Maria Rosario Mestre

Absolutely thrilled to see the amazing keynotes happening this afternoon at the PyTorch Conference! 🎤 📈 The panel discussion on Scaling & Benchmarking moderated by Soumith Chintala, featuring experts like Anastasios Angelopoulos, Lisa Dunlap, James Bradbury, Tri Dao, and Aparna Ramani, was incredibly insightful. It’s inspiring to hear from leaders across Meta, UC Berkeley, Anthropic, Together AI, and more about the future of AI scaling. 💡 Mudhakar Srivatsa from IBM Research delivered a fantastic session on Optimizing AI Inference for Large Language Models. The strategies discussed are sure to push the boundaries of what’s possible with LLMs. 🚀 Anush E.’s talk on Accelerating AI: How AMD and PyTorch Drive Innovation with Seamless Day-0 Support & High Performance highlighted some groundbreaking advancements that will undoubtedly enhance our AI projects. 📍 I’m sitting on the left at the 4th row, sporting my PyTorch cap. Great to be here and connect with fellow enthusiasts! 📸 Attaching a photo with Aparna Ramani and Amber Habib! It was wonderful meeting such inspiring individuals and exchanging ideas. Feeling energized and inspired by the incredible talent and innovation on display today. Excited to apply these insights and continue driving forward in the AI and ML space! #PyTorchConf #AI #ML #LLM #PyTorch #OpenSource

33

4 Comments

🚀 Exploring Extrinsic Hallucinations in LLMs! 🚀 The article delves into the causes and solutions for hallucinations in large language models (LLMs). 🌟Key highlights: - Causes of Hallucinations: Addressing issues in pre-training data and the challenges of fine-tuning with new knowledge. - Detection Methods: Utilizing techniques like retrieval-augmented evaluation and sampling-based detection to identify hallucinations. - Anti-Hallucination Techniques: Implementing strategies such as Retrieval-Augmented Generation (RAG), fine-tuning for factuality, and employing retrieval methods to enhance accuracy. https://lnkd.in/g3j5kU5b For more updates, follow Rohit Agarwal! #AI #LLMs #MachineLearning #TechInnovation #DataScience #ModelAccuracy #FactualAI #HallucinationDetection

4

For all large language models (LLM) can do, it's important to recognise what they can't. This research paper addresses a critical question: How reliable is LLM's knowledge? The authors, including the Head of Aveni Labs, Dr. Alexandra Birch, and Dr. Barry Haddow, our Head of Natural Language Processing, introduce a novel metric called MOdel kNowledge relIabiliTy scORe (MONITOR) to assess LLM's factual reliability. MONITOR works by asking models the same question in different ways and seeing how likely the model is to give the same answer each time. This innovative approach helps identify situations where an LLM might be making things up rather than providing facts. Read more: https://hubs.la/Q02w7fJk0 #LLM #largelanguagemodels #naturalLanguageProcessing #machinelearning #artificalintelligence

5

1 Comment

Combining the power of TensorFlow, NeuralForecast, and zero-shot LLMs, Jinhang Jiang shows how we can generate accurate multi-step quantile forecasts.

11