Mastodawn

Winbuzzer Apr 18, 2025

OpenAI's new o3 and o4-mini models integrated into ChatGPT demonstrate a strong ability to identify photo locations, sparking privacy debates

#ChatGPT #OpenAI #AI #Geolocation #GeoGuessr #Privacy #OSINT #o3 #o4mini #MachineLearning #VisualReasoning #PrivacyConcerns #AIEthics #AISafety

https://winbuzzer.com/2025/04/18/chatgpts-new-models-display-uncanny-photo-geolocation-skill-igniting-privacy-alarms-xcxwbn/

N-gated Hacker News Apr 9, 2025

🚀 Arcturus Labs promises that "visual reasoning" is just around the corner, but we all know it’s the tech equivalent of waiting for Godot. 🤖🔍 Meanwhile, their blog is a never-ending #SEO jamboree that makes you wish for the sweet release of a 404 page. 😂
http://arcturus-labs.com/blog/2025/03/31/visual-reasoning-is-coming-soon/ #ArcturusLabs #visualReasoning #techHumor #waitForGodot #404Page #HackerNews #ngated

Visual Reasoning is Coming Soon - Arcturus Labs

From silly cat costumes to world-changing innovations, OpenAI's latest release marks the beginning of something extraordinary. The fascinating world of visual reasoning is emerging, where AI models will soon think in pictures and solve complex spatial puzzles, transforming how machines understand and interact with the physical world.

Hacker News Apr 9, 2025

Visual Reasoning Is Coming Soon

http://arcturus-labs.com/blog/2025/03/31/visual-reasoning-is-coming-soon/

#HackerNews #VisualReasoning #IsComingSoon #ArcturusLabs #Technology #Innovation #AI

Visual Reasoning is Coming Soon - Arcturus Labs

N-gated Hacker News Apr 6, 2025

🎉 Wow, a "visual reasoning" model that can actually "think" with "evidence"—groundbreaking! 🚀 Because, you know, analyzing pictures and videos to solve math problems is exactly what the world was missing. 🙄 The future is truly here, folks, and it's apparently full of #buzzwords and grand promises! 🦄
https://qwenlm.github.io/blog/qvq-max-preview/ #visualreasoning #groundbreaking #innovation #futuretech #AI #HackerNews #ngated

QVQ-Max: Think with Evidence

QWEN CHAT GITHUB HUGGING FACE MODELSCOPE DISCORD Introduction Last December, we launched QVQ-72B-Preview as an exploratory model, but it had many issues. Today, we are officially releasing the first version of QVQ-Max, our visual reasoning model. This model can not only “understand” the content in images and videos but also analyze and reason with this information to provide solutions. From math problems to everyday questions, from programming code to artistic creation, QVQ-Max has demonstrated impressive capabilities.

Qwen

Jaleed Khan Feb 28, 2025

Our paper "KnowZRel: #CommonSense Knowledge-based Zero-Shot Relationship Retrieval for Generalised Scene Graph Generation" is now published in IEEE Transactions on #AI! 📜🤖🎯🎉
https://ieeexplore.ieee.org/document/10897903
@johnbreslin
#artificialintelligence #sceneunderstanding #visualreasoning #computervision #knowledgegraphs #deeplearning #NeurosymbolicAI

Winbuzzer Dec 26, 2024

Alibaba's new QVQ-72B open-source AI model combines visual and textual reasoning, achieving great benchmark results. #AI #MultimodalAI #VisualReasoning #Qwen #AlibabaAI #Innovation #AIResearch #AIModels

https://winbuzzer.com/2024/12/26/alibaba-qwen-releases-qvq-72b-preview-multimodal-reasoning-ai-model-xcxwbn/

Jaleed Khan Apr 1, 2024

Our paper "A Survey of #Neurosymbolic #VisualReasoning with Scene Graphs and #CommonSense Knowledge" has been accepted to Neurosymbolic #AI Journal➡️ https://neurosymbolic-ai-journal.com/paper/survey-neurosymbolic-visual-reasoning-scene-graphs-and-common-sense-knowledge-0 📜🎯🎉 @johnbreslin #artificialintelligence #sceneunderstanding #computervision #knowledgegraphs #deeplearning #research

Visual Reasoning is Coming Soon - Arcturus Labs

Visual Reasoning is Coming Soon - Arcturus Labs

QVQ-Max: Think with Evidence

A Survey of Neurosymbolic Visual Reasoning with Scene Graphs and Common Sense Knowledge | Neurosymbolic Artificial Intelligence