English
Related papers

Related papers: Vision as LoRA

200 papers

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

Traditional multimodal learning approaches require expensive alignment pre-training to bridge vision and language modalities, typically projecting visual features into discrete text token spaces. We challenge both fundamental assumptions…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Xuhui Zhan , Tyler Derr

Large pre-trained models, such as large language models (LLMs), present significant resource challenges for fine-tuning due to their extensive parameter sizes, especially for applications in mobile systems. To address this, Low-Rank…

Machine Learning · Computer Science 2024-07-18 Yuzhu Mao , Siqi Ping , Zihao Zhao , Yang Liu , Wenbo Ding

Vision-language-action (VLA) models for closed-loop robot control are typically cast under the Markov assumption, making them prone to errors on tasks requiring historical context. To incorporate memory, existing VLAs either retrieve from a…

Robotics · Computer Science 2026-03-16 Hang Li , Fengyi Shen , Dong Chen , Liudi Yang , Xudong Wang , Jinkui Shi , Zhenshan Bing , Ziyuan Liu , Alois Knoll

Processing visual data often involves small adjustments or sequences of changes, e.g., image filtering, surface smoothing, and animation. While established graphics techniques like normal mapping and video compression exploit redundancy to…

Graphics · Computer Science 2025-10-20 Anh Truong , Ahmed H. Mahmoud , Mina Konaković Luković , Justin Solomon

In this work, we introduce Libra, a prototype model with a decoupled vision system on a large language model (LLM). The decoupled vision system decouples inner-modal modeling and cross-modal interaction, yielding unique visual information…

Computer Vision and Pattern Recognition · Computer Science 2024-05-17 Yifan Xu , Xiaoshan Yang , Yaguang Song , Changsheng Xu

The integration of language instructions with robotic control, particularly through Vision Language Action (VLA) models, has shown significant potential. However, these systems are often hindered by high computational costs, the need for…

Robotics · Computer Science 2025-02-04 Marie Samson , Bastien Muraccioli , Fumio Kanehiro

Reinforcement learning (RL) has emerged as a critical paradigm for post-training Vision-Language-Action (VLA) models, enabling embodied agents to adapt and improve through environmental interaction. However, existing RL frameworks for VLAs…

Vision-language models (VLMs) pretrained on large-scale multimodal datasets encode rich visual and linguistic knowledge, making them a strong foundation for robotics. Rather than training robotic policies from scratch, recent approaches…

Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts. Multi-concept customization emerges as the challenging task within this domain. Existing approaches often rely on…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Yang Yang , Wen Wang , Liang Peng , Chaotian Song , Yao Chen , Hengjia Li , Xiaolong Yang , Qinglin Lu , Deng Cai , Boxi Wu , Wei Liu

Vision-Language-Action (VLA) models integrate visual perception, language understanding, and action decision-making for cross-modal semantic alignment, exhibiting broad application potential. However, the joint processing of…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Chuhang Liu , Yayun He , Zuheng Kang , Xiaoyang Qu , Jianzong Wang

Recently, Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on instruction-following tasks by integrating pretrained visual encoders with large language models (LLMs). However, existing approaches often…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Wayner Barrios , Andrés Villa , Juan León Alcázar , SouYoung Jin , Bernard Ghanem

Vision-language models (VLMs) lag behind text-only language models on mathematical reasoning when the same problems are presented as images rather than text. We empirically characterize this as a modality gap: the same question in text form…

Artificial Intelligence · Computer Science 2026-03-18 Saeed Khaki , Ashudeep Singh , Nima Safaei , Kamal Ginotra

Recent studies have demonstrated the effectiveness of Large Language Models (LLMs) as reasoning modules that can deconstruct complex tasks into more manageable sub-tasks, particularly when applied to visual reasoning tasks for images. In…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Ahmad Mahmood , Ashmal Vayani , Muzammal Naseer , Salman Khan , Fahad Shahbaz Khan

In this paper, we introduce Nested Low-Rank Adaptation (NoRA), a novel approach to parameter-efficient fine-tuning that extends the capabilities of Low-Rank Adaptation (LoRA) techniques. Vanilla LoRA overlooks pre-trained weight inheritance…

Machine Learning · Computer Science 2024-08-28 Cheng Lin , Lujun Li , Dezhi Li , Jie Zou , Wei Xue , Yike Guo

Vision-language models (VLMs) have shown powerful capabilities in visual question answering and reasoning tasks by combining visual representations with the abstract skill set large language models (LLMs) learn during pretraining. Vision,…

Artificial Intelligence · Computer Science 2023-09-01 Riley Tavassoli , Mani Amani , Reza Akhavian

Memory-augmented Large Language Models (LLMs) have demonstrated remarkable consistency during prolonged dialogues by storing relevant memories and incorporating them as context. Such memory-based personalization is also key in on-device…

Machine Learning · Computer Science 2025-12-05 Massimo Bini , Ondrej Bohdal , Umberto Michieli , Zeynep Akata , Mete Ozay , Taha Ceritli

Vision-language-action (VLA) models finetuned from vision-language models (VLMs) hold the promise of leveraging rich pretrained representations to build generalist robots across diverse tasks and environments. However, direct fine-tuning on…

Robotics · Computer Science 2025-09-18 Shresth Grover , Akshay Gopalkrishnan , Bo Ai , Henrik I. Christensen , Hao Su , Xuanlin Li

Vision-language models (VLMs) excel in tasks such as visual question answering and image captioning. However, VLMs are often limited by their use of pretrained image encoders, like CLIP, leading to image understanding errors that hinder…

Computer Vision and Pattern Recognition · Computer Science 2025-02-10 Aristeidis Panos , Rahaf Aljundi , Daniel Olmeda Reino , Richard E. Turner

Current vision-language-action (VLA) models, pre-trained on large-scale robotic data, exhibit strong multi-task capabilities and generalize well to variations in visual and language instructions for manipulation. However, their success rate…

Robotics · Computer Science 2025-10-17 Han Zhao , Jiaxuan Zhang , Wenxuan Song , Pengxiang Ding , Donglin Wang