𝚅𝚒𝚝𝚊𝚕𝚢𝚁 @der_emacs

Learning mathematics https://t.co/vFU49GDT1k vitalyr.com Joined September 2016

Tweets

4K
Followers

648
Following

2K
Likes

9K

Jeremy Cohen @deepcohen

16 hours ago

Our paper was published last ICLR and is on arXiv here: arxiv.org/abs/2410.24206. We've also created an blog version of the paper, with fun animated optimization trajectories: centralflows.github.io/part1/.

1 6 55 4K 34

Download Image

𝚅𝚒𝚝𝚊𝚕𝚢𝚁 @der_emacs

15 hours ago

Do you remember when you joined X? I do! #MyXAnniversary

0 0 0 22 0

Download Image

𝚅𝚒𝚝𝚊𝚕𝚢𝚁 @der_emacs

2 weeks ago

今天上了搏击课，练了直拳，摆拳，勾拳和泰拳的两种肘击。

0 0 2 96 0

François Chollet @fchollet

2 weeks ago

Buy the book from Amazon: amazon.com/Learning-Pytho… Buy the book from the publisher: manning.com/books/deep-lea… Read the free website: deeplearningwithpython.io The new edition has a ton more content around generative AI. It also covers JAX & PyTorch fundamentals, and everything new…

20 100 646 34K 609

Hiroki Furuta @frt03_

2 weeks ago

Two papers are accepted at #NeurIPS2025 🎉 (1) Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties arxiv.org/abs/2506.05744 (2) Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search arxiv.org/abs/2501.19252

7 33 305 36K 178

Quanta Magazine @QuantaMagazine

2 weeks ago

You can try it for yourself here: distill.pub/2020/growing-c… Read more about neural cellular automata: quantamagazine.org/self-assembly-…

5 75 370 20K 237

Download Video

Simone Scardapane @s_scardapane

2 weeks ago

*The Origins of Representation Manifolds in LLMs* by Modell et al. They study the presence of "interpretable features" in LLMs embedded as manifolds and how their geometry connects to the internal representations of the models. arxiv.org/abs/2505.18235

15 162 1K 52K 689

Download Image

𝚅𝚒𝚝𝚊𝚕𝚢𝚁 @der_emacs

3 weeks ago

开心一点吧

0 0 0 92 0

Download Image

Thinking Machines @thinkymachines

3 weeks ago

Today Thinking Machines Lab is launching our research blog, Connectionism. Our first blog post is “Defeating Nondeterminism in LLM Inference” We believe that science is better when shared. Connectionism will cover topics as varied as our research is: from kernel numerics to…

241 1K 8K 3.2M 5K

Download Image

𝚅𝚒𝚝𝚊𝚕𝚢𝚁 @der_emacs

3 weeks ago

libreboot创始人莫名其妙把我ban了。我2023年订阅了她一个月后取消了

0 0 3 276 1

Download Image

𝚅𝚒𝚝𝚊𝚕𝚢𝚁 @der_emacs

4 weeks ago

1 0 1 169 0

Download Image

Dan Hollick @DanHollick

a month ago

Last week, I published a chapter about color. It's fairly comprehensive: makingsoftware.com/chapters/color…

66 310 3K 124K 2K

Download Video

Simone Scardapane @s_scardapane

4 weeks ago

*Harnessing the Universal Geometry of Embeddings* by @rishi_d_jha @jxmnop @shmatikov With the proper set of losses, text embeddings from different models can be aligned with no paired data (what they call the "strong" Platonic hypothesis). arxiv.org/abs/2505.12540

1 62 377 19K 271

Download Image

𝚅𝚒𝚝𝚊𝚕𝚢𝚁 @der_emacs

a month ago

我等了五年

Team Cherry @TeamCherryGames

a month ago

我等了五年

2K 21K 74K 7.9M 3K

0 0 0 56 0

Vivek Galatage @vivekgalatage

a month ago

This paper shows how rearchitecting B+trees for SIMD brings multi-fold improvements in query throughput. If you are keen to deep dive into SIMD, this is a highly recommended read - "A High Throughput B+tree for SIMD Architectures". ece.lsu.edu/lpeng/papers/t…

Vivek Galatage @vivekgalatage

a month ago

2 136 1K 113K 1K

Download Image

1 41 333 15K 256

Download Image

𝚅𝚒𝚝𝚊𝚕𝚢𝚁 @der_emacs

a month ago

0 0 0 59 0

Download Image

Haeun Yu @hayu204

2 months ago

🙋 How do Large Language Models internally process cultural knowledge? 🌐 Happy to share our new preprint "Entangled in Representations: Mechanistic Investigation of Cultural Biases in Large Language Models" 📃 Paper: arxiv.org/abs/2508.08879