paper-with-me

홈 › Papers

Visual Instruction Pretraining for Domain-Specific Foundation Models

2025-09-22 · Yuxuan Li, Yicheng Zhang, Wenhao Tang, Yimian Dai, Ming-Ming Cheng, Xiang Li, Jian Yang arxiv

Modern computer vision is converging on a closed loop in which perception, reasoning and generation mutually reinforce each other. However, this loop remains incomplete: the top-down influence of high-level reasoning on the foundational learning of low-level perceptual features is not yet underexplored. This paper addresses this gap by proposing a new paradigm for pretraining foundation models in downstream domains. We introduce Visual insTruction Pretraining (ViTP), a novel approach that directly leverages reasoning to enhance perception. ViTP embeds a Vision Transformer (ViT) backbone within a Vision-Language Model and pretrains it end-to-end using a rich corpus of visual instruction data curated from target downstream domains. ViTP is powered by our proposed Visual Robustness Learning (VRL), which compels the ViT to learn robust and domain-relevant features from a sparse set of visual tokens. Extensive experiments on 16 challenging remote sensing and medical imaging benchmarks demonstrate that ViTP establishes new state-of-the-art performance across a diverse range of downstream tasks. The code is available at https://github.com/zcablii/ViTP.

📄 PDF Abstract BibTeX arXiv:2509.17562

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Supervised Fine-tuning in turn Improves Visual Foundation Models

2024-01-18 · Xiaohu Jiang, Yixiao Ge, Yuying Ge, Dachuan Shi 외

Image-text training like CLIP has dominated the pretraining of vision foundation models in recent years. Subsequent efforts have been made to introduce region-level visual learning into CLIP's pretraining but face scalab…

Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube

2020-04-29 · EMNLP 2020 11 · Jack Hessel, Zhenhai Zhu, Bo Pang, Radu Soricut

Pretraining from unlabelled web videos has quickly become the de-facto means of achieving high performance on many video understanding tasks. Features are learned via prediction of grounded relationships between visual c…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1

Domain Adapted Large Language Models for Additive Manufacturing

2026-03-23 · Peter Pak, Amir Barati Farimani arxiv

This work presents a collection of multi-modal domain adapted large language models built upon the instruction tuned variants of open weight models (Gemma 3, Qwen 3, Gemma 4) using a relatively small dataset of around 50…

The Construction of Instruction-tuned LLMs for Finance without Instruction Data Using Continual Pretraining and Model Merging

2024-09-30 · Masanori Hirano, Kentaro Imajo

This paper proposes a novel method for constructing instruction-tuned large language models (LLMs) for finance without instruction data. Traditionally, developing such domain-specific LLMs has been resource-intensive, re…

Continual Pretraining

Implicit Affordance Acquisition via Causal Action-Effect Modeling in the Video Domain

2023-12-18 · Hsiu-Yu Yang, Carina Silberer

Affordance knowledge is a fundamental aspect of commonsense knowledge. Recent findings indicate that world knowledge emerges through large-scale self-supervised pretraining, motivating our exploration of acquiring afford…

World Knowledge