🔥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

Interesting and welcome changes. I am wondering if a similar approach to reviews' length and legibility could be applied. Peer reviewers and ACs could oversee. Let's call this peer-review^2. At least until AGI becomes reviewer #2 ... 🙄

Today NVIDIA published a blog featuring our AI assistant Leo and its Bring Your Own Model feature! Learn how you can connect local AI models to our browser with tools like ollama, and the advantages of doing it, here: blogs.nvidia.com/blog/rtx-ai-br…

Knowledge Distillation in Human Intelligence

This video (youtube.com/watch?v=rbu7Zu…) from Grant Sanderson is mighty impressive. The sheer virtuosity … Integration of Manim (github.com/ManimCommunity…) with Anthropic artifacts would be paradigm shifting in education. Looking forward to advances in this space.

Honoured to be giving a talk at my alma mater on "Paying Attention to Efficiency: LLM Deployment on Mobile and Edge Devices" on Tue 05 Nov 2024, 1pm, as part of the AI Research Group Talks Series. Special thanks to Mateja Jamnik for hosting me. Details: talks.cam.ac.uk/talk/index/223…

I'll attending ACM #MobiCom2024 in DC next week, presenting: * A keynote @ FedEdge, titled "Downsizing GenAI: Running LLMs at the edge" (Mon 18th, 9am) * Our paper "MELTing Point: Mobile Evaluation of Language Transformers" (Tue 19th, 2pm) - arxiv.org/abs/2403.12844 See you there!

Looking forward to giving a talk this Friday at 10am GMT at Imperial College London (@ I-HUB) on "Transformers on the Edge: Adapting Models to Diverse Systems". Thanks, Sarab Sethi and Hamed , for the invite!

🚀 Excited to announce our MCDC ICLR 2026 workshop on Modularity for Collaborative, Decentralized, and Continual Deep Learning! 📜 Call for papers: sites.google.com/view/mcdc2025/… 🔥Topics of interest: MoEs, Routing of Specialized Experts (MoE-rging), Upcycling and MoE-fication,

We welcome submissions on efficient foundation models, on-device learning, and distributed learning to our ICML Conference workshop. Deadline: May 23rd Steve Laskaridis, Samuel Horváth, Berivan Isik, Peter Kairouz, Christina Giannoula, bilge, Angelos Katharopoulos, Martin Takac, nic lane