Zeming Lin
@ebetica.bsky.social
Bio/ML. Co-founder at EvoScale, worked on Pytorch and StarCraft back at meta. Most likely not skynet.
I'll be at NeurIPS for the workshops if folks want to meet up!
December 10, 2024 at 6:29 PM
I'll be at NeurIPS for the workshops if folks want to meet up!
Reposted by Zeming Lin
Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science.
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
December 6, 2024 at 8:39 AM
Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science.
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
Evolution is non-linear, the next step in the evolutionary lineage of the ESM series of models is a sequence only protein language model that sets a new state of the art in representation learning.
Check it out! The 300M and 600M models are open weights, 300M available for commercial usage.
Check it out! The 300M and 600M models are open weights, 300M available for commercial usage.
Introducing ESM Cambrian, a new family of protein language models, focused on creating representations of the underlying biology of proteins.
December 4, 2024 at 5:50 PM
Evolution is non-linear, the next step in the evolutionary lineage of the ESM series of models is a sequence only protein language model that sets a new state of the art in representation learning.
Check it out! The 300M and 600M models are open weights, 300M available for commercial usage.
Check it out! The 300M and 600M models are open weights, 300M available for commercial usage.
Reposted by Zeming Lin
#CASP16 results are in! Template-based VFold seems to be lead method for nucleic acid structure prediction! AlphaFold2 and 3 still seem to be best methods for protein monomer and complex prediction.
November 30, 2024 at 10:28 PM
#CASP16 results are in! Template-based VFold seems to be lead method for nucleic acid structure prediction! AlphaFold2 and 3 still seem to be best methods for protein monomer and complex prediction.
Reposted by Zeming Lin
Have you ever wondered how to train an autoregressive generative transformer on text and raw pixels, without a pretrained visual tokenizer (e.g. VQ-VAE)?
We have been pondering this during summer and developed a new model: JetFormer 🌊🤖
arxiv.org/abs/2411.19722
A thread 👇
1/
We have been pondering this during summer and developed a new model: JetFormer 🌊🤖
arxiv.org/abs/2411.19722
A thread 👇
1/
December 2, 2024 at 4:41 PM
Have you ever wondered how to train an autoregressive generative transformer on text and raw pixels, without a pretrained visual tokenizer (e.g. VQ-VAE)?
We have been pondering this during summer and developed a new model: JetFormer 🌊🤖
arxiv.org/abs/2411.19722
A thread 👇
1/
We have been pondering this during summer and developed a new model: JetFormer 🌊🤖
arxiv.org/abs/2411.19722
A thread 👇
1/
Reposted by Zeming Lin
Better VQ-VAEs with this one weird rotation trick!
I missed this when it came out, but I love papers like this: a simple change to an already powerful technique, that significantly improves results without introducing complexity or hyperparameters.
I missed this when it came out, but I love papers like this: a simple change to an already powerful technique, that significantly improves results without introducing complexity or hyperparameters.
December 2, 2024 at 7:52 PM
Better VQ-VAEs with this one weird rotation trick!
I missed this when it came out, but I love papers like this: a simple change to an already powerful technique, that significantly improves results without introducing complexity or hyperparameters.
I missed this when it came out, but I love papers like this: a simple change to an already powerful technique, that significantly improves results without introducing complexity or hyperparameters.
Reposted by Zeming Lin
I'm pleased to announce a new blog post from
@ruiqigao.bsky.social and some other folks on my team, showing that diffusion == Gaussian flow matching.
diffusionflow.github.io
December 2, 2024 at 9:12 PM
I'm pleased to announce a new blog post from
@ruiqigao.bsky.social and some other folks on my team, showing that diffusion == Gaussian flow matching.
diffusionflow.github.io
Reposted by Zeming Lin
Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition!
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
November 27, 2024 at 9:00 AM
Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition!
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
I think the #1 way you can tell apart AI images is when they don't seem to tell a story at all. A lot of these seem like psychedelic fractals rather than art with some kind of underlying theme.
Still blown away by GPT-4o’s images. It does dark fantasy very well.
I saw a statue of a frog doing yoga and wondered what it would look like as ornamentation in a baroque cathedral. It only really worked when I asked to zoom in…
I saw a statue of a frog doing yoga and wondered what it would look like as ornamentation in a baroque cathedral. It only really worked when I asked to zoom in…
November 27, 2024 at 6:56 AM
I think the #1 way you can tell apart AI images is when they don't seem to tell a story at all. A lot of these seem like psychedelic fractals rather than art with some kind of underlying theme.
Reposted by Zeming Lin
Arxiv sharing reminder
pdf ❌
abs ✅
pdf ❌
abs ✅
November 26, 2024 at 8:42 AM
Arxiv sharing reminder
pdf ❌
abs ✅
pdf ❌
abs ✅
Nice!
NeurIPS Conference is now Live on Bluesky!
-NeurIPS2024 Communication Chairs
-NeurIPS2024 Communication Chairs
November 22, 2024 at 5:03 PM
Nice!
Reposted by Zeming Lin
Hey folks! I got a tattoo of my beloved PIEZO ion channel on my arm! Now I can show how they activate (flatten) under pressure by flexing—Will add a bit of performance art to my science talks 🧪🧠.
November 22, 2024 at 4:05 AM
Hey folks! I got a tattoo of my beloved PIEZO ion channel on my arm! Now I can show how they activate (flatten) under pressure by flexing—Will add a bit of performance art to my science talks 🧪🧠.
Reposted by Zeming Lin
Evo: A genomic language model of prokaryote genomes generates functional cas9 proteins and transposons.
@brianhiestand.bsky.social
www.science.org/doi/10.1126/...
@brianhiestand.bsky.social
www.science.org/doi/10.1126/...
November 14, 2024 at 8:53 PM
Evo: A genomic language model of prokaryote genomes generates functional cas9 proteins and transposons.
@brianhiestand.bsky.social
www.science.org/doi/10.1126/...
@brianhiestand.bsky.social
www.science.org/doi/10.1126/...
Reposted by Zeming Lin
November 20, 2024 at 7:26 PM
Reposted by Zeming Lin
Two full starter packs for your bioml needs!
Two BioML starter packs now:
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
DM if you want to be included (or nominate people who should be!)
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
DM if you want to be included (or nominate people who should be!)
November 21, 2024 at 2:03 PM
Two full starter packs for your bioml needs!
Reposted by Zeming Lin
We're about to release a pretty massive multiome atlas (includes chromatin) of several adult tissues via ENCODE4 + a significant expansion of the bulk DNase and ATAC datasets (already out). Many more regions than ENCODE3.
November 20, 2024 at 3:41 PM
We're about to release a pretty massive multiome atlas (includes chromatin) of several adult tissues via ENCODE4 + a significant expansion of the bulk DNase and ATAC datasets (already out). Many more regions than ENCODE3.
What did it? The starter packs??
90 days ago Bluesky had 6.18M users
30 days ago Bluesky had 10.85M users
Tomorrow Bluesky will have 15M users
This is absolutely wild, thanks for believing in us y'all
30 days ago Bluesky had 10.85M users
Tomorrow Bluesky will have 15M users
This is absolutely wild, thanks for believing in us y'all
November 21, 2024 at 4:40 AM
What did it? The starter packs??
Hi Bluesky! I made it on Kevin's starter pack 😌😌😌 here to discuss all things bio and all things ML!
Two BioML starter packs now:
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
DM if you want to be included (or nominate people who should be!)
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
DM if you want to be included (or nominate people who should be!)
November 18, 2024 at 9:28 PM
Hi Bluesky! I made it on Kevin's starter pack 😌😌😌 here to discuss all things bio and all things ML!
Reposted by Zeming Lin
In a gratuitous attempt to acquire more followers myself 😁, I've made a start on a "starter pack". Hopefully as more people from 🐦 make it over to 🦋, we can extend this a bit. Suggestions welcome!
I've noticed not all accounts seem to be eligible to be added, anyone know what's up with that? 🤔
I've noticed not all accounts seem to be eligible to be added, anyone know what's up with that? 🤔
November 15, 2024 at 8:04 PM
In a gratuitous attempt to acquire more followers myself 😁, I've made a start on a "starter pack". Hopefully as more people from 🐦 make it over to 🦋, we can extend this a bit. Suggestions welcome!
I've noticed not all accounts seem to be eligible to be added, anyone know what's up with that? 🤔
I've noticed not all accounts seem to be eligible to be added, anyone know what's up with that? 🤔
Reposted by Zeming Lin
Two BioML starter packs now:
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
DM if you want to be included (or nominate people who should be!)
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
DM if you want to be included (or nominate people who should be!)
Anybody have a bioml starter pack?
November 18, 2024 at 5:09 PM
Two BioML starter packs now:
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
DM if you want to be included (or nominate people who should be!)
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
DM if you want to be included (or nominate people who should be!)