Generating ~200 million parameters in just minutes! 🥳 Excited to share our work with Doven Tang , ZHAO WANGBO , and Yang You: 'Recurrent Diffusion for Large-Scale Parameter Generation' (RPG for short). Example: Obtain customized models using prompts (see below). (🧵1/8)

🔥 Make parameter generation the next big thing! Nice work with Victor.Kai Wang, ZHAO WANGBO, and Yang You.

Generate models in minutes ???? !!!! Nice work with Victor.Kai Wang, ZHAO WANGBO, and Yang You.

🔥 AI Creates AI! Congrats to the team led by Victor.Kai Wang, Doven Tang, and ZHAO WANGBO

Very interesting work on parameter generation using RNNs and diffusion! Cool to see #weightspacelearning evolve and scale to 100s of millions of parameters.. Hope to see you at the ICLR 2025 Weight Space Learning Workshop, Kai!

I’m truly stunned 🤯

🤔 Is there a scaling law for model weight generation? 🚀 Generating ~200M parameters in just minutes! 📚 Check out these works: P-Diff: arxiv.org/abs/2402.13144 Conda P-Diff: arxiv.org/abs/2408.01415 Recurrent Diffusion for Large-Scale Parameter Generation:

🚀 We’re thrilled to introduce DD-Ranking: Rethinking the Evaluation of Dataset Distillation—a unified, user-friendly, and long-term maintained benchmark for dataset distillation (DD)! 📢 Together with 20 institutions worldwide, we’re releasing our Repo, API Documentation, and

Every area needs its equitable benchmark.