#EMNLP2025 results are out! 🎉 We got 5 papers from CoRAL @SCAI_ASU (+collaborators): ➡️ 2 in Main ➡️ 3 in Findings Huge congratulations to my amazing students (many first-timers 💪) and collaborators! 🥳🍾🎈 #NLP #NLProc #LLM #StructuredData @ASUEngineering, @ASU (1/n)

New on the Anthropic Engineering blog: writing effective tools for LLM agents. AI agents are only as powerful as the tools we give them. So how do we make those tools more effective? We share our best tips for developers:

Dear @DKShivakumar ji, Ather has built a technology which shows all the Potholes in a City. I don't know if this should make us proud or disappointed, that a 2 wheeler company has to give BETTER ROUTE options instead of Government making every Road Pothole Free. @atherenergy

How it works: Claude has access to a private computer environment where it can write code and run programs. Read more:

A beautiful quote by Michael Atiyah: In the broad light of day mathematicians check their equations and their proofs, leaving no stone unturned in their search for rigour. But, at night, under the full moon, they dream, they float among the stars and wonder at the miracle of the

I am pleased to share PDF and podcasts on My “Network Optimization” book and “Auction Algorithms” https://t.co/tIH9MACMBM and https://t.co/L21GVNotYJ The book focuses on algorithms for graph and network optimization with emphasis on auction. PDF at

New research explains why LLMs hallucinate, through a connection between supervised and self-supervised learning. We also describe a key obstacle that can be removed to reduce them. 🧵 https://t.co/6Lb6xlg0SZ

🧬 Bad news for medical LLMs. This paper finds that top medical AI models often match patterns instead of truly reasoning. Small wording tweaks cut accuracy by up to 38% on validated questions. The team took 100 MedQA questions, replaced the correct choice with None of the

Today we're releasing new @AnthropicAI research on how educators use AI, analyzing ~74,000 conversations from professors using @claudeai in collaboration with Northeastern University. 4 initial findings… #1 Educators are builders, not just users of AI. Faculty are creating

I am teaching intro to ML this Fall (starting today!), and watching @3blue1brown linear algebra videos several times is a mandatory prerequisite for the students!

"Leveraging LLM For Synchronizing Information Across Multilingual Tables", to help update low-resource language Wikipedias https://t.co/q55rKoY4sc

4 machine learning training paradigms, explained visually: - Transfer Learning - Fine-tuning - Multi-task Learning - Federated Learning

@IndianTechGuide This

In the eye of a haboob..#Tempe (yes, that's a recycling bin being unceremoniously pushed along the road..)

Microsoft added a new Copilot function in Excel This allows users to generate analysis, summaries, data classifications, and more by typing =COPILOT() in their cells Microsoft has now officially caught up with Google in delivering agentic spreadsheets https://t.co/KgrAP6sMqY

Uber CEO on Tesla using Camera Vision over LiDAR: “I think in the near-term it’s going to be very difficult, and @elonmusk would tell me I’m wrong, and never bet against him, but it’s my instinct — in the near-term it’s going to be very difficult to build a camera only product

@DanRothNLP +@yanjiefoo (SCAI, ASU)

🚨 Call for Papers - RARA Workshop @ICDM2025 🚨 We’re inviting submissions to the RARA Workshop ( https://t.co/vtP9gE8YNA) on Grounding Documents with Reasoning, Agents, Retrieval, and Attribution, co-located with ICDM in Washington DC (Nov 12, 2025). 📅 Deadline: Aug 29, 2025

Proud of the entire CoRAL team at @SCAI_ASU 💛- amazing students, collaborators, and first-time authors who made this possible! Onward 🚀 Check out our other works: https://t.co/Gh9S4hbBVE #EMNLP2025 @ASUEngineering @ASU (7/n ; n/n)

M-Help: Social Media Data for Mental Health Help-Seeking Signals 📌 MSVPJ Sathvik, Zuhair Hasan Shaik, Vivek Gupta 🔗 https://t.co/ShndQR6y7e tldr: Moving beyond standard labels - detecting help-seeking signals in online social media discourse. #EMNLP2025 #Findings (6/n)

Federated Retrieval-Augmented Generation: A Mapping Study 📌 Abhi Chakraborty, Chahana Dahal, Vivek Gupta 🔗 https://t.co/J9vtnViwBo tldr: Survey of federated learning in RAG - why it matters, what exists, and open challenges. #EMNLP2025 #Findings (5/n)