🔥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

It's tough times for science. 🥺 But we have to keep innovating to fight another day, and today I'm so proud to share Fred Zhangzhi Peng's new, groundbreaking sampling algorithm for generative language models, Path Planning (P2). 🌟 📜: arxiv.org/abs/2502.03540 💻: In the appendix!!

concurrent work that studies the decoding order of MDM. Cool results in logic puzzles. Feel amazing to see the same conclusion drawn from two works.

discrete diffusion models reaching the level of commercial LLMs!

Check out our work applying discrete diffusion model to noncoding RNA sequence design!

Open-Qwen2VL Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources

PTM-Mamba: a PTM-aware protein language model with bidirectional gated Mamba blocks Nature Methods 1. PTM-Mamba is the first protein language model explicitly designed to encode post-translational modifications (PTMs), using a novel bidirectional gated Mamba architecture fused

PTM-Mamba: a post-translational modification-aware protein language model, for protein modeling and design. nature.com/articles/s4159…

How can protein language models incorporate post-translational modifications (PTMs) to better represent the functional diversity of the proteome?Nature Methods Duke University "PTM-Mamba: a PTM-aware protein language model with bidirectional gated Mamba blocks" Authors: Fred Zhangzhi Peng

We are hiring a student researcher at Google DeepMind to work on fundamental problems in discrete generative modeling! Examples of our recent work: masked diffusion: arxiv.org/abs/2406.04329 learning-order AR: arxiv.org/abs/2503.05979 If you find this interesting, please send an

Generative protein language model! I'm assuming it's GPT?

Super exited about Singapore and ICLR2025. Will present my work on masked diffusion models at ICLR Nucleic Acids Workshop #DeLTa #FPI and GEMBio Workshop. Please stop by posters and chat about MDMs and protein design :)

insights on training next generation of pLM. Good work as always Hou Chao

FlashAttention-accelerated Protein Language Models ESM2 now supports Huggingface. One line change, up to 70% faster and 60% less memory! 🧬⚡ Huggingface: huggingface.co/fredzzp/esm2_t… Github: github.com/pengzhangzhi/f…