Mehrdad Farajtabar
@MFarajtabar
Research Scientist at @Apple, prev @DeepMind, prev @GeorgiaTech
📢Submissions are now open for #NeurIPS2025 CCFM workshop. Submission deadline: August 22, 2025, AoE. Website: sites.google.com/view/ccfm-neur… Call for papers: sites.google.com/view/ccfm-neur… Submission Link: openreview.net/group?id=NeurI…
Is your AI keeping Up with the world? Announcing #NeurIPS2025 CCFM Workshop: Continual and Compatible Foundation Model Updates When/Where: Dec. 6-7 San Diego Submission deadline: Aug. 22, 2025. (opening soon!) sites.google.com/view/ccfm-neur… #FoundationModels #ContinualLearning
We have a full-time position for research scientist in our team at #Apple. The topic is understanding and improving #reasoning abilities of #LLMs. We're also interested in developing new and efficient architectures based on transformer for language modeling, again reasoning…
🧵 1/8 The Illusion of Thinking: Are reasoning models like o1/o3, DeepSeek-R1, and Claude 3.7 Sonnet really "thinking"? 🤔 Or are they just throwing more compute towards pattern matching? The new Large Reasoning Models (LRMs) show promising gains on math and coding benchmarks,…
Apple research just revealed a way to make LLMs 5.35x faster. 🤯 That’s not a typo. They've found a method to get a >500% speedup for code & math tasks, with ZERO quality loss. Here's how they're unlocking AI model's "latent potential": 🧵
I noticed the same thing! Engaging in conversations, replies, or DMs with #DeepMind folks always feels safe and welcoming. Their culture is truly remarkable. Thanks to leaders like Samy Bengio, Devi Krishna, Daphne Luong, JG, and many others who've joined Apple, this incredible…
Personal observation: The level of intellectual discussion with @GoogleDeepMind vs @OpenAI that I am able to have is literally night and day. DeepMind knows my work, can raise serious objections, propose and develop alternatives, etc. OpenAI speaks to me with insulting memes…
Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential Autoregressive LMs already know future tokens, this work makes that usable: - Append <mask> tokens → jointly predict k+1 future tokens - Gated LoRA → updates only for MTP tokens, preserving NTP behavior…
It’s great to be excited about AI’s #IMO performance, while also recognizing the true source of its power. I came across this paragraph today during my reading of A Thousand Brains: A New Theory of #Intelligence, 2021, Jeff Hawkins!
In this report we describe the 2025 Apple Foundation Models ("AFM"). We also introduce the new Foundation Models framework, which gives app developers direct access to the on-device AFM model. machinelearning.apple.com/research/apple…