cs.CV · 2026-10-07 · No. 136
Computer Vision and Pattern Recognition, 2026-10-07.
15 new papers in cs.CV. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
15 entries-
01
4D-HOF: Hand-Object Flow Matching for Feed-Forward 4D Interaction Reconstruction
Shiqi Li, Sean Cho, Yijie Li, Fengzhi Guo, Bowen Wen, Cheng Zhang
cs.CV · cs.AI · cs.GR
Existing methods for 4D hand-object reconstruction often rely on costly per-sequence optimization, while generative approaches typically synthesize interactions from random noise, which can lead to unstable interaction prediction. We introduce 4D-HOF, a feed-forward framework that reconstructs 4D hand-object interactions from coarse but informative estimates produced by vision foundation models. Concretely, we learn a conditional flow...
-
02
Co-Evolving Paths and Flows via Path-Flow Alignment
Zeyu Michael Li, William Xingxu Chen, Xiang Cheng
cs.CV · cs.LG
We study path-flow alignment as a unified training objective for flow matching. Instead of fixing the interpolation path and learning only the velocity field, we jointly train an endpoint-preserving path network and a flow network using the same alignment loss: the flow learns to match the path velocity, and the path learns to align its velocity to the current flow. Although every fixed learned path defines a valid flow-matching objective,...
-
03
Selective Transfer of RL Updates for Visual Reasoning
Suxin Ji, Hungtao Wan, Mingjun Liu, An Zhang
cs.CV · cs.AI
Model merging provides a training-free way to transfer reasoning capabilities from language models to vision-language models (VLMs), but endpoint-based transfer can conflate pre-existing model differences with changes acquired during reasoning post-training. We instead formulate capability transfer around the training-stage update, isolating the parameter changes induced by reinforcement learning (RL). Yet transferring this update in full...
-
04
FedDermaSeg: Federated Learning for Dermatological Image Segmentation
Anabik Pal, Ganesh Patidar, Bikash Santra
cs.CV · cs.AI · cs.LG
Skin cancer is a major global health concern, and early detection and accurate lesion delineation are important for effective diagnosis and treatment planning. Automated skin lesion analysis can assist dermatologists, with lesion segmentation serving as a fundamental step in computer-aided diagnostic systems. Conventional deep learning-based segmentation models typically rely on centralized training, where images and their corresponding...
-
05
Have I Seen Enough? Frozen Video-Language Models Encode Evidence Readiness
Dan Ben-Ami, Kobi Cohen, Chaim Baskin
cs.CV · cs.CL · cs.LG
Streaming video-language models must decide not only what to answer, but whether the evidence needed for the current question has arrived. Existing systems learn that decision as a separate trigger; we ask whether an unmodified model already computes it. We show that frozen VideoLLMs carry a linearly readable evidence-readiness signal, labelled from timestamped evidence rather than from model output. It decodes in all seven models of a shared...
-
06
Beyond Perturbation Magnitude: Direction-Dependent Responses in Multimodal Geometric Representations
Yongsheng Luo, Wengan He, Yu Li, Rouying Wu, Wei Lv
cs.CV · cs.LG · cs.SD
Geometric alignment scores based on Gram determinants provide a compact way to model higher-order consistency among modalities, yet how such scores respond to modality degradation is poorly understood. This paper asks whether the response of a multimodal geometric score is determined primarily by the magnitude of the perturbation-induced displacement. Using frozen cohorts from MSR-VTT (N=878) and DiDeMo (N=980), we apply controlled video blur...
-
07
MedCORE: Criteria-Grounded Clinical Reasoning for Interpretable Medical Image Diagnosis
Asim Khan, Samee Ullah Khan, Dwarikanath Mahapatra
cs.CV · cs.AI
Clinical diagnosis is inherently a structured reasoning process, yet existing deep learning models often bypass this structure by mapping image features directly to disease labels without explicitly interrogating the morphological and textural criteria that clinicians systematically evaluate. This limits diagnostic transparency and may compromise safe clinical deployment. We present MedCORE (Medical Criteria-Oriented Reasoning and Evidence),...
-
08
Knee3DVLM: Dual-Sequence Full-Volume Vision-Language Modeling for Comprehensive Knee MRI Assessment
Maryam Baizhigitova, Andrew Seohwan Yu, Po-Hao Chen, Naveen Subhas, Sixu Chen, Xinxin Wang, Kunio Nakamura, Richard...
cs.CV · cs.AI
Vision-language models (VLMs) are increasingly being applied to three-dimensional medical imaging, but their application to knee MRI remains limited, particularly for interpreting the complementary sequences used in clinical practice. We introduce Knee3DVLM, a sequence-aware VLM that uses full-volume DESS and fluid-sensitive TSE MRI to predict 57 anatomically resolved binary diagnostic targets derived from the MRI Osteoarthritis Knee Score...
-
09
GeoPID: Decomposing and Steering Visual Information in Vision-Language Models
Seulgi Kim, Zhixiong Zhang, Xinwei Zhang, Jie Ling, Ronn Shaw
cs.CV · cs.AI
While recent vision-language models (VLMs) have shown outstanding performance across diverse applications, they tend to under-use visual information and over-rely on textual context. In this work, we propose \textsc{GeoPID}, a training-free framework that analyzes multimodal information within VLMs from a geometric perspective. \textsc{GeoPID} decomposes information into Redundant, Modality-Unique, and Synergistic components through the...
-
10
Test-Time Adaptation of Quantized ViTs via Single-Pass Quantizer-Aligned Recalibration
Hyeongheon Cha, Young D. Kwon, Sung-Ju Lee
cs.CV · cs.AI
Post-training quantization is a standard route to fitting vision transformers (ViTs) into edge compute and memory budgets, yet quantized models become especially brittle under distribution shift. Test-time adaptation (TTA) addresses such shifts without labels, but most existing approaches are poorly aligned with the constraints of quantized inference. Prevailing TTA methods recover accuracy through backpropagation, while backprop-free methods...
-
11
DIPrune: Task-Aware Token Pruning with Dual Importance for Efficient Multimodal Language Models
Shuo Yang, Changbai Li, Linlin Yang, Huobin Tan, Rongyu Chen, Tongfei Chen, Tian Wang, Sheng Xu, Baochang Zhang
cs.CV · cs.LG
Recent training-free pruning approaches for Multimodal Large Language Models (MLLMs) effectively cut computational overhead by exploiting visual redundancy or text-vision attention. However, they frequently suffer from semantic degradation due to their task-agnostic design or unreliable attention estimates. Based on our empirical analysis, we have found that this issue arises because salient tokens in shallow layers persistently suppress...
-
12
Transferable Spatial Temporal Coherence Adversarial Attack on Black-Box Vision Language Models for Autonomous Driving
Heyam Bin Jahlan Areej Alhothali Abeer Alhothali
cs.CV · cs.AI
The rapid integration of Vision Language Models (VLMs) into sensitive systems introduces critical safety vulnerabilities that remain unexplored in exist studies. While adversarial attack robustness has been extensively studied for image-based models, the susceptibility of VLMs to temporally-aware adversarial attacks against video in driving context poses a distinct and under examined threat. In this paper, we introduce novel adversarial...
-
13
Supermarket Product Detection and Recognition: Utilizing Deep Learning with Rectified Imagery
Mayank Sah, Jimson Mathew
cs.CV · cs.AI
Product Identification has sprung up to become one of the most challenging problems in the automation of the retail industry. With the new industry 5.0 standards, automated inventory management, and catalog creation tasks are vitally important. Object identification models have emerged as a viable answer with their unprecedented identification and localization accuracy. However, the close-knit rack design of supermarkets generates the problem...
-
14
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs
Yuan Feng, Qize Yang, Ruizhe Chen, Sibo Song, Haolin He, Muzhi Zhu, Zihan Liu, Yunfei Chu, Xize Cheng, Yuxuan Wang,...
cs.CV · cs.AI · cs.CL
Multimodal large language models have become the dominant paradigm for visual understanding, but incur substantial costs by encoding inputs into dense, fixed-size patch tokens. However, visual information is unevenly distributed: some regions require fine-grained detail, while others admit compact representations. Downsampling sacrifices this detail, while existing token pruning and adaptive approaches remain limited in content-adaptive...
-
15
Decide Before You Look: Learning Which Retrieved Memories Deserve Pixels
Youxing LI
cs.CV · cs.AI
Multimodal assistants answer questions from long-term memories that contain images. After retrieval, each retrieved image reaches the answering model either as pixels, at about a thousand visual tokens per image, or as a stored text proxy that often misses the detail the question asks about. We find that the benefit of pixels usually comes from one or two retrieved memories, and that it can be predicted before the answering model runs,...
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.