Evgenii Egorov (@eeevgen) header
Evgenii Egorov (@eeevgen) profile picture

PhD researcher University of Amsterdam / AMLab. Structure-aware ML for scientific systems: inference, efficient architectures, quantum AI4Science.

Amsterdam
Joined April 2010
Photo by Evgenii Egorov (@eeevgen)Photo by Evgenii Egorov (@eeevgen)Photo by Evgenii Egorov (@eeevgen)Photo by Evgenii Egorov (@eeevgen)Photo by Evgenii Egorov (@eeevgen)Photo by Evgenii Egorov (@eeevgen)Photo by Evgenii Egorov (@eeevgen)Photo by Evgenii Egorov (@eeevgen)Photo by Evgenii Egorov (@eeevgen)Photo by Evgenii Egorov (@eeevgen)
Evgenii Egorov retweeted
My group at the University of Edinburgh is recruiting #PhD students for 2027! 🎓 We are GLUEd: Geometric Learning & Uncertainty in Edinburgh. Group: vab.im/group/ How to apply: vab.im/vacancies/ 1/2
1
10
46
2,018
Sharing some deeply personal and existential reflections on scientific identity, the changing culture of AI research, the erosion of intellectual autonomy, and the growing disconnect between scientific rigor, professional recognition, and what organizations actually reward. As usual, feedback and debate are welcome and actively encouraged! mariya.fyi/posts/stranger-in… – at San Francisco, CA
17
66
16
506
39,844
Evgenii Egorov retweeted
Ten years ago we posted the first preprint on neural quantum states. Today we're launching Ketworks, a community site on NQS. Two parts: Ketbook, a reference written by the community, and Ketboard, variational energies from the literature on exactly defined benchmarks. Link below
4
16
1
90
4,467
Evgenii Egorov retweeted
LMs can play chess, but they can't really explain their moves well (chess engines can't at all). Our new BinProp scaffold tackles this, and nearly triples LMs’ score on our chess-explanation benchmark. It works on other games too! Try it on your own games on our site-🧵👇
7
12
6
59
5,888
Evgenii Egorov retweeted
breaking: fields medalists agree to shake fists at sky
5
18
4
286
18,168
Evgenii Egorov retweeted
I don't get it. Openai solves all math and my codex running for 40 hours with pro api and has nothing...
74
20
5
826
102,918
Can't believe this batch of PhD students gets to go to Seoul, Vienna, Singapore, Kyoto, San Diego, Hawaii while the previous batch visited Gather Town, and the one before that apparently just went to New Orleans multiple times
24
9
8
445
65,181
John Jumper, on why AlphaFold2 worked: > "It's not one or two home runs. It's 18 doubles. Midsize wins stacked together." His least popular take on AlphaFold2 is the over-crediting of SE(3)-equivariance / geometric deep learning. He ablated it and it only lifted performance about 2/30 points. FAPE (the frame-aligned point error) was actually most responsible for its improvement.
7
29
2
295
52,958
Evgenii Egorov retweeted
Replying to @Math_files
Which is actually: 2 (Area Ratio (Square / Inscribed Circle) / (Area Ratio (Cube / Inscribed Sphere)). math.stackexchange.com/quest…
1
1
332
Evgenii Egorov retweeted
🚀 Excited to share my @GoogleDeepMind student researcher project: Dual-Rate Diffusion✨ ⚡ A simple construction that speeds up both regular diffusion and distilled models by interleaving a heavy context encoder with a light conditional denoiser. 🧵👇
6
29
3
194
17,961
Evgenii Egorov retweeted
🌍Today we release Mosaic, a probabilistic weather model that shifts the Pareto frontier of ML weather forecasting. It matches the skill of state-of-the-art models while generating a 24-member, 10-day global forecast in under 12 s on a single H100. Thread!
28
136
23
1,249
147,691
Evgenii Egorov retweeted
On my way to ICLR to present our work on Latent Reasoning. Ping me here if you want to grab a coffee or drop by our poster! Sat, Apr 25, 2026, 3:15 – 5:45 PM 📍 Pavilion 3 P3-#905
(1/n) Introducing KaVa (arxiv.org/abs/2510.02312) – the first latent reasoning framework leveraging compressed KV-Cache to guide the latent generation. We beat previous approaches, especially on a realistic, Natural Language GSM8K dataset.
1
1
2
9
1,168
Evgenii Egorov retweeted
CCF(China Computer Federation) advises us not to engage with NeurIPS in any way — including submitting, reviewing, or ACing. They are even considering to remove NeurIPS from the CCF list. I’ll also stop submitting this year — though admittedly I don’t have a paper ready anyway.
Breaking: Academic freedom no more. The NeurIPS Foundation has announced it will no longer accept submissions from US-sanctioned institutions.
2
14
11
132
107,201
Evgenii Egorov retweeted
I want to follow more Chinese-only AI Researchers on Twitter. Do you have any recommendations?
2
3
9
2,012
Evgenii Egorov retweeted
On this International Women’s Day, we celebrate the incredible contributions of our women who help shape Russian Chess School every day. In a male-dominated industry, we’ve built a top-notch product together, and this is just the beginning!
24
15
1
425
55,710
Evgenii Egorov retweeted
hint:
2
5
1
41
2,342
Evgenii Egorov retweeted
i vibe-coded a collaborative art project. it is a giant shared grid of pixels. each user gets to flip one pixel every 5 minutes. it updates in real-time. curious to see what happens! follow the link and Flip Your Pixel, Now.
1
1
2
10
1,955
We suggest that these people stop trying to control language and find another job. We, normal folks, are offended by all this insanity.
Some may remember this ACM guidance on inclusive terminology. E.g., as advocated by an anon ICLR reviewer, it recommends against the technical term Byzantine. It was recently updated, and suggests avoiding "binary classification" and "stable marriage" (incorrectly defined)
1
4
1
39
7,666
Evgenii Egorov retweeted
Is it ok if I brag on my daughter for a few moments? 😇 She’s at MIT working on a PhD in physics (soft condensed matter and stat mech) and recently submitted this paper: arxiv.org/pdf/2503.11902 Among the many reasons to be proud, I see that she has used the word “ubiquitous” in the intro 🏆🙌, something her dad has also done in a physics paper.
54
42
2
1,397
84,289
Evgenii Egorov retweeted
Sofia Kovalevskaya wasthe first woman to receive a Ph.D. in mathematics. I recommend this wonderful book for both her life and scientific work by Michèle Audin who recently passsed away. fr.wikipedia.org/wiki/Mich%C…
2
11
105
4,113