, Yunshan Huang, Sunisth Kumar, Xanh Ho, Yun-Ang...

    cs.CV · cs.AI

    In text-to-image generation, a target that the prompt mentions often appears in the generated image in a way the prompt does not call for. We call this failure over-realization. Mental-spaces theory points to the situations where it can happen: under a negation, inside what a character believes or imagines, as the vehicle of a figurative comparison, or behind a viewpoint that hides the target. Prior work has studied only negation in depth,...

    arxiv.org/abs/2611.16630 · PDF

  15. 15

    Towards Democratising Low-Data Medical Image Classification: CPU-Trainable ZACH-ViT and Its Geometric Variants

    Athanasios Angelakis

    cs.CV · cs.LG

    Medical image classification in resource-constrained settings must contend with limited annotations and computational capacity. We evaluate four ZACH-ViT variants with linear, Euclidean prototype, Poincare and spherical heads alongside two compact multiple-instance-learning baselines. All models are trained from scratch with fewer than 260,000 parameters across seven MedMNIST+ datasets and three external benchmarks (PCam, ISIC2017 and...

    arxiv.org/abs/2611.16608 · PDF

  16. 16

    DesignTaste: Benchmarking AI-Generator Visual Design Against Award-Wining Works

    Zhou Chen, JiaXiang Li, DanYing Pan, Ye Li, TianRui Yang, EnBao Zhang, YaNan Xiao, LiXin Sun, Anqi Liu, Dong Zhao,...

    cs.CV · cs.AI

    Text-to-image benchmarks commonly assess text-image alignment or overall preference. Whether models can produce good designs when a brief leaves the appearance open remains less well understood. We introduce DesignTaste, a visual design benchmark that compares generated images with award-winning works. From these works and their publicly available context, we derive 403 design briefs: 100 poster tasks from 100 Beste Plakate 2025 and 303 tasks...

    arxiv.org/abs/2611.16442 · PDF

  17. 17

    PhysCapBench: A Cross-Domain Benchmark for Physically Grounded Video Captioning

    Haofeng Wang, Pengcheng Wen, Ruiqi Li, Yuhao Zhang, Tiange Zhang, Boren Zheng, Xuanyi Liu, Siyu Tao, Danni Yu, Gan...

    cs.CV · cs.AI

    Physical AI aims to learn transferable physical knowledge from real-world experience to understand, predict, and act in the physical world. Internet videos and embodied demonstrations provide complementary observations of motion, interaction, and state evolution. A foundational data challenge is to measure and preserve this physical information as training supervision. In video-language pretraining, captions express observed processes in...

    arxiv.org/abs/2611.16424 · PDF

  18. 18

    TransXplainRRG: A Radiologist-Evaluated LVLM for Chest Radiograph Report Generation

    Chayan Mondal, Duc-Son Pham, Tele Tan, Ashu Gupta, Vincent T. Y. Tiong, Shreya Ghosh, Tom Gedeon

    cs.CV · cs.AI

    Recent advancements in Large Vision-Language Models (LVLM) enhance X-ray report generation, but often neglect clinical context, overlook workflow integration, and lack explainability, which hinders clinical adoption due to interpretability and reliability concerns. This paper addresses the dual challenges of performance and expert explainability in automated X-ray report generation for clinical AI applications. Our proposed approach,...

    arxiv.org/abs/2611.16393 · PDF

  19. 19

    ReliaGuard: Reconstruction-Aware Watermarking for Source Attribution and Blind Edit Localization

    Hailong Wang, Wuzheng Tan, Zixin Zhang, Xujun Fang, Fengjuan Gong

    cs.CV · cs.AI · cs.CR

    Generative image editing facilitates content creation but complicates source attribution and edit verification. Existing watermarking methods combine copyright protection with tamper localization, yet background reconstruction can weaken spatial evidence even when source identifiers remain recoverable. We propose ReliaGuard, a reconstruction-aware watermarking framework for source attribution and blind edit localization. The writer optimizes...

    arxiv.org/abs/2611.16368 · 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.