🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

On my way to the AAAI/ACM conference AIES (AI, Ethics, and Society) in Montreal. This is an in person conference but it is possible to register to watch the program from remote. #aiethics #responsibleai #ArtificialIntelligence aies-conference.com/2023/

Happy to share that our paper "On #Popularity #Bias of #Multimodal-aware #RecommenderSystems: a Modalities-driven Analysis" has been accepted at the MMIR WS at #acmmm2023! w/ Daniele Malitesta Claudio Pomo Tommaso Di Noia Preprint: tinyurl.com/3dkpp2ju GitHub: tinyurl.com/3fycjknv

The trio Daniele Malitesta Giandomenico Cornacchia and Claudio Pomo (with our great supervisor Tommaso Di Noia) strikes again! If you're into #multimodal #recsys, you should definitively follow our latest works 🚀 and the best is yet to come 🤓

Our preprint "Formalizing #Multimedia #Recommendation through #Multimodal Deep Learning" is now out on arXiv! arxiv.org/pdf/2309.05273… (1/2)

Yes, you heard it right! #RecSys2024 will be held in #Bari (#Italy), my hometown 😍🤓 ACM RecSys

Working on topics related to graphs and IR? We might know what suits you 😎 We present the 1st International Workshop on Graph-Based Approaches in Information Retrieval (#IRonGraphs), co-located with #ECIR2024 ECIR2024 Check out the workshop website: irongraphs.github.io/ecir2024/

Having a bad start of the week already? Cheer up! The CFP for #IRonGraphs (co-located with #ECIR2024) is officially out 🤩 ECIR2024 IRonGraphs@ECIR2024 Glasgow IR Group

Last conference of my #PhD 🥲 but I'm super excited as this is the first time for me at ACM #MM23 ACM SIGMM (this year held in #Ottawa, ON, Canada) 🤩🍁❄️ We at SisInfLab - Polytechnic of Bari (Politecnico di Bari) are going to present two papers, more info in the thread ⤵️

2) On 11/02 we present "On Popularity #Bias of #Multimodal-aware #Recommender Systems: A Modalities-driven Analysis" by myself, Giandomenico Cornacchia, Claudio Pomo, and Tommaso Di Noia at the MMIR workshop Paper: tinyurl.com/52pf8taa GitHub: tinyurl.com/4xbezvam

I'm proud to announce that I've started a new position as Research Scientist - Security & Privacy at IBM Research Europe! Looking forward to diving into #foundationmodels #safety and #privacy #responsibleAi assessment and contributing to impactful research.#IBMer

Our paper "Formalizing Multimedia Recommendation through Multimodal Deep Learning" is now accepted in ACM Transactions on Recommender Systems (ACM TORS) 😍🚀 We survey, formalize, benchmark, and outline open questions in #multimodal #recsys! A work w/ Claudio Pomo Giandomenico Cornacchia Felice Antonio Merra Tommaso Di Noia Eugenio Di Sciascio

watsonx.governance has a jailbreaking and prompt injection detector. Check it out. medium.com/trusted-ai/sec…

Safeguarding LLMs is increasingly critical. Try out the IBM Research open-source 38M-parameter and 125M-parameter hate/abuse/profanity classifiers available on Hugging Face with an Apache v2.0 license. They have small environmental impact and low latency. research.ibm.com/blog/efficient…

We released best-in-class Apache 2.0 licensed models for detecting general harm and RAG hallucinations as part of the Granite 3.0 release! Read more: linkedin.com/pulse/ibm-open… Documentation: ibm.com/granite/docs/m… Hugging Face: huggingface.co/collections/ib… Try them out!

"Want to make AI safer? 🛡️ Join us through the Summer '25 internship program! Help level up our open-source models that keep AI honest and harmless. Granite-Guardian project is calling ✨ Apply now!" Link to apply: careers.ibm.com/job/21097301/2… DM me if you are interested.

Nice media coverage of our open-sourced Granite-Guardian models - "Open sourcing AI guardrails - IBM's push to improve safety and reduce hallucinations" diginomica.com/open-sourcing-…

"That's not to say all the big-name AI companies are lying about their open source street cred. For example, IBM's Granite 3.0 LLMs really are open source under the Apache 2 license." theregister.com/2024/10/25/opi…

Check out the latest Attack Atlas taxonomy at the NeurIPS Conference red teaming workshop! It maps out a framework for thinking through single-turn prompt attacks in Gen AI arxiv.org/abs/2409.15398 #AIsafety #RedTeam #AIsecurity Giandomenico Cornacchia Pin-Yu Chen Prasanna Sattigeri Kush Varshney कुश वार्ष्णेय

📢 Exciting #NeurIPS2024 highlights 🧵 First up, 🛡️ Granite Guardian technical report is out. Check out the demo at the NeurIPS IBM booth with Werner Geyer. Huggingface paper page: huggingface.co/papers/2412.07…

We released Granite Guardian 3.1 today! Even better at harm detection than Granite Guardian 3.0. The main new feature is 'function calling hallucination' detection relevant for tool-using AI agents. github.com/ibm-granite/gr…