Call for participation: *SciVQA* Shared Task (https://sdproc.org/2025/scivqa.html)

@NFDI4DS members Ekaterina Borisova and Georg Rehm are organizing a shared task “Scientific Visual Question Answering Shared Task (SciVQA)” on July 31 or August 1st, 2025 in Vienna, Austria, hosted as part of the SDP 2025 Workshop.

Deadline for system submissions: May 16, 2025

#chart
#diagram
#multimodalQA
#visualattributes
#questionanswering
#arXiv
#SciVQA
#SDP2025
#ACL2025
#Vienna
#codabench
#huggingface
#NFDI4DS

Our Institute is hiring. If you are interested in working at the intersection of conversational question-answering and geographic knowledge graphs, we would love to hear from you!
#knowledgegraph #questionanswering

Full job ad: https://www.verw.tu-dresden.de/StellAus/stelle.asp?id=11872&lang=de&style=verw

📝 "PDF-Based Question Answering with Amazon Bedrock and Haystack"

👤 Bilge Yucel (@bilgeyucel)

🔗 https://medium.com/deepset-ai/pdf-based-question-answering-with-amazon-bedrock-and-haystack-dc234003ffd8?source=rss-dacda5cb969d------2

#pyladies #python #amazonwebservices #haystack #amazonbedrock #questionanswering #opensearch

#TechNews: #Qwen Releases New #VisionLanguage #LLM Qwen2-VL 🖥️👁️

After a year of development, #Qwen has released Qwen2-VL, its latest #AI system for interpreting visual and textual information. 🚀

Key Features of Qwen2-VL:

1. 🖼️ Image Understanding:

Qwen2-VL shows performance on #VisualUnderstanding benchmarks including #MathVista, #DocVQA, #RealWorldQA, and #MTVQA.

2. 🎬 Video Analysis:

Qwen2-VL can analyze videos over 20 minutes in length. This is achieved through online streaming capabilities, allowing for video-based #QuestionAnswering, #Dialog, and #ContentCreation. #VideoAnalysis

3. 🤖 Device Integration:

The #AI can be integrated with #mobile phones, #robots, and other devices. It uses reasoning and decision-making abilities to interpret visual environments and text instructions for device control. #AIAssistants 📱

4. 🌍 Multilingual Capabilities:

Qwen2-VL understands text in images across multiple languages. It supports most European languages, Japanese, Korean, Arabic, Vietnamese, among others, in addition to English and Chinese. #MultilingualAI

This release represents an advancement in #ArtificialIntelligence, combining visual perception and language understanding. 🧠 Potential applications include #education, #healthcare, #robotics, and #contentmoderation.

https://github.com/QwenLM/Qwen2-VL

Meet GraphRAG: Microsoft’s New Graph-Based AI Method for Superior Data Insights.

See here - https://techchilli.com/artificial-intelligence/meet-graphrag-microsofts-new-graph-based-ai-method-for-superior-data-insights/

#GraphRAG #Microsoft #AI #DataInsights #TechInnovation #GitHub #DataRetrieval #AItechnology #QuestionAnswering #DataAnalysis #FutureOfAI #GraphBasedAI #TechTrends #Innovation

🎉 We developed a prompting method for improved (and more human-like) LLM reasoning and applied it to hybrid question answering, surpassing the GPT-4 baseline. 🚀

Thanks to my co-authors Dhananjay, Preetam and @SaharVahdati ! We'll present the work at #ACL2024 in Bangkok this year where I hope I'll be able to meet a few of you.

Blog post: https://linkedin.com/pulse/beyond-boundaries-human-like-approach-question-over-sources-lehmann-dhtne

Paper: https://www.amazon.science/publications/beyond-boundaries-a-human-like-approach-for-question-answering-over-structured-and-unstructured-information-sources

#AI #LLMs #QuestionAnswering #ConversationalAI

Very biased, but also very excited about Khyathi Chandu's presentation of our new proposed shared task at #INLG2023: "LowReCorp: The Low-Resource NLG Corpus Building Challenge"

Join the #SharedTask during the coming year if you want to use our UI or task design to collect #NLG data for #LowResourceLanguages!

#DialogueSummarization #QuestionAnswering #ResponseGeneration