🔥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

Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks arxiv.org/abs/2406.02550

Awesome collaboration with my students Tianyu He Darshil Doshi @ICML2025 Aritra Das @ Neurips! We got a GPT-style model to learn modular arithmetic in-context. There are phase transitions as a function of data diversity, number of in-context examples & visually stunning representations.

🚀 Excited to share our latest paper: "QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation"! 📄 Read the paper: arxiv.org/abs/2406.00132 💻 Explore the code: github.com/quanta-fine-tu… #NLP #LLM #Finetuing #MachineLearning #Quantum #GenAI

Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the best AI conference NeurIPS Conference We have ethical reviews for authors, but missed it for invited speakers? 😡

Excited to share our paper "Universal Sharpness Dynamics..." is accepted to #ICLR2025! Neural net training exhibits rich curvature (sharpness) dynamics (sharpness reduction, progressive sharpening, Edge of Stability)- but why?🤔 We show that a minimal model captures it all! 1/n

New paper! Collaboration with Tianyu He and Aditya Cowsik. Thread.🧵

🚨 ICML 2025 🚨 I'll be at ICML Conference Mon-Fri. DM if you'd like to chat!☕️ Also come check out our poster on cracking Pseudo-Random Number Generators with Transformers! 🕚 Tuesday @ 11am #⃣ E-1206 🔗arxiv.org/abs/2502.10390

🤖 Transformers can write poetry, code, and generate stunning art, but can they predict seemingly random numbers? We show that they learn to predict simple PRNGs (LCGs) by figuring out prime factorization on their own!🤯 Find Darshil tomorrow, 11am at #ICML2025 poster session!