English
Related papers

Related papers: Preconditioned Visual Language Inference with Weak…

200 papers

Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens, which consume a significant portion of the context window and impose a substantial computational burden. Prior work has empirically explored visual token…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Dingchen Yang , Bowen Cao , Anran Zhang , Weibo Gu , Winston Hu , Guang Chen

Medical Vision Language Pretraining (VLP) has recently emerged as a promising solution to the scarcity of labeled data in the medical domain. By leveraging paired/unpaired vision and text datasets through self-supervised learning, models…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Prashant Shrestha , Sanskar Amgain , Bidur Khanal , Cristian A. Linte , Binod Bhattarai

Vision-Language Models (VLMs) have shown remarkable performance in integrating visual and textual information for tasks such as image captioning and visual question answering. However, these models struggle with compositional generalization…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Ashwath Vaithinathan Aravindan , Abha Jha , Mihir Kulkarni

Vision Language Models excel in handling a wide range of complex tasks, including Optical Character Recognition (OCR), Visual Question Answering (VQA), and advanced geometric reasoning. However, these models fail to perform well on…

Computation and Language · Computer Science 2024-10-30 Ayush Singh , Mansi Gupta , Shivank Garg

A user pointing their phone at a supermarket shelf and asking "Which soda has the least sugar?" poses a difficult challenge for current visual Al assistants. Such queries require not only object recognition, but explicit set-based reasoning…

Multimedia · Computer Science 2026-03-18 Zehua Cheng , Wei Dai , Wenhu Zhang , Thomas Lukasiewicz , Jiahao Sun

Vision Language Models (VLMs) excel at identifying and describing objects but often fail at spatial reasoning. We study why VLMs, such as LLaVA, underutilize spatial cues despite having positional encodings and spatially rich vision encoder…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Jianing Qi , Jiawei Liu , Hao Tang , Zhigang Zhu

Large vision-language models (LVLMs) often hallucinate when language priors dominate weak or ambiguous visual evidence. Existing contrastive decoding methods mitigate this problem by comparing predictions from the original image with those…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Tian Qin , Junzhe Chen , Yuqing Shi , Tianshu Zhang , Qiang Ju , Lijie Wen

Accurately predicting human behaviors is crucial for mobile robots operating in human-populated environments. While prior research primarily focuses on predicting actions in single-human scenarios from an egocentric view, several robotic…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Utsav Panchal , Yuchen Liu , Luigi Palmieri , Ilche Georgievski , Marco Aiello

When people query Vision-Language Models (VLMs) but cannot see the accompanying visual context (e.g. for blind and low-vision users), augmenting VLM predictions with natural language explanations can signal which model predictions are…

Computation and Language · Computer Science 2026-04-23 Keyu He , Tejas Srinivasan , Brihi Joshi , Xiang Ren , Jesse Thomason , Swabha Swayamdipta

Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. However, despite showing promising performance, LVLMs suffer from hallucinations caused by language bias, leading to diminished focus on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Haozhe Zhao , Shuzheng Si , Liang Chen , Yichi Zhang , Maosong Sun , Mingjia Zhang , Baobao Chang

Fine-grained supervision based on object annotations has been widely used for vision and language pre-training (VLP). However, in real-world application scenarios, aligned multi-modal data is usually in the image-caption format, which only…

Computer Vision and Pattern Recognition · Computer Science 2023-05-09 Lisai Zhang , Qingcai Chen , Zhijian Chen , Yunpeng Han , Zhonghua Li , Zhao Cao

Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM. Our approach focuses on analyzing the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Clement Neo , Luke Ong , Philip Torr , Mor Geva , David Krueger , Fazl Barez

Vision-Language Models (VLMs) have been shown to be blind, often underutilizing their visual inputs even on tasks that require visual reasoning. In this work, we demonstrate that VLMs are selectively blind. They modulate the amount of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Wan-Cyuan Fan , Jiayun Luo , Declan Kutscher , Leonid Sigal , Ritwik Gupta

While Vision Language Models (VLMs) learn conceptual representations, in the form of generalized knowledge, during training, they are typically used to analyze individual instances. When evaluation instances are atypical, this paradigm…

Computation and Language · Computer Science 2025-10-15 Stella Frank , Emily Allaway

Vision-language-action (VLA) models have shown strong potential for generalist robot manipulation, yet they remain limited by insufficient spatial reasoning, particularly in determining where to interact in complex visual scenes. While…

Robotics · Computer Science 2026-05-26 Runze Wang , Yuqian Fu , Yu Li , Tao Lin , Tianwen Qian , Mohamed Elhoseiny , Bo Zhao , Yanwei Fu , Yu-Gang Jiang , Xiangyang Xue

Recognizing and disentangling visual attributes from objects is a foundation to many computer vision applications. While large vision language representations like CLIP had largely resolved the task of zero-shot object recognition,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-03 William Yicheng Zhu , Keren Ye , Junjie Ke , Jiahui Yu , Leonidas Guibas , Peyman Milanfar , Feng Yang

State-of-the-art (SOTA) reinforcement learning (RL) methods have enabled vision-language model (VLM) agents to learn from interaction with online environments without human supervision. However, these methods often struggle with learning…

Machine Learning · Computer Science 2025-05-22 Qingyuan Wu , Jianheng Liu , Jianye Hao , Jun Wang , Kun Shao

Recent advances in vision-language reasoning underscore the importance of thinking with images, where models actively ground their reasoning in visual evidence. Yet, prevailing frameworks treat visual actions as optional tools, boosting…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Changpeng Wang , Haozhe Wang , Xi Chen , Junhan Liu , Taofeng Xue , Chong Peng , Donglian Qi , Fangzhen Lin , Yunfeng Yan

In standard large vision-language models (LVLMs) pre-training, the model typically maximizes the joint probability of the caption conditioned on the image via next-token prediction (NTP); however, since only a small subset of caption tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-05-15 Yangyi Chen , Hao Peng , Tong Zhang , Heng Ji

Vision Language Models (VLMs) have demonstrated strong reasoning capabilities in Visual Question Answering (VQA) tasks; however, their ability to perform Theory of Mind (ToM) tasks, such as inferring human intentions, beliefs, and mental…

Computer Vision and Pattern Recognition · Computer Science 2025-04-25 Ximing Wen , Mallika Mainali , Anik Sen