Kaveh Hassani

A substantial piece of work from Apple led by Iman Mirzadeh, keivan alizadeh vahid, Oncel Tuzel, Samy Bengio, Mehrdad Farajtabar and Hooman Shahrokhi supports the thesis that transformer-based LLMs do not reason--they perform pattern-matching. The team from  also provides a great benchmarking tool--GSM-Symbolic for assessing mathematical and formal reasoning. This supports my anecdotal findings when I evaluated o1 https://lnkd.in/ec72fecb as well as my thoughts on the incompleteness of our assessments of AGI https://lnkd.in/ehBT3HB3

16

2 Comments

One good news: one of my research papers gets accepted in ICSE-2025 (research track). The title of the paper is “Ranking Relevant Tests for Order-Dependent Flaky Tests”. #ICSE2025, #LLM, #testing, #ottawa - #Canada

89

20 Comments

🎉 Thrilled to share some great news stemming from an amazing example of collaboration between UK and Greece supported by ARCHIMEDES Research on AI, Data Science, and Algorithms which will soon reach new highs thans to our partnership via the CHAI Hub. Our paper, "Benchmarking Counterfactual Image Generation," has been accepted to NeurIPS 2024 in the Datasets & Benchmarks track! We’ll present it in Vancouver on December 11th, and I couldn’t be prouder of our incredible Greek dream team of students who led this effort— Thomas Melistas Nikos Spyrou and Nefeli Gkouti. We address a critical challenge: how do we rigorously evaluate counterfactual image generation, where causal constraints must be respected, and ground truths are elusive? Our team developed a benchmarking framework that highlights the strengths of Hierarchical VAEs across diverse datasets. We’ve even made it available as a user-friendly Python package to encourage community collaboration. 🚀 Interactive demo: https://lnkd.in/e9GA5Ebu 📄 Paper: https://lnkd.in/eR2ig3pY A huge thanks to co-authors: Pedro P. Sanchez, Yannis Panagakis, Giorgos Papanastasiou, PhD, and Dr Athanasios Vlontzos. Excited to share our work with the AI community at NeurIPS. Do go and see the work and talk to this wonderful team of students. #NeurIPS2024 #GenerativeAI #Counterfactuals #CausalInference #MachineLearning #AIResearch

40

1 Comment

Go check out Brevitas at the links below and start experimenting with MX and all the latest quantization algorithms!

11

Excited to share our latest publication in Computers in Biology and Medicine. In collaboration with the BC Children's Hospital Research Institute, this study introduces BRI-Net, an interpretable deep-learning model that leverages adversarial training to learn an unbiased representation of data, helping identify genetic markers associated with specific phenotypes. Using genomic data from a cohort of 362 pediatric cancer patients treated with cisplatin, recruited by the Canadian Pharmacogenomics Network for Drug Safety, our model identified two statistically significant SNPs associated with cisplatin-induced ototoxicity: CERS6 rs13022792 and TLR4 rs10759932. To explore our methodology and findings in detail, check out the full paper at https://lnkd.in/gEn4fZb9. A huge thanks to my amazing co-authors and collaborators, especially Bahareh Kashani, for making this possible!

66

4 Comments

If everything goes right, I'm giving the exam in my EngSci Intro to Programming class this Saturday morning and flying out to NeurIPS 2024 in Vancouver on Saturday night. With Chunsheng (Jason) Zuo (EngSci 2T4) and Pavel Guerzhoy (my dad who still answers the phone when I need help with math homework), we are presenting Chunsheng Zuo, Pavel Guerzhoy and Michael Guerzhoy, Positional Information Can Emerge Through Causal Attention Making Nearby Token Embeddings Similar Even Without Positional Encodings at Interpretable AI in Action Workshop @ NeurIPS 2024 https://lnkd.in/g-akwxfs . It's been shown a while ago that you can train causal Transformers without positional encodings. We show that even untrained causal Transformers contain information that allows you to infer positions of tokens, and provide a novel explanation of how that can happen. (Expanded version will be at COLING 2025, watch this space). With Kexin Chen (UofT MIE MEng), Claire Lee (Princeton '20), and Noelle Lim (UofT EngSci 2T3), we are presenting Exploring Complex Mental Health Symptoms via Classifying Social Media Data with Explainable LLMs at Machine Learning for Health Findings (ML4H, co-located with NeurIPS) https://lnkd.in/gm9UwtZ9 We propose training LLM classifiers on social media data of people talking about mental health symptoms, generating explanations for why the LLM classified a post in a particular way, and then qualitatively analyzing the explanations to potentially gain new insights into the interaction of the symptoms and the nosology of mental health issues. Key: find challenging and interesting tasks for the LLMs! Finally, for my ESC180 students, I and the TAs have been hard at work on the ESC180 exam for this Saturday. Incredibly proud of that work, check out the pdf here: https://lnkd.in/gDAZnCY6

139

7 Comments

Are you thinking about participating in the Quantum Resource Estimation challenge, but don't know where to start? Check out the video tutorial on using Azure Quantum Resource Estimator! https://lnkd.in/gqGUhzp5

50

1 Comment

Unlock the full potential of your Large Language Models (LLMs) with Intel® Extension for PyTorch (IPEX) and the Intel® LLM Library for PyTorch (IPEX-LLM). Download this whitepaper to explore the optimization of LLMs, including their performance, resource utilization, and response times in real-world applications. Link - https://intel.ly/3BBJ4ey

1

With apologies to Daft Punk, I’m at University of Waterloo about to give an invited talk titled “Harder, Better, Faster, Stronger: Visualization for HCAI Tools” hosted by Jian Zhao in the Cheriton School of Computer Science. Our arXiv paper on this topic can be found here: https://lnkd.in/dY2ncEDq

118

3 Comments

Vancouver AI people: I'm hosting an event! I'm founding the Vancouver chapter of The Ai Salon and will be hosting our inaugural session on Thursday, November 28. The Ai Salon is a community founded in San Francisco that brings together scientists, founders, builders, and the generally curious to hold small-sized group conversations on the sociological, economic, cultural, and philosophical impacts of AI. Our inaugural event: Autonomous Scientific Discovery Will we ever be able to build an AI scientist? What would that look like? Is the genius and creativity of scientific breakthroughs something AI could ever replicate? What is the significance of the recent Nobel Prizes in physics and chemistry awarded for work on AI? Let's discuss. This will be an in-person event. Details and registration information at the link below. https://lu.ma/u1px71f0

38

3 Comments

NiNo: A Novel Machine Learning Approach to Accelerate Neural Network Training through Neuron Interaction and Nowcasting Researchers from Samsung’s SAIT AI Lab, Concordia University, Université de Montréal, and Mila have introduced a novel approach known as Neuron Interaction and Nowcasting (NINO) networks. This method aims to significantly reduce training time by predicting the future state of network parameters. Rather than applying an optimization step at every iteration, as with traditional methods, NINO employs a learnable function to predict future parameter updates periodically. By integrating neural graphs—which capture the relationships and interactions between neurons within layers—NINO can make rare yet highly accurate predictions. This periodic approach reduces the computational load while maintaining accuracy, particularly in complex architectures like transformers. At the core of the NINO methodology lies its ability to leverage neuron connectivity through graph neural networks (GNNs). Traditional optimizers like Adam treat parameter updates independently without considering the interactions between neurons. NINO, however, uses neural graphs to model these interactions, making predictions about future network parameters in a way that reflects the network’s inherent structure. The researchers built on the Weight Nowcaster Networks (WNN) method but improved it by incorporating neuron interaction modeling. They conditioned NINO to predict parameter changes for the near and distant future. This adaptability allows NINO to be applied at different stages of training without requiring constant retraining, making it suitable for various neural architectures, including vision and language tasks. The model can efficiently learn how network parameters evolve by using supervised learning from training trajectories across multiple tasks, enabling faster convergence.... Read our article on this:https://lnkd.in/gSQFYtcG Paper: https://lnkd.in/g9rJ5JT2 GitHub Page: https://lnkd.in/gJPbT-kM

25

🌟 Reconnecting with a long-standing Friend and Discussing the Future of AI in Computer Vision & Medical Image Analysis 🔍I recently had the incredible opportunity to host Professor Tal Arbel and her students from McGill University and Mila - Quebec Artificial Intelligence Institute at TheraPanacea. Tal is not only an outstanding colleague and a great asset to the community but also a fantastic friend. Her energy, motivation, and engagement extend far beyond the scientific realm.  🩺 We discussed how AI and machine learning have revolutionized medical image analysis, enhancing diagnostic accuracy and predictive analytics. Technologies like deep learning are transforming healthcare, leading to better patient outcomes and more efficient workflows in fields such as oncology and neurology. 🚀 Our primary focus, however, was on future directions. We explored concepts like personalized medicine, which aims to tailor treatments based on individual imaging data, moving towards holistic treatment pathways. We also emphasized the importance of collaborative efforts in an academic-industry startup setting, involving clinical experts, advanced algorithms, and data management to drive innovation. The synergy between academia and industry will be pivotal in shaping the future of healthcare. #AI #MedicalImaging #HealthcareInnovation #FutureOfMedicine #AcademicConnections

111

5 Comments

⚡ Just a chill (very intense) guy in Vancouver for #NeurIPS... 🎉 🚨 Presenting not one, not two, but THREE papers that the Enkrypt AI team and I authored this weekend at the NeurIPS workshops! 🧠💥 Here’s what’s on deck from the Enkrypt AI team: 1️⃣ Red Teaming Gen AI: The SAGE-RT Synthetic Data Generation Process 2️⃣ Pluralistic Alignment: SAGE-RT Dataset's Impact on Model Safety Alignment 3️⃣ Safe Gen AI: Bias uncovered in over 50 LLMs (yes, it’s wild!) If you're here and want to chat about AI, AI safety, or just share some workshop wisdom, let’s connect! 📩 Let’s make some brilliant conversations happen. 🚀 Reach out if you're here! Let's talk all things AI and AI Safety! 🚀 #NeurIPS #NIPS #AISafety #AISecurity #Vancouver #Enkrypt AI

51

There's only 5 days left to submit your paper! Remember, we only a short 1-page abstract

2

We are currently present on Conference on Neural Information Processing Systems (NeurIPS) in Vancouver, Canada! Check out more about the conference here: https://neurips.cc/ Two members of GoodAi will today present their paper - Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models. The insights from this research played a key role in implementing LTM in AI People. Find more about the paper here: https://lnkd.in/ejBP8CdS.

16

I'm thrilled to announce the release of two new fine-tuned large language models (LLMs) and a groundbreaking dataset for Persian NLP. 🚀 Shotor (Llama 3 8B): Fine-tuned on the Persian Alpaca Deep Clean dataset. Paya (Aya 23 8B): Also fine-tuned on the same comprehensive dataset. These models are crafted for high-quality performance in various Persian language applications, leveraging the Alpaca Deep Clean dataset which I meticulously processed. The fine-tuning was achieved using Dora for efficiency. Explore the models: Shotor: https://lnkd.in/ddge8CAh Paya: https://lnkd.in/dT55qCH4 Additionally, I’ve released the first Persian DPO dataset for LLM alignment, aiming to set a new standard in Persian language processing. Check out the datasets: Persian Alpaca Deep Clean: https://lnkd.in/d8ejpYRf Persian DPO: https://lnkd.in/dMF2sihF Your feedback and insights are invaluable as we strive to advance Persian NLP. I invite the community to test these models and datasets, and share your thoughts. Feel free to engage and share this post to spread the word! Looking forward to your feedback and collaboration. #NLP #PersianNLP #MachineLearning #AI #LanguageModels #DataScience #HuggingFace

36

6 Comments