ZERO: Industry-ready Vision Foundation Model with Multi-modal Prompts

• URL: http://arxiv.org/abs/2507.04270v4
• Date: Fri, 07 Nov 2025 06:42:08 GMT
• Title: ZERO: Industry-ready Vision Foundation Model with Multi-modal Prompts
• Abstract summary: Superb AI introduces ZERO, an industry-ready vision foundation model.<n> ZERO is trained on a compact yet representative 0.9 million annotated samples from a proprietary billion-scale industrial dataset.<n> ZERO is the first vision foundation model explicitly built for domain-specific, zero-shot industrial applications.
• Score: 1.2744523252873352
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Foundation models have revolutionized AI, yet they struggle with zero-shot deployment in real-world industrial settings due to a lack of high-quality, domain-specific datasets. To bridge this gap, Superb AI introduces ZERO, an industry-ready vision foundation model that leverages multi-modal prompting (textual and visual) for generalization without retraining. Trained on a compact yet representative 0.9 million annotated samples from a proprietary billion-scale industrial dataset, ZERO demonstrates competitive performance on academic benchmarks like LVIS-Val and significantly outperforms existing models across 37 diverse industrial datasets. Furthermore, ZERO achieved 2nd place in the CVPR 2025 Object Instance Detection Challenge and 4th place in the Foundational Few-shot Object Detection Challenge, highlighting its practical deployability and generalizability with minimal adaptation and limited data. To the best of our knowledge, ZERO is the first vision foundation model explicitly built for domain-specific, zero-shot industrial applications.

Related papers

• Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselines [50.471211036005286]
  We introduce a Large-Scale Multi-Modal Industrial Open-Closed benchmark (MMIOC-1M)<n> MMIOC-1M is the first unified largest benchmark supporting both open-vocabulary and closed-set industrial detection.<n>We propose a Refined Text-Visual Prompt Network (RTVPNet) that incorporates three key innovations.
  arXiv  Detail & Related papers  (2026-06-06T03:06:10Z)
• Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models [15.709482146201283]
  A simple linear classifier trained on the frozen features of modern Vision Foundation Models establishes a new state-of-the-art.<n>We show that this baseline matches specialized detectors on standard benchmarks but also decisively outperforms them on in-the-wild datasets.<n>We conclude by advocating for a paradigm shift in AI forensics, moving from overfitting on static benchmarks to harnessing the evolving world knowledge of foundation models for real-world reliability.
  arXiv  Detail & Related papers  (2026-02-02T07:20:02Z)
• Towards Open-Vocabulary Industrial Defect Understanding with a Large-Scale Multimodal Dataset [1.1470070927586018]
  We present IMDD-1M, the first large-scale Industrial Multimodal Defect dataset comprising 1,000,000 aligned image-text pairs.<n>This dataset enables a wide spectrum of applications, including classification, segmentation, retrieval, captioning, and generative modeling.
  arXiv  Detail & Related papers  (2025-12-30T11:45:22Z)
• VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation [61.82502719679122]
  We introduce VLNVerse, a benchmark for Versatile, Embodied, Realistic Simulation, and Evaluation.<n>VLNVerse redefines VLN as a scalable, full-stack embodied AI problem.<n>We propose a novel unified multi-task model capable of addressing all tasks within the benchmark.
  arXiv  Detail & Related papers  (2025-12-22T04:27:26Z)
• VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment [88.83260031198023]
  We propose a vision-encoder-centered generative pre-training pipeline and develop the VITAL-Series LMMs.<n>We construct over 4.5M vision-language (VL) pairs-the largest VQualA training dataset to date.<n>We employ a multi-task training workflow that simultaneously enhances the model's quantitative scoring precision.
  arXiv  Detail & Related papers  (2025-11-22T07:55:21Z)
• Transferring Vision-Language-Action Models to Industry Applications: Architectures, Performance, and Challenges [19.814547689126396]
  Vision language-action (VLA) models have been a key paradigm in AI to unify perception, reasoning, and control.<n>We compare the performance of existing state-of-the-art VLA models in industrial scenarios and analyze the limitations of VLA models for real-world industrial deployment.
  arXiv  Detail & Related papers  (2025-09-27T05:02:57Z)
• Scalable Object Detection in the Car Interior With Vision Foundation Models [42.958409172092225]
  We propose the novel Object Detection and Localization (ODAL) framework for interior scene understanding.<n>Our approach leverages vision foundation models through a distributed architecture, splitting computational tasks between on-board and cloud.<n>To benchmark model performance, we introduce ODALbench, a new metric for comprehensive assessment of detection and localization.<n>Remarkably, our fine-tuned ODAL-LLaVA model achieves an ODAL$_score$ of 89%, representing a 71% improvement over its baseline performance and outperforming GPT-4o by nearly 20%.
  arXiv  Detail & Related papers  (2025-08-27T07:58:57Z)
• UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement [25.139037597606233]
  Zero-shot domain adaptation (ZSDA) presents substantial challenges due to the lack of images in the target domain.<n>Previous approaches leverage Vision-Language Models (VLMs) to tackle this challenge.<n>We propose the unified prompt and representation enhancement (UPRE) framework, which jointly optimize both textual prompts and visual representations.
  arXiv  Detail & Related papers  (2025-07-01T13:00:41Z)
• InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models [59.7084864920244]
  InternSpatial is the largest open-source dataset for spatial reasoning in vision-language models (VLMs)<n> InternSpatial comprises 12 million QA pairs spanning both single-view and multi-view settings.<n> InternSpatial-Bench is a corresponding evaluation benchmark designed to assess spatial understanding under diverse instruction formats.
  arXiv  Detail & Related papers  (2025-06-23T08:17:22Z)
• AuxDet: Auxiliary Metadata Matters for Omni-Domain Infrared Small Target Detection [58.67129770371016]
  We propose a novel IRSTD framework that reimagines the IRSTD paradigm by incorporating textual metadata for scene-aware optimization.<n>AuxDet consistently outperforms state-of-the-art methods, validating the critical role of auxiliary information in improving robustness and accuracy.
  arXiv  Detail & Related papers  (2025-05-21T07:02:05Z)
• Search is All You Need for Few-shot Anomaly Detection [39.737510049667556]
  Few-shot anomaly detection (FSAD) has emerged as a crucial yet challenging task in industrial inspection.<n>We show that a straightforward nearest-neighbor search framework can surpass state-of-the-art performance in both single-class and multi-class FSAD scenarios.<n>Our method achieves remarkable image-level AUROC scores of 97.4%, 94.8%, and 70.8% respectively.
  arXiv  Detail & Related papers  (2025-04-16T09:21:34Z)
• Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains [92.36624674516553]
  Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs)<n>We investigate the effectiveness and scalability of RLVR across diverse real-world domains including medicine, chemistry, psychology, economics, and education.<n>We utilize a generative scoring technique that yields soft, model-based reward signals to overcome limitations posed by binary verifications.
  arXiv  Detail & Related papers  (2025-03-31T08:22:49Z)
• Efficient Adaptation For Remote Sensing Visual Grounding [0.46425518005471045]
  Adapting pre-trained models has become an effective strategy in artificial intelligence, offering a scalable and efficient alternative to training models from scratch.<n>This study highlights the potential of PEFT techniques to advance efficient and precise multi-modal analysis in remote sensing.
  arXiv  Detail & Related papers  (2025-03-29T13:49:11Z)
• Visual-RFT: Visual Reinforcement Fine-Tuning [75.20572976629646]
  Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI o1 learns from feedback on its answers.<n>Visual-RFT further extends the application areas of RFT on visual tasks.
  arXiv  Detail & Related papers  (2025-03-03T18:16:32Z)
• No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance [68.18779562801762]
  multimodal models require exponentially more data to achieve linear improvements in downstream "zero-shot" performance. Our study reveals an exponential need for training data which implies that the key to "zero-shot" generalization capabilities under large-scale training paradigms remains to be found.
  arXiv  Detail & Related papers  (2024-04-04T17:58:02Z)
• Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Pilot Study [61.65123150513683]
  multimodal foundation models, such as CLIP, produce state-of-the-art zero-shot results. It is reported that these models close the robustness gap by matching the performance of supervised models trained on ImageNet. We show that CLIP leads to a significant robustness drop compared to supervised ImageNet models on our benchmark.
  arXiv  Detail & Related papers  (2024-03-15T17:33:49Z)
• Data-efficient Large Vision Models through Sequential Autoregression [58.26179273091461]
  We develop an efficient, autoregression-based vision model on a limited dataset. We demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint.
  arXiv  Detail & Related papers  (2024-02-07T13:41:53Z)
• Robust Fine-Tuning of Vision-Language Models for Domain Generalization [6.7181844004432385]
  Foundation models have impressive zero-shot inference capabilities and robustness under distribution shifts. We present a new recipe for few-shot fine-tuning of the popular vision-language foundation model CLIP. Our experimentation demonstrates that, while zero-shot CLIP fails to match performance of trained vision models on more complex benchmarks, few-shot CLIP fine-tuning outperforms its vision-only counterparts.
  arXiv  Detail & Related papers  (2023-11-03T20:50:40Z)
• Recognize Any Regions [55.76437190434433]
  RegionSpot integrates position-aware localization knowledge from a localization foundation model with semantic information from a ViL model.<n>Experiments in open-world object recognition show that our RegionSpot achieves significant performance gain over prior alternatives.
  arXiv  Detail & Related papers  (2023-11-02T16:31:49Z)
• Domain-Controlled Prompt Learning [49.45309818782329]
  Existing prompt learning methods often lack domain-awareness or domain-transfer mechanisms. We propose a textbfDomain-Controlled Prompt Learning for the specific domains. Our method achieves state-of-the-art performance in specific domain image recognition datasets.
  arXiv  Detail & Related papers  (2023-09-30T02:59:49Z)
• Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding [54.49214267905562]
  We construct a transformer-based framework for multi-modal manipulation detection and grounding tasks. Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment. We propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality.
  arXiv  Detail & Related papers  (2023-09-22T06:55:41Z)
• Zero-Shot Anomaly Detection with Pre-trained Segmentation Models [2.9322869014189985]
  This report outlines our submission to the zero-shot track of the Visual Anomaly and Novelty Detection (VAND) 2023 Challenge. Building on the performance of the WINCLIP framework, we aim to enhance the system's localization capabilities by integrating zero-shot segmentation models. Our pipeline requires no external data or information, allowing for it to be directly applied to new datasets.
  arXiv  Detail & Related papers  (2023-06-15T16:43:07Z)
• Zero-shot Video Moment Retrieval With Off-the-Shelf Models [17.254884920876695]
  We propose a zero-shot simple approach for one such task, Video Moment Retrieval (VMR) We vastly improve performance of previous zero-shot approaches by at least 2.5x on all metrics. We also show that our zero-shot approach beats non-pretrained supervised models on the Recall metrics and comes very close on mAP metrics.
  arXiv  Detail & Related papers  (2022-11-03T23:11:04Z)
• INTERN: A New Learning Paradigm Towards General Vision [117.3343347061931]
  We develop a new learning paradigm named INTERN. By learning with supervisory signals from multiple sources in multiple stages, the model being trained will develop strong generalizability. In most cases, our models, adapted with only 10% of the training data in the target domain, outperform the counterparts trained with the full set of data.
  arXiv  Detail & Related papers  (2021-11-16T18:42:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.