Recent searches

No recent searches

Search options

Only available when logged in.
sigmoid.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A social space for people researching, working with, or just interested in AI!

Administered by:

Server stats:

587
active users

sigmoid.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.3

#AiResearch

15 posts15 participants0 posts today
Antonio Lieto

Un articolo de Il Mattino che parla del sistema di generazione e riconoscimento di metafore METCL, sviluppato Gian Luca Pozzato e Stefano Zoia, e sarà presentato alla 34th International Joint Conference on Artificial Intelligence, a Montreal #IJCAI2025 :

Paper: The Delta of Thought: Channeling Rivers of Commonsense Knowledge in the Sea
of Metaphorical Interpretations: ciitlab.org/IJCAI_25_Lieto_Poz

An article on il Mattino on the METCL metaphor generation and recognition system developed with @Gian Luca Pozzato and Stefano Zoia, and that will be presented at the 34th International Joint Conference on Artificial Intelligence, #IJCAI2025, in Montreal

Paper: The Delta of Thought: Channeling Rivers of Commonsense Knowledge in the Sea
of Metaphorical Interpretations: ciitlab.org/IJCAI_25_Lieto_Poz

#computationalcreativity#commonsensereasoning#metaphors
Continued thread
UKP Lab

The briefing also features perspectives from:
👤 Prof. Dr. Chris Biemann, Universität Hamburg
👤 Dr. Paul Röttger, MilaNLP Group, Università Bocconi

All experts stress that strong benchmark results do not automatically translate into reliable performance in real-world applications.

📄 Read the full statements here: (in German)
sciencemediacenter.de/angebote

(3/3)

www.sciencemediacenter.deGPT-5 veröffentlicht: Wie gut messen Benchmarks Leistung von KI-Modellen?
#AI#Benchmarks#NLP
*
Dirk Schnelle-Walka

ai-2027.com presents a predictive scenario about the impact of superhuman #AI over the next decade based on trend extrapolations and expert feedback. A timeline of AI development, from Stumbling Agents in 2025 to more powerful models that can accelerate AI research and potentially "survive and replicate." The scenario includes two possible endings to spark conversation about the future of AI.
​#ArtificialIntelligence #FutureOfAI #SuperhumanAI #AIPrediction #TechFuture #AIResearch

AI 2027
ai-2027.comAI 2027A research-backed AI scenario forecast.
Continued thread
*
Institute for AI

MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning

In manufacturing, quality control remains a critical yet complex task, especially when multiple defect types are involved. MultiADS introduces a system capable of detecting and segmenting a wide range of anomalies (e.g., scratches, bends, holes), even in zero-shot settings.

By combining visual analysis with descriptive textual input and using a curated Knowledge Base for Anomalies, MultiADS generalizes to unseen defect types without requiring prior visual examples and consistently outperforms state-of-the-art models across several benchmarks, offering a robust and scalable solution for industrial inspection tasks.

Sadikaj, Y., Zhou, H., Halilaj, L., Schmid, S., Staab, S., & Plant, C. MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning. International Conference on Computer Vision, ICCV 2025, Hawai, Oct 19-23, 2025, #ICCV2025. arxiv.org/abs/2504.06740.

arXiv logo
arXiv.orgMultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot LearningPrecise optical inspection in industrial applications is crucial for minimizing scrap rates and reducing the associated costs. Besides merely detecting if a product is anomalous or not, it is crucial to know the distinct type of defect, such as a bent, cut, or scratch. The ability to recognize the "exact" defect type enables automated treatments of the anomalies in modern production lines. Current methods are limited to solely detecting whether a product is defective or not without providing any insights on the defect type, nevertheless detecting and identifying multiple defects. We propose MultiADS, a zero-shot learning approach, able to perform Multi-type Anomaly Detection and Segmentation. The architecture of MultiADS comprises CLIP and extra linear layers to align the visual- and textual representation in a joint feature space. To the best of our knowledge, our proposal, is the first approach to perform a multi-type anomaly segmentation task in zero-shot learning. Contrary to the other baselines, our approach i) generates specific anomaly masks for each distinct defect type, ii) learns to distinguish defect types, and iii) simultaneously identifies multiple defect types present in an anomalous product. Additionally, our approach outperforms zero/few-shot learning SoTA methods on image-level and pixel-level anomaly detection and segmentation tasks on five commonly used datasets: MVTec-AD, Visa, MPDD, MAD and Real-IAD.
#AI#AIResearch#ComputerVision
Continued thread
*
Institute for AI

Making the Web More Inclusive: Enter AccessGuru

Despite the availability of accessibility guidelines like #WCAG, most websites still present barriers for users with disabilities. This paper introduces AccessGuru, a system that leverages Large Language Models (#LLMs) to automatically detect and correct accessibility violations in HTML code.

AccessGuru is guided by a novel taxonomy of syntactic, semantic, and layout violations and combines rule-based tools with LLM reasoning over code and visuals.

It reduces violation scores by up to 84%, outperforming existing tools, and achieves 73% similarity to human-generated semantic corrections. A benchmark dataset of 3,500 real-world violations is also released to support future research.

This work demonstrates how LLMs can meaningfully automate accessibility efforts and foster a more inclusive Web.

Fathallah, N. (@nadeenfathallah), Hernández, D. (@daniel), & Staab, S. (2025). AccessGuru: Leveraging LLMs to detect and correct web accessibility violations in HTML code. The 27th International ACM SIGACCESS Conference on Computers and Accessibility #ASSETS2025. arxiv.org/abs/2507.19549.

arXiv logo
arXiv.orgAccessGuru: Leveraging LLMs to Detect and Correct Web Accessibility Violations in HTML CodeThe vast majority of Web pages fail to comply with established Web accessibility guidelines, excluding a range of users with diverse abilities from interacting with their content. Making Web pages accessible to all users requires dedicated expertise and additional manual efforts from Web page providers. To lower their efforts and promote inclusiveness, we aim to automatically detect and correct Web accessibility violations in HTML code. While previous work has made progress in detecting certain types of accessibility violations, the problem of automatically detecting and correcting accessibility violations remains an open challenge that we address. We introduce a novel taxonomy classifying Web accessibility violations into three key categories - Syntactic, Semantic, and Layout. This taxonomy provides a structured foundation for developing our detection and correction method and redefining evaluation metrics. We propose a novel method, AccessGuru, which combines existing accessibility testing tools and Large Language Models (LLMs) to detect violations and applies taxonomy-driven prompting strategies to correct all three categories. To evaluate these capabilities, we develop a benchmark of real-world Web accessibility violations. Our benchmark quantifies syntactic and layout compliance and judges semantic accuracy through comparative analysis with human expert corrections. Evaluation against our benchmark shows that AccessGuru achieves up to 84% average violation score decrease, significantly outperforming prior methods that achieve at most 50%.
#AI#AIResearch#Accessibility
*
Institute for AI

🎉 Researchers from our AI institute at the University of Stuttgart @Uni_Stuttgart will present two papers tackling real-world challenges with AI:

- "Making the Web More Inclusive: Enter AccessGuru" (#ASSETS2025).

- "MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning" (#ICCV2025).

ki.uni-stuttgart.de/institute/

#AI#AIResearch
TrendingLive feeds
About