BusyBrain⌨
@w42.bsky.social
Interested in how machine can speak human language and automated theorem proving
Reposted by BusyBrain⌨
🤯 We use the term 'intelligence' a lot, but wth do we mean?
We got 303 survey responses from researchers. The most agreed-on criteria are generalization, adaptability & reasoning.
ACL Findings preprint: arxiv.org/abs/2505.20959
with @brtrm.bsky.social @terne.bsky.social @heinrichst.bsky.social /1
We got 303 survey responses from researchers. The most agreed-on criteria are generalization, adaptability & reasoning.
ACL Findings preprint: arxiv.org/abs/2505.20959
with @brtrm.bsky.social @terne.bsky.social @heinrichst.bsky.social /1
June 2, 2025 at 9:27 AM
🤯 We use the term 'intelligence' a lot, but wth do we mean?
We got 303 survey responses from researchers. The most agreed-on criteria are generalization, adaptability & reasoning.
ACL Findings preprint: arxiv.org/abs/2505.20959
with @brtrm.bsky.social @terne.bsky.social @heinrichst.bsky.social /1
We got 303 survey responses from researchers. The most agreed-on criteria are generalization, adaptability & reasoning.
ACL Findings preprint: arxiv.org/abs/2505.20959
with @brtrm.bsky.social @terne.bsky.social @heinrichst.bsky.social /1
Reposted by BusyBrain⌨
Happy Friday everyone! I just posted what I think is an important blog post on my website. It is a critique of meta-meta-analyses: meta-analyses of meta-analyses.
Link: matthewbjane.github.io/blog-posts/b...
#stats #metascience
Link: matthewbjane.github.io/blog-posts/b...
#stats #metascience
May 23, 2025 at 10:47 PM
Happy Friday everyone! I just posted what I think is an important blog post on my website. It is a critique of meta-meta-analyses: meta-analyses of meta-analyses.
Link: matthewbjane.github.io/blog-posts/b...
#stats #metascience
Link: matthewbjane.github.io/blog-posts/b...
#stats #metascience
Reposted by BusyBrain⌨
1/🧵ICLR 2025 Spotlight Research on LM & Memorization!
Language models (LMs) often "memorize" data, leading to privacy risks. This paper explores ways to reduce that!
Paper: arxiv.org/pdf/2410.02159
Code: github.com/msakarvadia/...
Blog: mansisak.com/memorization/
Language models (LMs) often "memorize" data, leading to privacy risks. This paper explores ways to reduce that!
Paper: arxiv.org/pdf/2410.02159
Code: github.com/msakarvadia/...
Blog: mansisak.com/memorization/
March 4, 2025 at 6:15 PM
1/🧵ICLR 2025 Spotlight Research on LM & Memorization!
Language models (LMs) often "memorize" data, leading to privacy risks. This paper explores ways to reduce that!
Paper: arxiv.org/pdf/2410.02159
Code: github.com/msakarvadia/...
Blog: mansisak.com/memorization/
Language models (LMs) often "memorize" data, leading to privacy risks. This paper explores ways to reduce that!
Paper: arxiv.org/pdf/2410.02159
Code: github.com/msakarvadia/...
Blog: mansisak.com/memorization/
Reposted by BusyBrain⌨
Microtubule regulation drives an asymmetry in the regeneration of sensory neurons, with specific proteins controlling growth.
buff.ly/4ijksHC
buff.ly/4ijksHC
March 4, 2025 at 6:27 PM
Microtubule regulation drives an asymmetry in the regeneration of sensory neurons, with specific proteins controlling growth.
buff.ly/4ijksHC
buff.ly/4ijksHC
Reposted by BusyBrain⌨
1/13 New Paper!! We try to understand why some LMs self-improve their reasoning while others hit a wall. The key? Cognitive behaviors! Read our paper on how the right cognitive behaviors can make all the difference in a model's ability to improve with RL! 🧵
March 4, 2025 at 6:15 PM
1/13 New Paper!! We try to understand why some LMs self-improve their reasoning while others hit a wall. The key? Cognitive behaviors! Read our paper on how the right cognitive behaviors can make all the difference in a model's ability to improve with RL! 🧵
Reposted by BusyBrain⌨
Reading and Writing Google Sheets in DuckDB duckdb.org/2025/02/26/g...
March 1, 2025 at 10:29 AM
Reading and Writing Google Sheets in DuckDB duckdb.org/2025/02/26/g...
Reposted by BusyBrain⌨
www.nature.com/articles/s41... awesome new work out today! From the Lee lab in the intramural research program at NIMH!
Brain-wide presynaptic networks of functionally distinct cortical neurons - Nature
Behavioural-state-dependent pyramidal neurons have a distinct pattern of long-range glutamatergic inputs, with a larger proportion of thalamic versus motor cortex inputs compared with non-behavio...
www.nature.com
February 27, 2025 at 12:21 AM
www.nature.com/articles/s41... awesome new work out today! From the Lee lab in the intramural research program at NIMH!
Reposted by BusyBrain⌨
Our online book on systems principles of LLM scaling is live at jax-ml.github.io/scaling-book/
We hope that it helps you make the most of your computing resources. Enjoy!
We hope that it helps you make the most of your computing resources. Enjoy!
February 4, 2025 at 6:59 PM
Our online book on systems principles of LLM scaling is live at jax-ml.github.io/scaling-book/
We hope that it helps you make the most of your computing resources. Enjoy!
We hope that it helps you make the most of your computing resources. Enjoy!
Reposted by BusyBrain⌨
Excited to share 𝐈𝐧𝐟𝐀𝐥𝐢𝐠𝐧!
Alignment optimization objective implicitly assumes 𝘴𝘢𝘮𝘱𝘭𝘪𝘯𝘨 from the resulting aligned model. But we are increasingly using different and sometimes sophisticated inference-time compute algorithms.
How to resolve this discrepancy?🧵
Alignment optimization objective implicitly assumes 𝘴𝘢𝘮𝘱𝘭𝘪𝘯𝘨 from the resulting aligned model. But we are increasingly using different and sometimes sophisticated inference-time compute algorithms.
How to resolve this discrepancy?🧵
January 1, 2025 at 7:59 PM
Excited to share 𝐈𝐧𝐟𝐀𝐥𝐢𝐠𝐧!
Alignment optimization objective implicitly assumes 𝘴𝘢𝘮𝘱𝘭𝘪𝘯𝘨 from the resulting aligned model. But we are increasingly using different and sometimes sophisticated inference-time compute algorithms.
How to resolve this discrepancy?🧵
Alignment optimization objective implicitly assumes 𝘴𝘢𝘮𝘱𝘭𝘪𝘯𝘨 from the resulting aligned model. But we are increasingly using different and sometimes sophisticated inference-time compute algorithms.
How to resolve this discrepancy?🧵
what kind news is this? lol
“Three USAID workers said that Gemini, an A.I. program, had been installed on their email accounts, leading to fears that deputies of Elon Musk were trying to surveil their activities.”
www.nytimes.com/2025/02/01/u...
www.nytimes.com/2025/02/01/u...
End Appears Near for U.S. Aid Agency, Democratic Lawmakers Say
www.nytimes.com
February 2, 2025 at 7:44 AM
what kind news is this? lol
Reposted by BusyBrain⌨
On monday in our reading group we discuss "Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective" arxiv.org/abs/2412.03487
With Neta Shaul.
Join on zoom on Monday at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/logg
With Neta Shaul.
Join on zoom on Monday at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/logg
January 25, 2025 at 9:08 PM
On monday in our reading group we discuss "Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective" arxiv.org/abs/2412.03487
With Neta Shaul.
Join on zoom on Monday at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/logg
With Neta Shaul.
Join on zoom on Monday at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/logg
Reposted by BusyBrain⌨
🚨 Researchers uncover 4.5M fake stars on GitHub 🌟, often boosting malware disguised as pirated software & crypto bots. Fake stars surge in 2024, posing major risks to open-source trust & security.
#CyberSecurity #GitHub #OpenSource #SupplyChainSecurity
arxiv.org/abs/2412.13459
#CyberSecurity #GitHub #OpenSource #SupplyChainSecurity
arxiv.org/abs/2412.13459
4.5 Million (Suspected) Fake Stars in GitHub: A Growing Spiral of Popularity Contests, Scams, and Malware
GitHub, the de-facto platform for open-source software development, provides a set of social-media-like features to signal high-quality repositories. Among them, the star count is the most widely used...
arxiv.org
December 20, 2024 at 8:58 PM
🚨 Researchers uncover 4.5M fake stars on GitHub 🌟, often boosting malware disguised as pirated software & crypto bots. Fake stars surge in 2024, posing major risks to open-source trust & security.
#CyberSecurity #GitHub #OpenSource #SupplyChainSecurity
arxiv.org/abs/2412.13459
#CyberSecurity #GitHub #OpenSource #SupplyChainSecurity
arxiv.org/abs/2412.13459
Reposted by BusyBrain⌨
That exhilarating feeling that *everything is possible* when you open an editor to code, it hopefully never goes away.
December 9, 2024 at 7:25 AM
That exhilarating feeling that *everything is possible* when you open an editor to code, it hopefully never goes away.
Reposted by BusyBrain⌨
Binary code is pervasive, and binary analysis is a key task in reverse engineering, malware classification, and vulnerability discovery. So, they created Assemblage - the dataset of source-to-binary projects compiled from GitHub.
Assemblage - A dataset of binary executable corpuses
Assemblage - A dataset of binary executable corpuses
December 8, 2024 at 2:58 AM
Binary code is pervasive, and binary analysis is a key task in reverse engineering, malware classification, and vulnerability discovery. So, they created Assemblage - the dataset of source-to-binary projects compiled from GitHub.
Assemblage - A dataset of binary executable corpuses
Assemblage - A dataset of binary executable corpuses
Reposted by BusyBrain⌨
What came first, life or evolution?
Does evolution act on non-living materials?
Competitive Exclusion among Self-Replicating Molecules Curtails the Tendency of Chemistry to Diversify 🧪
www.nature.com/articles/s41...
Self-replicating molecules demonstrate basic principles of Darwinian evolution
Does evolution act on non-living materials?
Competitive Exclusion among Self-Replicating Molecules Curtails the Tendency of Chemistry to Diversify 🧪
www.nature.com/articles/s41...
Self-replicating molecules demonstrate basic principles of Darwinian evolution
December 5, 2024 at 1:30 PM
What came first, life or evolution?
Does evolution act on non-living materials?
Competitive Exclusion among Self-Replicating Molecules Curtails the Tendency of Chemistry to Diversify 🧪
www.nature.com/articles/s41...
Self-replicating molecules demonstrate basic principles of Darwinian evolution
Does evolution act on non-living materials?
Competitive Exclusion among Self-Replicating Molecules Curtails the Tendency of Chemistry to Diversify 🧪
www.nature.com/articles/s41...
Self-replicating molecules demonstrate basic principles of Darwinian evolution
this morning walk, an ideas stuck me: can you play chess on Rubik's Cube (does not have to be 3x3 one)? not just chess with 6 sides, but normal chess board abstracted away to Rubik's Cube representation and operation
December 2, 2024 at 6:27 PM
this morning walk, an ideas stuck me: can you play chess on Rubik's Cube (does not have to be 3x3 one)? not just chess with 6 sides, but normal chess board abstracted away to Rubik's Cube representation and operation
Reposted by BusyBrain⌨
Half of Twitter right now is people getting mad at some random lady that got a literature PhD. Seems a bit crazy to get so mad about, but I do agree woke academia has become silly and we need to go back to when it was about real solid research, like measuring skull sizes to determine personalities
December 2, 2024 at 12:02 PM
Half of Twitter right now is people getting mad at some random lady that got a literature PhD. Seems a bit crazy to get so mad about, but I do agree woke academia has become silly and we need to go back to when it was about real solid research, like measuring skull sizes to determine personalities
Reposted by BusyBrain⌨
Good news everyone! A new version of graph-tool is just out! @graph-tool.skewed.de
graph-tool.skewed.de
Graph-tool is a comprehensive and efficient Python library to work with networks, including structural, dynamical, and statistical algorithms, as well as visualization. 1/N
#networkscience
graph-tool.skewed.de
Graph-tool is a comprehensive and efficient Python library to work with networks, including structural, dynamical, and statistical algorithms, as well as visualization. 1/N
#networkscience
December 2, 2024 at 12:55 PM
Good news everyone! A new version of graph-tool is just out! @graph-tool.skewed.de
graph-tool.skewed.de
Graph-tool is a comprehensive and efficient Python library to work with networks, including structural, dynamical, and statistical algorithms, as well as visualization. 1/N
#networkscience
graph-tool.skewed.de
Graph-tool is a comprehensive and efficient Python library to work with networks, including structural, dynamical, and statistical algorithms, as well as visualization. 1/N
#networkscience
Reposted by BusyBrain⌨
An aspect of flow matching which I find a bit interesting is that it is covariant under affine changes of coordinate (c.f. optimal transport, which need not be). This allows for a few nice WLOGs, which I imagine have more applications than I realise.
Optimal transport computes an interpolation between two distributions using an optimal coupling. Flow matching, on the other hand, uses a simpler “independent” coupling, which is the product of the marginals.
December 2, 2024 at 1:21 PM
An aspect of flow matching which I find a bit interesting is that it is covariant under affine changes of coordinate (c.f. optimal transport, which need not be). This allows for a few nice WLOGs, which I imagine have more applications than I realise.
If you think the out (site) group isn't enjoying thinking like your ingroup, I've lost respect for you. Sorry.
December 1, 2024 at 10:10 PM
If you think the out (site) group isn't enjoying thinking like your ingroup, I've lost respect for you. Sorry.
Reposted by BusyBrain⌨
Reposted by BusyBrain⌨
More formal verification, this time from the engineers at Cloudflare using a lesser-known verification stack:
Cloudflare uses racket & rosette, a solver-aided programming system to, ensure the correctness of their DNS query engine configuration
blog.cloudflare.com/topaz-policy...
Cloudflare uses racket & rosette, a solver-aided programming system to, ensure the correctness of their DNS query engine configuration
blog.cloudflare.com/topaz-policy...
How we prevent conflicts in authoritative DNS configuration using formal verification
We describe how Cloudflare uses a custom Lisp-like programming language and formal verifier (written in Racket and Rosette) to prevent logical contradictions in our authoritative DNS nameserver’s beha...
blog.cloudflare.com
November 21, 2024 at 11:50 AM
More formal verification, this time from the engineers at Cloudflare using a lesser-known verification stack:
Cloudflare uses racket & rosette, a solver-aided programming system to, ensure the correctness of their DNS query engine configuration
blog.cloudflare.com/topaz-policy...
Cloudflare uses racket & rosette, a solver-aided programming system to, ensure the correctness of their DNS query engine configuration
blog.cloudflare.com/topaz-policy...
Reposted by BusyBrain⌨
Some recent discussions made me write up a short read on how I think about doing computer vision research when there's clear potential for abuse.
Alternative title: why I decided to stop working on tracking.
Curious about other's thoughts on this.
lb.eyer.be/s/cv-ethics....
Alternative title: why I decided to stop working on tracking.
Curious about other's thoughts on this.
lb.eyer.be/s/cv-ethics....
November 29, 2024 at 2:51 PM
Some recent discussions made me write up a short read on how I think about doing computer vision research when there's clear potential for abuse.
Alternative title: why I decided to stop working on tracking.
Curious about other's thoughts on this.
lb.eyer.be/s/cv-ethics....
Alternative title: why I decided to stop working on tracking.
Curious about other's thoughts on this.
lb.eyer.be/s/cv-ethics....
Reposted by BusyBrain⌨
I don't know if this was known or not, but if you open your Google search page, type 'Chicxulub' and press enter, something interesting happens.
Easter egg? But a funny one!
Easter egg? But a funny one!
November 30, 2024 at 6:59 PM
I don't know if this was known or not, but if you open your Google search page, type 'Chicxulub' and press enter, something interesting happens.
Easter egg? But a funny one!
Easter egg? But a funny one!