English
Related papers

Related papers: Attention-driven GUI Grounding: Leveraging Pretrai…

200 papers

To perform tasks specified by natural language instructions, autonomous agents need to extract semantically meaningful representations of language and map it to visual elements and actions in the environment. This problem is called…

Graphical user interface (GUI) grounding, the process of mapping human instructions to GUI actions, serves as a fundamental basis to autonomous GUI agents. While existing grounding models achieve promising performance to simulate the mouse…

Human-Computer Interaction · Computer Science 2026-01-13 Zeyi Liao , Yadong Lu , Boyu Gou , Huan Sun , Ahmed Awadallah

Despite the significant progress in multimodal large language models (MLLMs), their high computational cost remains a barrier to real-world deployment. Inspired by the mixture of depths (MoDs) in natural language processing, we aim to…

Computer Vision and Pattern Recognition · Computer Science 2024-10-18 Yaxin Luo , Gen Luo , Jiayi Ji , Yiyi Zhou , Xiaoshuai Sun , Zhiqiang Shen , Rongrong Ji

Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM…

Machine Learning · Computer Science 2026-02-03 Parmida Davarmanesh , Ashia Wilson , Adityanarayanan Radhakrishnan

Temporal language grounding (TLG) aims to localize a video segment in an untrimmed video based on a natural language description. To alleviate the expensive cost of manual annotations for temporal boundary labels, we are dedicated to the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Yuechen Wang , Wengang Zhou , Houqiang Li

Using Large Language Models (LLMs) to process graph-structured data is an active research area, yet current state-of-the-art approaches typically rely on multi-step pipelines with Graph Neural Network (GNN) encoders that compress rich…

Machine Learning · Computer Science 2026-05-12 Dario Vajda

Multi-modal Large Language Models (MLLMs) integrate visual and linguistic reasoning to address complex tasks such as image captioning and visual question answering. While MLLMs demonstrate remarkable versatility, MLLMs appears limited…

Computation and Language · Computer Science 2025-03-07 Wenke Huang , Jian Liang , Xianda Guo , Yiyang Fang , Guancheng Wan , Xuankun Rong , Chi Wen , Zekun Shi , Qingyun Li , Didi Zhu , Yanbiao Ma , Ke Liang , Bin Yang , He Li , Jiawei Shao , Mang Ye , Bo Du

Despite the existing evolution of Multimodal Large Language Models (MLLMs), a non-neglectable limitation remains in their struggle with visual text grounding, especially in text-rich images of documents. Document images, such as scanned…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Ming Li , Ruiyi Zhang , Jian Chen , Chenguang Wang , Jiuxiang Gu , Yufan Zhou , Franck Dernoncourt , Wanrong Zhu , Tianyi Zhou , Tong Sun

Multi-modal large language models (MLLMs) have achieved remarkable success in fine-grained visual understanding across a range of tasks. However, they often encounter significant challenges due to inadequate alignment for fine-grained…

Computer Vision and Pattern Recognition · Computer Science 2024-11-15 Wei Wang , Zhaowei Li , Qi Xu , Linfeng Li , YiQing Cai , Botian Jiang , Hang Song , Xingcan Hu , Pengyu Wang , Li Xiao

We present Simplified Text-Attributed Graph Embeddings (STAGE), a straightforward yet effective method for enhancing node features in Graph Neural Network (GNN) models that encode Text-Attributed Graphs (TAGs). Our approach leverages…

Computation and Language · Computer Science 2024-07-19 Aaron Zolnai-Lucas , Jack Boylan , Chris Hokamp , Parsa Ghaffari

Multimodal Large Language Models (MLLMs) have shown strong performance in multi-image cross-modal retrieval, yet suffer from severe position bias, where predictions are dominated by input order rather than semantic relevance. Through…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Mingtao Xian , Yifeng Yang , Qinying Gu , Xinbing Wang , Nanyang Ye

Large Language Models (LLMs) have demonstrated excellent capabilities in composing various modules together to create programs that can perform complex reasoning tasks on images. In this paper, we propose TANGO, an approach that extends the…

Artificial Intelligence · Computer Science 2024-12-17 Filippo Ziliotto , Tommaso Campari , Luciano Serafini , Lamberto Ballan

Large language models (LLMs) have been proposed as powerful tools for detecting software vulnerabilities, where task-specific fine-tuning is typically employed to provide vulnerability-specific knowledge to the LLMs. However, existing…

Software Engineering · Computer Science 2025-07-22 Ruijun Feng , Hammond Pearce , Pietro Liguori , Yulei Sui

This work studies self-supervised graph learning for text-attributed graphs (TAGs) where nodes are represented by textual attributes. Unlike traditional graph contrastive methods that perturb the numerical feature space and alter the…

Machine Learning · Computer Science 2024-06-19 Yi Fang , Dongzhe Fan , Daochen Zha , Qiaoyu Tan

Fine-grained multimodal capability in Multimodal Large Language Models (MLLMs) has emerged as a critical research direction, particularly for tackling the visual grounding (VG) problem. Despite the strong performance achieved by existing…

Computer Vision and Pattern Recognition · Computer Science 2025-08-21 Weitai Kang , Weiming Zhuang , Zhizhong Li , Yan Yan , Lingjuan Lyu

The language-guided robot grasping task requires a robot agent to integrate multimodal information from both visual and linguistic inputs to predict actions for target-driven grasping. While recent approaches utilizing Multimodal Large…

Robotics · Computer Science 2025-02-10 Houjian Yu , Mingen Li , Alireza Rezazadeh , Yang Yang , Changhyun Choi

GUI grounding aims to align natural language instructions with precise regions in complex user interfaces. Advanced multimodal large language models show strong ability in visual GUI grounding but still struggle with small or visually…

Artificial Intelligence · Computer Science 2025-12-02 Aiden Yiliu Li , Bizhi Yu , Daoan Lei , Tianhe Ren , Shilong Liu

Spatial awareness is key to enable embodied multimodal AI systems. Yet, without vast amounts of spatial supervision, current Multimodal Large Language Models (MLLMs) struggle at this task. In this paper, we introduce TWIST & SCOUT, a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Aritra Bhowmik , Mohammad Mahdi Derakhshani , Dennis Koelma , Yuki M. Asano , Martin R. Oswald , Cees G. M. Snoek

Grounding natural language queries in graphical user interfaces (GUIs) poses unique challenges due to the diversity of visual elements, spatial clutter, and the ambiguity of language. In this paper, we introduce DiMo-GUI, a training-free…

Artificial Intelligence · Computer Science 2025-09-08 Hang Wu , Hongkai Chen , Yujun Cai , Chang Liu , Qingwen Ye , Ming-Hsuan Yang , Yiwei Wang

Large language models (LLMs) have recently been introduced to graph learning, aiming to extend their zero-shot generalization success to tasks where labeled graph data is scarce. Among these applications, inference over text-attributed…

Machine Learning · Computer Science 2025-06-10 Haoyu Wang , Shikun Liu , Rongzhe Wei , Pan Li