Sourav
@souravmishra.bsky.social
I like to talk about ML & 3D. University of Tokyo alumni. Previously: Virginia Tech, Stanford Biodesign. Visiting Fellow @ MSR Big Data
L5 Manager stork making sure the L3 and L4 employee storks finishing their task properly 😂
cc @pierrealquier.bsky.social
cc @pierrealquier.bsky.social
May 18, 2025 at 5:52 AM
L5 Manager stork making sure the L3 and L4 employee storks finishing their task properly 😂
cc @pierrealquier.bsky.social
cc @pierrealquier.bsky.social
Reposted by Sourav
Our survey on meta reinforcement learning has now been published by Foundations and Trends in Machine Learning: nowpublishers.com/article/Deta...
now publishers - A Tutorial on Meta-Reinforcement Learning
Publishers of Foundations and Trends, making research accessible
nowpublishers.com
April 18, 2025 at 3:19 PM
Our survey on meta reinforcement learning has now been published by Foundations and Trends in Machine Learning: nowpublishers.com/article/Deta...
Big win for Stanford NLP to have @yejinchoinka.bsky.social Looking forward to new amazing directions
Look who we found hanging out in her new Stanford Gates Computer Science office!
We’re truly delighted to welcome @yejinchoinka.bsky.social as a new @stanfordnlp.bsky.social faculty member, starting full-time in September. ❤️
nlp.stanford.edu/people/
We’re truly delighted to welcome @yejinchoinka.bsky.social as a new @stanfordnlp.bsky.social faculty member, starting full-time in September. ❤️
nlp.stanford.edu/people/
April 8, 2025 at 3:57 AM
Big win for Stanford NLP to have @yejinchoinka.bsky.social Looking forward to new amazing directions
Excited to see Waymo come to Tokyo
* Tokyo has a passive, secondary transportation mode which will stay strong despite the subway.
* It is generally considered to be one of the safest cities. Low chances of vandalism.
* People are curious to try out new technology across all age strata.
* Tokyo has a passive, secondary transportation mode which will stay strong despite the subway.
* It is generally considered to be one of the safest cities. Low chances of vandalism.
* People are curious to try out new technology across all age strata.
The first waymo depot in Tokyo has been identified, a huge milestone: thelastdriverlicenseholder.com/2025/04/07/w...
April 8, 2025 at 3:21 AM
Excited to see Waymo come to Tokyo
* Tokyo has a passive, secondary transportation mode which will stay strong despite the subway.
* It is generally considered to be one of the safest cities. Low chances of vandalism.
* People are curious to try out new technology across all age strata.
* Tokyo has a passive, secondary transportation mode which will stay strong despite the subway.
* It is generally considered to be one of the safest cities. Low chances of vandalism.
* People are curious to try out new technology across all age strata.
Picking the brains of the Claude model. Anthropic has made a new foray into "AI biology" and some interesting case studies on what the assumptions are.
Turns out LLMs don't entirely piece together their response the way we do. Great investigate work
www.anthropic.com/research/tra...
Turns out LLMs don't entirely piece together their response the way we do. Great investigate work
www.anthropic.com/research/tra...
Tracing the thoughts of a large language model
Anthropic's latest interpretability research: a new microscope to understand Claude's internal mechanisms
www.anthropic.com
March 27, 2025 at 9:49 PM
Picking the brains of the Claude model. Anthropic has made a new foray into "AI biology" and some interesting case studies on what the assumptions are.
Turns out LLMs don't entirely piece together their response the way we do. Great investigate work
www.anthropic.com/research/tra...
Turns out LLMs don't entirely piece together their response the way we do. Great investigate work
www.anthropic.com/research/tra...
Reposted by Sourav
Can we understand the mechanisms of a frontier AI model?
📝 Blog post: www.anthropic.com/research/tra...
🧪 "Biology" paper: transformer-circuits.pub/2025/attribu...
⚙️ Methods paper: transformer-circuits.pub/2025/attribu...
Featuring basic multi-step reasoning, planning, introspection and more!
📝 Blog post: www.anthropic.com/research/tra...
🧪 "Biology" paper: transformer-circuits.pub/2025/attribu...
⚙️ Methods paper: transformer-circuits.pub/2025/attribu...
Featuring basic multi-step reasoning, planning, introspection and more!
On the Biology of a Large Language Model
transformer-circuits.pub
March 27, 2025 at 6:18 PM
Can we understand the mechanisms of a frontier AI model?
📝 Blog post: www.anthropic.com/research/tra...
🧪 "Biology" paper: transformer-circuits.pub/2025/attribu...
⚙️ Methods paper: transformer-circuits.pub/2025/attribu...
Featuring basic multi-step reasoning, planning, introspection and more!
📝 Blog post: www.anthropic.com/research/tra...
🧪 "Biology" paper: transformer-circuits.pub/2025/attribu...
⚙️ Methods paper: transformer-circuits.pub/2025/attribu...
Featuring basic multi-step reasoning, planning, introspection and more!
In the Ghibli world I look like this. Not bad. Not bad at all! :-)
March 27, 2025 at 9:34 PM
In the Ghibli world I look like this. Not bad. Not bad at all! :-)
Is "vibe coding" same as "prompt engineering" from 6 mo ago?
I am having trouble keeping up with names and acronyms now, forget research papers
I am having trouble keeping up with names and acronyms now, forget research papers
March 25, 2025 at 12:06 PM
Is "vibe coding" same as "prompt engineering" from 6 mo ago?
I am having trouble keeping up with names and acronyms now, forget research papers
I am having trouble keeping up with names and acronyms now, forget research papers
Reposted by Sourav
don’t learn to write code, learn to read code
March 23, 2025 at 9:13 PM
don’t learn to write code, learn to read code
Too bad it's a little late for Team Australia for the Olympics
March 25, 2025 at 11:50 AM
Too bad it's a little late for Team Australia for the Olympics
Such a beautiful representation of the vernal equinox 😍
🌍 Happy #Equinox! On 20 March 2025 at 09:01 GMT/10:01 CET, just a few moments ago, the Sun appeared directly above Earth's equator - with our planet neither tilting towards nor away from the Sun!
(pic: @eumetsat.int, processed by ESA/S. Proud)
See flic.kr/p/2qT1ZUu
(pic: @eumetsat.int, processed by ESA/S. Proud)
See flic.kr/p/2qT1ZUu
March 20, 2025 at 11:09 AM
Such a beautiful representation of the vernal equinox 😍
"There was a girl from India who had overstayed her student visa for 3 days before heading back home. She then came back to the US on a new, valid visa to finish her master’s degree and was handed over to ICE due to the 3 days she had overstayed"
WOW. Just wow. Cruelty is in vogue for US govt. now
WOW. Just wow. Cruelty is in vogue for US govt. now
I am seriously questioning whether it will be safe to visit the US for three weeks this summer, as I had planned.
A powerful account from Jasmine Mooney, a Canadian detained in ICE facilities for 12 days for no reason. (The cruelty is the point.)
www.theguardian.com/us-news/2025...
A powerful account from Jasmine Mooney, a Canadian detained in ICE facilities for 12 days for no reason. (The cruelty is the point.)
www.theguardian.com/us-news/2025...
I’m the Canadian who was detained by Ice for two weeks. It felt like I had been kidnapped
I was stuck in a freezing cell without explanation despite eventually having lawyers and media attention. Yet, compared with others, I was lucky
www.theguardian.com
March 20, 2025 at 10:30 AM
"There was a girl from India who had overstayed her student visa for 3 days before heading back home. She then came back to the US on a new, valid visa to finish her master’s degree and was handed over to ICE due to the 3 days she had overstayed"
WOW. Just wow. Cruelty is in vogue for US govt. now
WOW. Just wow. Cruelty is in vogue for US govt. now
Best LLMs are decided by evals on leaderboards
(I am looking at you, Gemini)
(I am looking at you, Gemini)
Quote this post with a fact from your field which is a complete total lie, but which people outside your field would completely believe if you posted it confidently on social media
March 20, 2025 at 9:34 AM
Best LLMs are decided by evals on leaderboards
(I am looking at you, Gemini)
(I am looking at you, Gemini)
Like Notion? Well this is a open source clone sponsored by FR-DE governments. And frankly, it looks great
docs.numerique.gouv.fr/login/
docs.numerique.gouv.fr/login/
Docs
Docs: Your new companion to collaborate on documents efficiently, intuitively, and securely.
docs.numerique.gouv.fr
March 18, 2025 at 12:01 PM
Like Notion? Well this is a open source clone sponsored by FR-DE governments. And frankly, it looks great
docs.numerique.gouv.fr/login/
docs.numerique.gouv.fr/login/
The arrival of early spring *chef's kiss* Nice shots Sid. Get yourself a proper camera
March 17, 2025 at 3:47 AM
The arrival of early spring *chef's kiss* Nice shots Sid. Get yourself a proper camera
OLMo2 goodies ↓
The longer version of this story and how it relates to Gemma 3 too is here: buff.ly/5OZYGrq
For more information, read the technical blog post: buff.ly/lJxPodz
Or try the model: buff.ly/6lAGGkw
Get the artifacts here: buff.ly/Wz2VjUC
buff.ly
March 14, 2025 at 3:49 AM
OLMo2 goodies ↓
Reposted by Sourav
Announcing OLMo 2 32B: the first fully open model to beat GPT 3.5 & GPT-4o mini on a suite of popular, multi-skill benchmarks.
Comparable to best open-weight models, but a fraction of training compute. When you have a good recipe, ✨ magical things happen when you scale it up!
Comparable to best open-weight models, but a fraction of training compute. When you have a good recipe, ✨ magical things happen when you scale it up!
March 13, 2025 at 6:36 PM
Announcing OLMo 2 32B: the first fully open model to beat GPT 3.5 & GPT-4o mini on a suite of popular, multi-skill benchmarks.
Comparable to best open-weight models, but a fraction of training compute. When you have a good recipe, ✨ magical things happen when you scale it up!
Comparable to best open-weight models, but a fraction of training compute. When you have a good recipe, ✨ magical things happen when you scale it up!
True open source looks like OLMO2 😅 codes weights, recipes all available to inspect
ofc benchmarks are one thing, vibes checks are another! encourage folks to play w it & read the post
🍣 playground.allenai.org
🐙 allenai.org/blog/olmo2-32B
lookin forward to all the cool research - interpretability, training dynamics, generalization, etc - this hopefully enables 🤩
🍣 playground.allenai.org
🐙 allenai.org/blog/olmo2-32B
lookin forward to all the cool research - interpretability, training dynamics, generalization, etc - this hopefully enables 🤩
playground.allenai.org
March 14, 2025 at 3:46 AM
True open source looks like OLMO2 😅 codes weights, recipes all available to inspect
Reposted by Sourav
The 3rd edition of Interpretable Machine Learning is out! 🎉 Major cleanup, better examples, and new chapters on Data & Models, Interpretability Goals, Ceteris Paribus, and LOFO Importance.
The book remains free to read for everyone. But you can also buy ebook or paperback.
The book remains free to read for everyone. But you can also buy ebook or paperback.
March 13, 2025 at 12:09 PM
The 3rd edition of Interpretable Machine Learning is out! 🎉 Major cleanup, better examples, and new chapters on Data & Models, Interpretability Goals, Ceteris Paribus, and LOFO Importance.
The book remains free to read for everyone. But you can also buy ebook or paperback.
The book remains free to read for everyone. But you can also buy ebook or paperback.
Reposted by Sourav
Introducing our Gemma 3 open models, the most capable models that you can run on a single GPU or TPU. Multimodal, multilingual, 128k context length, and exceeds quality of other open models that are an order of magnitude larger in terms of hardware footprint. 🎉
blog.google/technology/d...
blog.google/technology/d...
Introducing Gemma 3: The most capable model you can run on a single GPU or TPU
Today, we're introducing Gemma 3, our most capable, portable and responsible open model yet.
blog.google
March 13, 2025 at 2:55 PM
Introducing our Gemma 3 open models, the most capable models that you can run on a single GPU or TPU. Multimodal, multilingual, 128k context length, and exceeds quality of other open models that are an order of magnitude larger in terms of hardware footprint. 🎉
blog.google/technology/d...
blog.google/technology/d...
Nice. Congratulations Pierre.
(I am pretty sure I won't understand it. It looks pretty dense 😂😅 so I am honest with you. But congratulations for the acceptance 🥳)
(I am pretty sure I won't understand it. It looks pretty dense 😂😅 so I am honest with you. But congratulations for the acceptance 🥳)
Our joint paper with Geoffrey Wolfer @gwolfer.bsky.social "Variance-Aware Estimation of the Kernel Mean Embedding" accepted for publication in the Journal of Machine Learning Research 🥳
arxiv.org/abs/2210.06672
arxiv.org/abs/2210.06672
Variance-Aware Estimation of Kernel Mean Embedding
An important feature of kernel mean embeddings (KME) is that the rate of convergence of the empirical KME to the true distribution KME can be bounded independently of the dimension of the space, prope...
arxiv.org
March 12, 2025 at 11:30 AM
Nice. Congratulations Pierre.
(I am pretty sure I won't understand it. It looks pretty dense 😂😅 so I am honest with you. But congratulations for the acceptance 🥳)
(I am pretty sure I won't understand it. It looks pretty dense 😂😅 so I am honest with you. But congratulations for the acceptance 🥳)
ML project naming is getting out of hands 😀
March 11, 2025 at 12:08 AM
ML project naming is getting out of hands 😀
Any news about the book release @fchollet.bsky.social ? The new chapters look promising especially
March 9, 2025 at 1:23 PM
Any news about the book release @fchollet.bsky.social ? The new chapters look promising especially
I have a solid feeling that Bsky has better academic discussion than Twitter as of now
Musk's app will be relegated to all kinds of shitposting in general by me. Serious posts belong here 😅
Musk's app will be relegated to all kinds of shitposting in general by me. Serious posts belong here 😅
March 5, 2025 at 12:28 PM
I have a solid feeling that Bsky has better academic discussion than Twitter as of now
Musk's app will be relegated to all kinds of shitposting in general by me. Serious posts belong here 😅
Musk's app will be relegated to all kinds of shitposting in general by me. Serious posts belong here 😅
Reposted by Sourav
I updated my ML lecture material: davidpicard.github.io/teaching/
I show many (boomer) ML algorithms with working implementation to prevent the black box effect.
Everything is done in notebooks so that students can play with the algorithms.
Book-ish pdf export: davidpicard.github.io/pdf/poly.pdf
I show many (boomer) ML algorithms with working implementation to prevent the black box effect.
Everything is done in notebooks so that students can play with the algorithms.
Book-ish pdf export: davidpicard.github.io/pdf/poly.pdf
David Picard
davidpicard.github.io
February 27, 2025 at 7:09 PM
I updated my ML lecture material: davidpicard.github.io/teaching/
I show many (boomer) ML algorithms with working implementation to prevent the black box effect.
Everything is done in notebooks so that students can play with the algorithms.
Book-ish pdf export: davidpicard.github.io/pdf/poly.pdf
I show many (boomer) ML algorithms with working implementation to prevent the black box effect.
Everything is done in notebooks so that students can play with the algorithms.
Book-ish pdf export: davidpicard.github.io/pdf/poly.pdf