English
Related papers

Related papers: Do Foundation Models Know Geometry? Probing Frozen…

200 papers

This work investigates the fundamental fragility of state-of-the-art Vision-Language Models (VLMs) under basic geometric transformations. While modern VLMs excel at semantic tasks such as recognizing objects in canonical orientations and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Jason Qiu , Zachary Meurer , Xavier Thomas , Deepti Ghadiyaram

Visual grounding seeks to localize the image region corresponding to a free-form text description. Recently, the strong multimodal capabilities of Large Vision-Language Models (LVLMs) have driven substantial improvements in visual…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Seil Kang , Jinyeong Kim , Junhyeok Kim , Seong Jae Hwang

Multimodal Large Language Models (MLLMs), which couple pre-trained vision encoders and language models, have shown remarkable capabilities. However, their reliance on the ubiquitous Pre-Norm architecture introduces a subtle yet critical…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Bozhou Li , Xinda Xue , Sihan Yang , Yang Shi , Xinlong Chen , Yushuo Guan , Yuanxing Zhang , Wentao Zhang

Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual…

Machine Learning · Computer Science 2025-07-09 Wenyi Wu , Zixuan Song , Kun Zhou , Yifei Shao , Zhiting Hu , Biwei Huang

Shouldn't language and vision features be treated equally in vision-language (VL) tasks? Many VL approaches treat the language component as an afterthought, using simple language models that are either built upon fixed word embeddings…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Andrea Burns , Reuben Tan , Kate Saenko , Stan Sclaroff , Bryan A. Plummer

Medical Vision-Language Models can give different yes or no answers to rephrasings of the same clinical question. We study this in MedGemma-4B using PSF-Med Sadanandan and Behzadan (2025), which provides paraphrase pairs for systematic…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Binesh Sadanandan , Vahid Behzadan

Vision-Language-Action (VLA) models show promise for robotic control, yet performance in complex household environments remains sub-optimal. Mobile manipulation requires reasoning about global scene layout, fine-grained geometry, and…

Robotics · Computer Science 2026-03-25 Ruisen Tu , Arth Shukla , Sohyun Yoo , Xuanlin Li , Junxi Li , Jianwen Xie , Hao Su , Zhuowen Tu

Vision-language-action (VLA) models inherit rich visual-semantic priors from pre-trained vision-language backbones, but adapting them to robotic control remains challenging. Full fine-tuning (FFT) is prone to overfitting on downstream…

Robotics · Computer Science 2026-05-11 Yuhua Jiang , Junjie Lu , Xinyao Qin , Xiaoyu Chen , Kaixin Wang , Feifei Gao , Li Zhao

Vision-language models (VLMs) have enabled strong zero-shot classification through image-text alignment. Yet, their purely visual inference capabilities remain under-explored. In this work, we conduct a comprehensive evaluation of both…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Illia Volkov , Nikita Kisel , Klara Janouskova , Jiri Matas

Large Language Models (LLMs) perform internal computations in continuous vector spaces yet produce discrete tokens -- a fundamental mismatch whose geometric consequences remain poorly understood. We develop a mathematical framework that…

Machine Learning · Computer Science 2026-03-25 Mohamed A. Mabrok

Reliable deployment of language models requires two capabilities that appear distinct but share a common geometric foundation: predicting whether a model will accept targeted behavioral control, and detecting when its internal structure…

Machine Learning · Computer Science 2026-04-30 Prashant C. Raju

Parameter-efficient fine-tuning enables fast personalization of text-to-image diffusion models, but composing multiple custom concepts remains challenging due to representation interference. Existing modular methods either rely on expensive…

Machine Learning · Computer Science 2026-05-22 Javad Parsa , Enis Simsar , Amir Joudaki , Thomas Hofmann , André M. H. Teixeira

Graph foundation models represent a transformative paradigm for learning transferable representations across diverse graph domains. Recent methods leverage large language models to unify graph and text modalities into a shared…

Machine Learning · Computer Science 2025-12-23 Heng Zhang , Tianyi Zhang , Yuling Shi , Xiaodong Gu , Yaomin Shen , Haochen You , Zijian Zhang , Yilei Yuan , Jin Huang

Large Language Models (LLMs) show strong generalization across diverse tasks, yet the internal decision-making processes behind their predictions remain opaque. In this work, we study the geometry of hidden representations in LLMs through…

Machine Learning · Computer Science 2025-11-26 Abhinav Joshi , Divyanshu Bhatt , Ashutosh Modi

Embedded numeric anchors on images systematically bias Vision-Language Model quality judgments across six VLMs from five architectural families (ANOVA eta^2 = 0.18-0.77, all p < 0.001). Anchor effects are 2.5x larger than severe image…

Artificial Intelligence · Computer Science 2026-05-13 M. Shalankin

Despite strong performance on vision-language tasks, Multimodal Large Language Models (MLLMs) struggle with mathematical problem-solving, with both open-source and state-of-the-art models falling short of human performance on visual-math…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 William Rudman , Michal Golovanevsky , Amir Bar , Vedant Palit , Yann LeCun , Carsten Eickhoff , Ritambhara Singh

With the rapid improvement of machine learning (ML) models, cognitive scientists are increasingly asking about their alignment with how humans think. Here, we ask this question for computer vision models and human sensitivity to geometric…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Zekun Wang , Sashank Varma

Remote sensing has become a vital tool across sectors such as urban planning, environmental monitoring, and disaster response. While the volume of data generated has increased significantly, traditional vision models are often constrained…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Jia Yun Chua , Argyrios Zolotas , Miguel Arana-Catania

A robot resolving ``put the cup on that one'' must fuse gesture, language, and scene geometry, yet 3D grounding benchmarks only partially capture this regime: descriptions are written post-hoc, gestures are templated, or pointing is staged…

Robotics · Computer Science 2026-05-26 Anna Deichler

Benchmark accuracy is often implicitly assumed to reflect grounded visual understanding in vision-language models (VLMs), yet it remains unclear to what extent such scores truly reflect reliance on visual evidence. Motivated by a surprising…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Zixuan Lan , Luzhe Sun , Matthew R. Walter , Jiawei Zhou