pan tom
@daspantom
Followers
114
Following
273
Media
13
Statuses
135
Joined August 2014
Really pleased to share what I have been working on for 2 months: 🇬🇧 UK SovAI are today announcing our £8m seed investment into OpenBind - A consortium that will actually make AI for drug discovery great by generating 500k experiment protein-ligand complexes!! Explainer 🧵 (1/n)
Excited to see this announcement from the Government’s SovereignAI unit: funding for the world’s largest dataset of protein interactions, led by a truly world-class group of researchers As @demishassabis says, “This is a brilliant initiative for UK science”
8
34
205
Excited to have contributed to this amazing work by @LVaitl! https://t.co/Ti8pxrH0mu
Ever felt like Boltzmann Generators trained with Flow Matching were doing fine, just not good enough? We slapped Path Gradients on top, and things got better. No extra samples, no extra compute, no changes to the model. Just gradients you already have access to.
1
1
18
Ever felt like Boltzmann Generators trained with Flow Matching were doing fine, just not good enough? We slapped Path Gradients on top, and things got better. No extra samples, no extra compute, no changes to the model. Just gradients you already have access to.
1
9
37
I will be @iclr_conf in Singapore and I'm looking for a senior ML scientist to join my team @PrescientDesign @genentech! 🧬 If you have experience & interest in multi-modal biological foundation models and agents for science, reach out and let's meet up! Link to apply 👇
2
9
55
Our new work https://t.co/WLBk0Y5KrK extends the theory of diffusion bridges to degenerate noise settings, including underdamped Langevin dynamics (with @DenBless94, @julberner). This enables more efficient diffusion-based sampling with substantially fewer discretization steps.
1
31
141
I am excited to announce that our paper on Stochastic Normalizing Flows for Entanglement Entropy has been accepted for publication in Physics Review Letters 🚀 -> https://t.co/fUgJX3Ek0L Big up to Andrea Bulgarelli for his hard work and to the rest of the collaboration 👏
3
16
117
We are hiring an intern on generative models for proteins for 6-12 months and typically results in publication. Find out what science is like in a bio-ml industry research lab. Bonus: float along the Rhine to work (perfectly normal commute here): https://t.co/nj57Qn5Ygy
0
2
12
we're still hiring fresh phd level MLEs for LLMs. https://t.co/IWflIOWbY2 as well as slightly seniors (LLMs) https://t.co/CyeVZEGZAW and also infrastructure MLEs https://t.co/HZwnhgGrVX
2
13
43
JAMUN: Transferable Molecular Conformational Ensemble Generation with Walk-Jump Sampling @PrescientDesign • JAMUN introduces a generative model based on Walk-Jump Sampling (WJS) to efficiently generate molecular conformational ensembles, outperforming traditional molecular
2
17
71
We have a few spots left! Register now at https://t.co/AWdNGoZyQn 14 technical talks 3 keynotes 3 panel discussions 1 poster session and much more... Including speakers like (in random order) @daspantom, @jonkhler, @msalbergo, @wangleiphy, @lorenz_richter, and many more!
indico.hiskp.uni-bonn.de
🚨 Workshop Alert 🚨 Dive into Gen AI and its applications, from physics to drug design, with a top-notch line-up of speakers! 🚀 Join us in Bonn this fall! 🇩🇪 Register now: https://t.co/tGL6mjbco0
#AI4Science #Workshop #UniBonn #GenerativeModels
0
6
10
Great collaborative work with @lorenz_richter!
And back to Vienna again. I will present our work on time-continuous discrete-space diffusion models at @icmlconf (with @ludiXIVwinkler, Thu, 11:30). For the first time, we can connect those models to score-based generative modeling, see https://t.co/RMz90ezHZx. Ping me!
0
1
2
Machine Learning enhanced optimization of Quantum Circuits strikes back ☄️ Beyond excited to present our new work on Adaptive Shot Control for VQEs using Gaussian Processes at @icmlconf 🎉 Check out the paper now https://t.co/rkj6DEbDGr
#icml2024
2
4
6
Fantastic workshop coming up...
🚨 Workshop Alert 🚨 Dive into Gen AI and its applications, from physics to drug design, with a top-notch line-up of speakers! 🚀 Join us in Bonn this fall! 🇩🇪 Register now: https://t.co/tGL6mjbco0
#AI4Science #Workshop #UniBonn #GenerativeModels
0
1
9
🚨 Workshop Alert 🚨 Dive into Gen AI and its applications, from physics to drug design, with a top-notch line-up of speakers! 🚀 Join us in Bonn this fall! 🇩🇪 Register now: https://t.co/tGL6mjbco0
#AI4Science #Workshop #UniBonn #GenerativeModels
3
8
33
Our small molecule team at @PrescientDesign within @genentech is hiring for two Machine Learning Scientists. Come work with us to impact drug discovery through computation and machine learning! https://t.co/bOXoOaBneL
https://t.co/z1LmZRricL
@VishnuSresht
2
8
42
Fantastic opportunity...
We’re hiring again! If you’re in to the idea of using AI+Chemistry to design new medicines, apply! If you just want to know more, shoot me a message. https://t.co/5ZXRyNtkZ4
https://t.co/FCEUgrw5HH
0
0
3
We’re hiring again! If you’re in to the idea of using AI+Chemistry to design new medicines, apply! If you just want to know more, shoot me a message. https://t.co/5ZXRyNtkZ4
https://t.co/FCEUgrw5HH
1
16
84
Excited to share our new preprint 🥳🥳 Implicit guidance with PropEn: Match your data to follow the gradient 🔗 https://t.co/8G0vGE5V1j Joint work with @loukasa_tweet, @kchonyc, @GligorijevicV at @prescientdesign & @genentech
2
20
77
It's been quite the journey, from conception to wet lab validation, but we can finally share some of our results. ⚛️🤖🔬 Excited to share these findings
Excited to share our new preprint 🥳🥳 Implicit guidance with PropEn: Match your data to follow the gradient 🔗 https://t.co/8G0vGE5V1j Joint work with @loukasa_tweet, @kchonyc, @GligorijevicV at @prescientdesign & @genentech
0
3
27
As part of our commitment to open science, I'm excited to share that an alpha version of our protein design code is available! Check out the tutorials to learn how to designs proteins yourself with guided discrete diffusion, just like the pros https://t.co/JsPSDYYOzO
Very nice talk by @kchonyc at #ICLR2024! TIL feature attribution can be used in protein synthesis to identify regions to mutate based on target properties of interest 🔍
2
21
72