English
Related papers

Related papers: What Happens Before Decoding? Prefill Determines G…

200 papers

With the development of multimodal reasoning models, Computer Use Agents (CUAs), akin to Jarvis from \textit{"Iron Man"}, are becoming a reality. GUI grounding is a core component for CUAs to execute actual actions, similar to mechanical…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Miaosen Zhang , Ziqiang Xu , Jialiang Zhu , Qi Dai , Kai Qiu , Yifan Yang , Chong Luo , Tianyi Chen , Justin Wagle , Tim Franklin , Baining Guo

Visual grounding, the task of linking textual queries to specific regions within images, plays a pivotal role in vision-language integration. Existing methods typically rely on extensive task-specific annotations and fine-tuning, limiting…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Liqin Luo , Guangyao Chen , Xiawu Zheng , Yongxing Dai , Yixiong Zou , Yonghong Tian

Vision-and-Language Navigation (VLN) requires grounding instructions, such as "turn right and stop at the door", to routes in a visual environment. The actual grounding can connect language to the environment through multiple modalities,…

Computation and Language · Computer Science 2019-06-11 Ronghang Hu , Daniel Fried , Anna Rohrbach , Dan Klein , Trevor Darrell , Kate Saenko

Pre-trained LLMs that are further trained with image data perform well on vision-language tasks. While adding images during a second training phase effectively unlocks this capability, it is unclear how much of a gain or loss this two-step…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Sedrick Keh , Jean Mercat , Samir Yitzhak Gadre , Kushal Arora , Igor Vasiljevic , Benjamin Burchfiel , Shuran Song , Russ Tedrake , Thomas Kollar , Ludwig Schmidt , Achal Dave

Graphical user interface (GUI) grounding is a key capability for computer-use agents, mapping natural-language instructions to actionable regions on the screen. Existing Multimodal Large Language Model (MLLM) approaches typically formulate…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Shijie Zhou , Viet Dac Lai , Hao Tan , Jihyung Kil , Wanrong Zhu , Changyou Chen , Ruiyi Zhang

By combining natural language understanding, generation capabilities, and breadth of knowledge of large language models with image perception, recent large vision language models (LVLMs) have shown unprecedented visual reasoning…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Siming Yan , Min Bai , Weifeng Chen , Xiong Zhou , Qixing Huang , Li Erran Li

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first…

Computer Vision and Pattern Recognition · Computer Science 2025-07-03 Aarti Ghatkesar , Ganesh Venkatesh

Vision-Language Navigation in Continuous Environments (VLNCE), where an agent follows instructions and moves freely to reach a destination, is a key research problem in embodied AI. However, most existing approaches are sensitive to…

Computer Vision and Pattern Recognition · Computer Science 2026-02-23 Josh Qixuan Sun , Huaiyuan Weng , Xiaoying Xing , Chul Min Yeum , Mark Crowley

Long-context inference in decoder-only language models is costly because long prompts are processed during Prefill, cached at every layer, and repeatedly attended to during autoregressive Decode. We introduce \emph{Shallow Prefill, dEEp…

Artificial Intelligence · Computer Science 2026-05-08 Jungsuk Oh , Hyeseo Jeon , Hyunjune Ji , Kyongmin Kong , Jay-Yoon Lee

Large vision language models (VLMs) increasingly claim reasoning skills, yet current benchmarks evaluate them in single-turn or question answering settings. However, grounding is an interactive process in which people gradually develop…

Computation and Language · Computer Science 2025-09-05 Saki Imai , Mert İnan , Anthony Sicilia , Malihe Alikhani

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved performance on tasks such as visual grounding and visual question answering. However, the reasoning processes of these models remain largely opaque;…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Haobo Yuan , Yueyi Sun , Yanwei Li , Tao Zhang , Xueqing Deng , Henghui Ding , Lu Qi , Anran Wang , Xiangtai Li , Ming-Hsuan Yang

Most visual grounding solutions primarily focus on realistic images. However, applications involving synthetic images, such as Graphical User Interfaces (GUIs), remain limited. This restricts the development of autonomous computer…

Human-Computer Interaction · Computer Science 2025-07-21 El Hassane Ettifouri , Jessica López Espejel , Laura Minkova , Tassnim Dardouri , Walid Dahhane

Vision Language Models (VLMs) mix visual tokens and text tokens. A puzzling issue is the fact that visual tokens most related to the query receive little to no attention in the final layers of the LLM module of VLMs from the answer tokens,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Parsa Esmaeilkhani , Longin Jan Latecki

GUI agents powered by Multimodal Large Language Models (MLLMs) have demonstrated impressive capability in understanding and executing user instructions. However, accurately grounding instruction-relevant elements from high-resolution…

Artificial Intelligence · Computer Science 2026-05-18 Yichao Liu , Huawen Shen , Liu Yu , Shiyu Liu , Zeyu Chen , Yu Zhou

Gaze following requires both scene understanding and gaze reasoning to localize the gaze target of an in-scene person. Recently, vision foundation models (VFMs) have demonstrated strong performance on this task, enabling simpler…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Shijing Wang , Yaping Huang , Chaoqun Cui , David Wong , Yihua Cheng , Alexandros Neophytou , Hyung Jin Chang

Vision language models (VLMs) have shown promising reasoning capabilities across various benchmarks; however, our understanding of their visual perception remains limited. In this work, we propose an eye examination process to investigate…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Nam Hyeon-Woo , Moon Ye-Bin , Wonseok Choi , Lee Hyun , Tae-Hyun Oh

Multi-view spatial reasoning remains difficult for current vision-language models. Even when multiple viewpoints are available, models often underutilize cross-view relations and instead rely on single-image shortcuts, leading to fragile…

Computation and Language · Computer Science 2026-03-09 Xingjian Tao , Yiwei Wang , Yujun Cai , Yifan Song , Jing Tang

In this work, we explore neat yet effective Transformer-based frameworks for visual grounding. The previous methods generally address the core problem of visual grounding, i.e., multi-modal fusion and reasoning, with manually-designed…

Computer Vision and Pattern Recognition · Computer Science 2022-06-15 Jiajun Deng , Zhengyuan Yang , Daqing Liu , Tianlang Chen , Wengang Zhou , Yanyong Zhang , Houqiang Li , Wanli Ouyang

Despite the rapid progress of multimodal large language models in building Graphical User Interface (GUI) agents, their real-world task completion is fundamentally bottlenecked by a lack of world knowledge about GUI operations. Existing…

Computation and Language · Computer Science 2026-05-28 Zheng Wu , Chengcheng Han , Zhengxi Lu , Tianjie Ju , Yanyu Chen , Qi Gu , Xunliang Cai , Zhuosheng Zhang

Latent visual reasoning involves visual evidence more directly in multimodal reasoning by inserting continuous latent tokens before textual generation. However, the necessity of these latent tokens at inference remains ambiguous. We show…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Dongyao Zhu , Zhen Wang , Xi Xiao , Han Jiang , Saeed Vahidian , Wei-Lun Chao , Tanya Berger-Wolf , Yu Su , Raju Vatsavai , Jianyang Gu