🔥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

New paper officially out! Congratulations to Mari Sosa - amazing work - and just before she sets off to UC Boulder to start her own lab!

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…

Delighted to bring gene circuits into a wide array of primary cells where they can be used for safe, effective gene therapies. 🧵 (1/n) Tremendous work by lead author Kasey Love to dig into the details of these systems and figure out how to get these to work well! Original

1/N How do neural dynamics in motor cortex interact with those in subcortical networks to flexibly control movement? I’m beyond thrilled to share our work on this problem, led by Eric Kirk Eric Kirk with help from Kangjia Cai! biorxiv.org/content/10.110…

I'm thrilled to announce that our work to develop the Neuropixels-NHP 1.0 neural recording probe is now out in print in Nature Neuroscience. nature.com/articles/s4159…

I grew up around blindness; my mom’s dad had retinitis pigmentosa, and I remember when Wired said in 2002 that visual prostheses were just around the corner. Today Science submitted our full CE mark application for marketing approval in Europe for our PRIMA retinal prosthesis.

So you want to change transgene expression: just change your promoter, right? Changing the promoter increases RNA and thus protein levels. What more could be happening? [1/n] Well, promoters don’t just set RNA levels; they uniquely transform how RNAs are transmitted into protein

Wow, we can steer diffusion models at inference time! Introducing Diffusion Tree Sampling (DTS): a search-based approach inspired by Monte Carlo Tree Search that turns inference into an anytime, reward-guided optimization process. Diffusion Tree Sampling (DTS) produces

Adenoviruses, despite their large cargo carrying capacity, have been beat by the much smaller AAV in the gene therapy field. I wrote a summary on why that is (link below.) (hint: having a large genome is a double edged sword in the viral vector space)

the fastest way to kill motivation is to make your identity depend on the outcome. it’s called ego involvement. when failing becomes failing as a person, your brain starts avoiding the whole thing. not because you don’t care, but because you care too much.

Some scientists see the increasingly impressive results from protein binding models and argue "solving" this problem actually has marginal return on an end-to-end drug campaign in practice. Generally, they claim (1) traditional immunization / hybridoma assays are already quite

The 3-decade-old competition that enabled the emergence and evaluate of AlphaFold has run out of NIH funding. The program will be terminated in weeks. This is terminating success. science.org/content/articl…

1/4 🚀 Announcing the 2025 Protein Engineering Tournament. This year’s challenge: design PETase enzymes, which degrade the type of plastic in bottles. Can AI-guided protein design help solve the climate crisis? Let’s find out! ⬇️ #AIforBiology #ClimateTech #ProteinEngineering

Printing this out and pasting it above every thermostat at work

🧵generative models are sweet, but navigating existing repositories can be overwhelming, particularly when starting a new research project so i built jax-interpolants, a clean & flexible implementation of the stochastic interpolant framework in jax github.com/nmboffi/jax-in…

📢Presenting SDE Matching🔥🔥🔥 🚀We extend diffusion models to construct a simulation-free framework for training Latent SDEs. It enables sampling from the exact posterior process marginals without any numerical simulations. 📜: arxiv.org/abs/2502.02472 🧵1/8

Big day for Python tooling enjoyers: Modal finally has first-class uv support! Use: • `uv_sync` to sync your Modal image with your local project • `uv_pip_install` to install packages lightning fast⚡️

"Okay, so imagine a magic button." "I'm imagining the button." "If you press the button—" "What color is it?" "It's the only button. It doesn't matter what color it is." "Nah, I ain't falling for that again. Last time there was a red button and a blue button—" "That's a

An AI-ready lab notebook for life science doesn't need to be complex or expensive. At PioneerLabs, we use a lab management system built entirely with generic software tools. It's simple, cheap, and easy to modify. See our now how-to post ⬇️

My talk for AI Engineer on what I think every person working with language models needs to know about GPUs is now available! - Latency lags bandwidth. - GPUs embrace bandwidth. - Don't be scared of N squared. - Use the Tensor Cores, Luke! youtube.com/watch?v=y-UGrY…