Artem Moskalev 🕊️
@artemmoskalev
Followers
997
Following
4K
Statuses
283
Re-imagining drug discovery with AI 🧬. Deep Learning ⚭ Geometry. Previously PhD at the University of Amsterdam. 🦋 artemmoskalev
Amsterdam, Netherlands
Joined February 2017
Don't treat the language of biology as natural language! Biology speaks in hierarchical patterns that natural language models don't fully capture. Meet HELM: a novel approach to train LMs that aligns with the intrinsic hierarchy of mRNA sequences. 1/5
3
20
140
Cool work on improving MIM
✨New Preprint ✨ Ever thought that reconstructing masked pixels for image representation learning seems sub-optimal? In our new preprint, we show how masking principal components—rather than raw pixel patches— improves Masked Image Modelling (MIM). Find out more below 🧵
0
0
2
UvdL says “The AI race is just beginning” after implementing EU AI act earlier.. what a great start
The AI race is just beginning. Building on the European AI Champions initiative, I’m glad to announce InvestAI 🇪🇺 We aim to mobilise €200 billion in AI investments in Europe ↓
0
0
1
AI/ML Internships in Drug Discovery🚨 Our team is hiring PhD research interns for summer 2025 in the US. Come work with us on cutting-edge drug discovery projects! We have 3 openings: 1. Hyperbolic NNs for sequence modeling: 2. Causal Inference and Bayesian Optimization: 3. Multi-modal Sequence, Structure & Interaction modeling: Apply and reach out to me if interested! Share if you know a good candidate 😁
3
19
131
RT @dbaek__: 1/9 🚨 New Paper Alert: Cross-Entropy Loss is NOT What You Need! 🚨 We introduce harmonic loss as alternative to the standard CE…
0
549
0
0
0
1
0
0
1
1
0
1
RT @_mullerlab: Great working with @LiboniLuisa @budzinski_r @alexandranbusch Sindy Löwe @t_andy_keller and @wellingmax on this paper, just…
0
14
0
RT @gklambauer: GenMol: A Drug Discovery Generalist with Discrete Diffusion (by NVIDIA) Very simple categorical diffusion model used to ge…
0
58
0
RT @rohanpaul_ai: FlashAttention on a Napkin 🧠 Mathematical visualization framework systematically derives optimal GPU implementations. T…
0
25
0
RT @HannesStaerk: Tomorrow in the reading group, Johannes Brehmer will present his paper "Does equivariance matter at scale?" https://t.co/…
0
5
0
RT @k_neklyudov: 🧵(1/5) Have you ever wanted to combine different pre-trained diffusion models but don't have time or data to retrain a new…
0
53
0
RT @dereklim_lzh: Our new workshop at ICLR 2025: Weight Space Learning: Weights are data. We can learn from weigh…
0
58
0
RT @PascalMettes: Hyperbolic learning is growing rapidly by the day. From weekly alerts in 2023 to daily digests in 2024! From our current…
0
32
0
RT @davidwromero: Very happy to share my first project at NVIDIA! 🚀 We present Meshtron, a pure Transformer model that consistently reason…
0
26
0