| 1 | Jul 24, '23 | This design is better than “𝕏”. | 80.4× | 5M | 92k | 9.2k | 861 |
| 2 | Oct 1, '21 | The Mysteries of the Universe | 61.5× | 0 | 82k | 18k | 2k |
| 3 | Oct 5, '20 | Nothing against @JeffBezos but this is the stuff of evil genius villians 🙃 | 60.8× | 0 | 67k | 11k | 2.1k |
| 4 | Apr 15, '22 | Trolley problem solved: | 42× | 0 | 57k | 11k | 1.5k |
| 5 | Nov 28, '19 | Gradient descent is used in many ways at Tesla | 33× | 0 | 50k | 7.3k | 436 |
| 6 | Apr 29, '23 | Pushing around these little robot soccer players, from DeepMind’s “Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning” paper. | 28× | 1.7M | 4.1k | 656 | 697 |
| 7 | Jan 6, '23 | A #StableDiffusion model trained on images of Japanese Kanji characters came up with “Fake Kanji” for novel concepts like Skyscraper, Pikachu, Elon Musk, Deep Learning, YouTube, Gu | 20.5× | 1.3M | 3.5k | 715 | 517 |
| 8 | Jul 13, '25 | Google’s Gemini 2.5 paper has 3295 authors | 19.5× | 1.2M | 3k | 427 | 769 |
| 9 | Dec 28, '22 | High resolution inpainting experiment with #StableDiffusion2 Transporting the famous Futaba Sushi restaurant in Ginza, Tokyo, to other cities, countries, planets, and finally, to a | 13.8× | 852k | 1.5k | 274 | 228 |
| 10 | Jan 11, '23 | The opening line of David Goodstein’s textbook, “States of Matter” 🤯 | 13.4× | 831k | 7.3k | 1.1k | 552 |
| 11 | May 12, '23 | AI Twitter these days. 👇🧵 | 12.9× | 798k | 7.9k | 1.1k | 186 |
| 12 | Jun 22, '24 | Language is primarily a tool for communication rather than thought “Language is a defining characteristic of our species, but the function, or functions, that it serves has been de | 10.4× | 645k | 1.4k | 309 | 1k |
| 13 | May 22, '23 | LIMA, a 65B LLaMa fine-tuned only with supervised learning on 1000 curated examples, without any RLHF, demonstrates remarkably strong performance, generalizes well to unseen tasks | 9.6× | 591k | 1.5k | 223 | 602 |
| 14 | Aug 17, '23 | Personal Announcement! I’m launching @SakanaAILabs together with my friend, Llion Jones (@YesThisIsLion). is a new R&D-focused company based in Tokyo, Japan. We’re on a quest t | 9.3× | 573k | 2.7k | 393 | 290 |
| 15 | Dec 23, '22 | If Google doesn’t get their act together and start shipping, they will go down in history as the company who nurtured and trained an entire generation of machine learning researche | 9.2× | 570k | 1.8k | 173 | 180 |
| 16 | Oct 22, '23 | Artificial lifeforms are super fascinating to watch. These self-organizing, self-replicating, “lifeforms” emerged from a continuous time cellular automata system called Flow-Lenia. | 9.2× | 569k | 2.5k | 483 | 724 |
| 17 | May 27, '23 | I prefer: MANGA 💕💖✨ | 8.9× | 552k | 3k | 527 | 121 |
| 18 | Jun 6, '23 | QR codes created using Stable Diffusion and ControlNet. This is Art. | 8.6× | 534k | 3.5k | 442 | 449 |
| 19 | Jun 28, '20 | drone pilots | 7.1× | 0 | 8.6k | 1.9k | 357 |
| 20 | Feb 23, '20 | I just ordered this book for my kids. | 6.9× | 0 | 8.9k | 1.8k | 260 |
| 21 | Dec 30, '22 | "Some rich people lost all their fortunes and became homeless" #StableDiffusion2 #AIart (Source: ) | 6.7× | 413k | 2.5k | 269 | 214 |
| 22 | Apr 23, '23 | Deploying large language models to production: | 6.4× | 399k | 5.2k | 696 | 115 |
| 23 | Dec 22, '24 | AI generated videos out of control 😹 | 6.3× | 388k | 5.4k | 588 | 801 |
| 24 | Jun 2, '25 | Facebook AI Research is the OG “Open” AI | 5.7× | 353k | 2.9k | 249 | 571 |
| 25 | Jan 24, '25 | DeepSeek is a side project 🔥 | 5.7× | 350k | 3.1k | 305 | 584 |
| 26 | Mar 1, '23 | This is what life is like at a Generative AI startup. | 5.6× | 347k | 3.4k | 373 | 142 |
| 27 | Apr 6, '25 | 😅 | 5.1× | 317k | 8.3k | 132 | 212 |
| 28 | Dec 3, '23 | Being able to fool AI detection algorithms IRL will be an important survival skill in the 21st century 👻 | 5.1× | 316k | 1.5k | 220 | 210 |
| 29 | Jun 11, '23 | OpenAI, Google & Anthropic ban the use of the generated output content from their AI models to train other AI models, under their terms-of-service. However, they’ve been using | 4.9× | 300k | 1.4k | 322 | 201 |
| 30 | Apr 14, '24 | Announcing NeurIPS Preschool Track This year, we invite preschoolers to submit machine learning research papers. | 4.6× | 287k | 2.8k | 373 | 292 |
| 31 | Mar 25 | I’m incredibly proud of The AI Scientist team for this milestone publication in @Nature. We started this project to explore if foundation models could execute the entire research l | 4.6× | 283k | 1.2k | 155 | 738 |
| 32 | May 26, '24 | Infinitely Recursive of Game of Life. Life and civilization emerges from self-organization at different levels of complexity. | 4.3× | 268k | 1.8k | 348 | 551 |
| 33 | May 12, '25 | New Paper: Continuous Thought Machines 🧠 Neurons in brains use timing and synchronization in the way that they compute, but this is largely ignored in modern neural nets. We belie | 4.2× | 258k | 3.1k | 543 | 2.1k |
| 34 | Sep 23, '23 | TinyML and Efficient Deep Learning Computing MIT 6.5940 () “This course will introduce efficient AI computing techniques that enable powerful deep learning applications on resource | 3.9× | 240k | 1.3k | 211 | 1.3k |
| 35 | Apr 22, '19 | We're living in a cyberpunk future: “Fooling automated surveillance cameras: adversarial patches to attack person detection” | 3.8× | 0 | 3.6k | 1.6k | 181 |
| 36 | Sep 4, '24 | Excited to announce our Series A! We raised more than $100M to grow Sakana AI into a World Class AI Lab in Japan. We’re going to really push the frontiers of what’s possible with A | 3.8× | 234k | 1.4k | 103 | 158 |
| 37 | Aug 29, '23 | Anti-hype LLM reading list. Pretty good list. | 3.7× | 229k | 2.4k | 452 | 2k |
| 38 | Oct 28, '21 | An auto-encoder with a very strong inductive bias. | 3.5× | 0 | 4.3k | 1k | 223 |
| 39 | Jan 30, '19 | A fun way to learn about neural networks and AI is to implement a simulation game giving your agents little neural net brains, and training them using a simple method like evolutio | 2.9× | 0 | 3.1k | 1.1k | 201 |
| 40 | Jun 13, '23 | Life before GPUs. | 2.8× | 172k | 1.5k | 156 | 76 |
| 41 | Feb 10, '21 | The most important formula in deep learning after 2018 | 2.8× | 0 | 3k | 489 | 729 |
| 42 | Dec 27, '20 | Interesting physics analogy of ML from the viewpoint of compression (@elonmusk) “Physics formulas are compression algorithms for reality…If you ran physics simulation of the univer | 2.8× | 0 | 3.2k | 530 | 426 |
| 43 | Oct 24, '20 | One of the most well-known pieces of software for downloading YouTube videos, “youtube-dl” was removed from GitHub following a takedown notice from the Recording Industry Associati | 2.7× | 0 | 2.8k | 883 | 263 |
| 44 | Mar 21, '19 | This person took ~1700 pages of notes in mathematics lectures using LaTeX and Vim, and documented the workflow: | 2.7× | 0 | 2.7k | 862 | 291 |
| 45 | Oct 4, '22 | New blog post: Collective Intelligence for Deep Learning Recently, @yujin_tang and I published a paper about how ideas like swarm behavior, self-organization, emergence are gaining | 2.5× | 0 | 2.3k | 445 | 796 |
| 46 | Jul 9, '22 | MIT offers an excellent course on Deep Learning for Art, Aesthetics, and Creativity. All of the lecture videos are available on YouTube, with a fantastic list of speakers: | 2.3× | 0 | 1.9k | 392 | 892 |
| 47 | Aug 15, '19 | Teams of high school students built bottle-flipping robots for RoboCon 2018 in Japan | 2.3× | 0 | 2.5k | 797 | 69 |
| 48 | Jun 12, '19 | Weight Agnostic Neural Networks 🦎 Inspired by precocial species in biology, we set out to search for neural net architectures that can already (sort of) perform various tasks even | 2.0× | 0 | 2.1k | 622 | 242 |
| 49 | Feb 21, '25 | After many years, this guy has come back to haunt me. | 1.8× | 110k | 1.4k | 62 | 136 |
| 50 | Oct 27, '17 | I'm blown away by the method and results in this paper. Progressive growing neural nets may be a trend we will see in 2018. | 1.8× | 0 | 1.9k | 770 | 1 |
| 51 | May 9, '20 | data preprocessing | 1.7× | 0 | 2.6k | 364 | 36 |
| 52 | Aug 16, '20 | Roman Emperor Project Using GAN-based tools to help create photorealistic portraits of Roman Emperors from historical references Project Article | 1.7× | 0 | 2k | 510 | 124 |
| 53 | Sep 25, '19 | Using gradient descent for everything | 1.7× | 0 | 2.3k | 418 | 49 |
| 54 | Dec 21, '18 | A GAN trained on accepted @CVPR papers. | 1.7× | 0 | 1.9k | 581 | 68 |
| 55 | Sep 15, '20 | How do you skim a research paper? I usually read (in order): 1) abstract 2) 1st paragraph of the intro 3) last paragraph of intro (for contributions) 4) 1st paragraph of the conclu | 1.7× | 0 | 1.9k | 314 | 356 |
| 56 | May 11, '22 | Interesting application combining computer vision and high-powered lasers to eradicate weeds on a farm. | 1.7× | 0 | 2.1k | 372 | 151 |
| 57 | Mar 23, '24 | I love the diversity of Tokyo’s urban architecture. This Tiny House is designed by Atelier Tekuto. | 1.6× | 101k | 1.7k | 119 | 169 |
| 58 | Apr 12, '20 | RIP, John Conway. | 1.6× | 0 | 1.8k | 651 | 19 |
| 59 | Sep 18, '18 | 4 hours of baby play in 2 minutes | 1.6× | 0 | 1.9k | 440 | 79 |
| 60 | Nov 26, '18 | This amazing book on the foundations of machine learning is now available for free from Microsoft as a PDF download. I learned so much from this book over the years, and I feel tha | 1.6× | 0 | 1.6k | 530 | 237 |
| 61 | Mar 2, '20 | Jupyter notebooks with Python examples for reproducing examples from each chapter of Christopher Bishop's “Pattern Recognition and Machine Learning” textbook (also available for fr | 1.6× | 0 | 1.4k | 404 | 428 |
| 62 | May 5, '20 | PixelMe: Convert your photo into Pixel Art | 1.6× | 0 | 1.6k | 363 | 328 |
| 63 | Jun 23, '18 | Papers with Code: A searchable site that links machine learning papers on ArXiv with code on GitHub. They also tag any framework libraries used, along with other info like GitHub s | 1.6× | 0 | 1.6k | 607 | 111 |
| 64 | May 13, '22 | Asked #Dalle to generate photographs of the bear stock market in the 1930s | 1.5× | 0 | 2k | 345 | 100 |
| 65 | May 16, '19 | A Line Rider on Beethoven's 5th Symphony | 1.5× | 0 | 1.6k | 541 | 79 |
| 66 | Jul 12, '22 | The map of the brain, created by an aerospace engineer. These are the result of six years of research. It’s always interesting to me to view the perspective of one challenging scie | 1.5× | 0 | 1.4k | 301 | 498 |
| 67 | Nov 6, '21 | Face to Anime using AnimeGANv2 | 1.5× | 0 | 1.6k | 338 | 326 |
| 68 | Oct 6, '20 | Neural network video streaming SDK from @NVIDIAAI can compress video conference data like these at ~0.1KB / frame, roughly 1000x better than H.264 (MPEG-4) compression on the same | 1.5× | 0 | 1.6k | 429 | 125 |
| 69 | Jul 22, '17 | Decoding the Enigma with RNNs. They trained a LSTM with 3000 hidden units to decode ciphertext with 96%+ accuracy. | 1.5× | 0 | 1.4k | 731 | 3 |
| 70 | Sep 30, '22 | Some personal news: After six years at Google, I decided it was time for me to leave and try something new again. I had a fantastic time at Google Brain, and I’ll miss my friends, | 1.5× | 0 | 2.6k | 42 | 55 |
| 71 | Oct 16, '22 | This #StableDiffusion add-on for Blender looks amazing. @AI_Render renders an AI-generated image based on a text prompt and your scene in Blender. | 1.5× | 0 | 1.4k | 311 | 397 |
| 72 | Apr 30, '19 | A series of blog posts on applying machine learning to architecture Experiments: Background: | 1.5× | 0 | 1.6k | 476 | 127 |
| 73 | Apr 29, '20 | Fooling Facial Detection with Fashion Nice article surveying common face detection methods, and tests practical implementations of adversarial patches on a face mask for fooling th | 1.4× | 0 | 1.5k | 464 | 179 |
| 74 | Aug 6, '20 | Self-attention mechanism can be viewed as the update rule of a Hopfield network with continuous states. Deep learning models can take advantage of Hopfield networks as a powerful c | 1.4× | 0 | 1.4k | 349 | 357 |
| 75 | Jul 7, '20 | Also how deep learning models are trained on a MacBook | 1.4× | 0 | 2.1k | 271 | 45 |
| 76 | Aug 12, '18 | Academic Torrents is a distributed system for sharing enormous datasets. So far they have made 27.23TB of research data available. | 1.4× | 0 | 1.4k | 516 | 148 |
| 77 | Jun 16, '21 | Proof by meme? | 1.4× | 0 | 2.1k | 270 | 26 |
| 78 | May 13, '19 | An interactive article explaining why weight initialization is so important for training neural nets by @deeplearningai_, written in the format. | 1.4× | 0 | 1.5k | 455 | 177 |
| 79 | Oct 31, '20 | A.I. camera mistakes referee’s bald head for ball, follows it through the match. | 1.4× | 0 | 1.5k | 303 | 61 |
| 80 | Dec 20, '21 | I’m super excited to see ideas from complex systems such as swarm intelligence, self-organization, and emergent behavior gain traction again in AI research. We wrote a survey of re | 1.4× | 0 | 1.4k | 281 | 342 |
| 81 | Jun 7, '22 | “Oriental Painting of Sun Tzu playing a game of Warcraft II on his desktop compute” generated using #Dalle | 1.4× | 0 | 1.8k | 293 | 107 |
| 82 | Jun 3, '20 | Machines see objects Humans see ideology | 1.3× | 0 | 1.8k | 357 | 47 |
| 83 | Jun 21, '20 | uh oh... | 1.3× | 0 | 1.7k | 370 | 53 |
| 84 | Apr 6, '20 | Dive into Deep Learning: An interactive deep learning book with code, math, and discussions, based on the NumPy interface. I really like the format of the textbook! | 1.3× | 0 | 1.4k | 319 | 312 |
| 85 | Oct 10, '18 | Reinforcement Learning for Improving Agent Design: What happens when we let an agent learn a better body design together with learning its task? article: pdf: | 1.3× | 0 | 1.5k | 405 | 103 |
| 86 | Aug 2, '17 | how probability distributions are related | 1.3× | 0 | 1.4k | 459 | 69 |
| 87 | Sep 15, '21 | Uber developed a system of nested hexagons to represent space, called H3: | 1.3× | 0 | 1.4k | 182 | 253 |
| 88 | Oct 1, '20 | The most well-dressed snowball fight, colorized using deep learning. | 1.2× | 0 | 1.7k | 306 | 72 |
| 89 | May 26, '20 | “First Order Motion Model for Image Animation” hooked up to a live camera: Original NeurIPS2019 paper / code: | 1.2× | 0 | 1.5k | 310 | 165 |
| 90 | Jan 18, '20 | Edo period cat meme | 1.2× | 0 | 1.3k | 459 | 46 |
| 91 | Oct 29, '21 | MANGA sounds better than FAANG | 1.2× | 0 | 1.4k | 399 | 30 |
| 92 | Sep 22, '22 | "Anime scene of Yann Lecun at Bell Labs working on convolutional neural networks." #StableDiffusion | 1.1× | 0 | 1.8k | 136 | 63 |
| 93 | Dec 15, '21 | With the right body, no brain is needed. | 1.1× | 0 | 1.4k | 228 | 128 |
| 94 | Oct 19, '20 | Conventional thinking: Build a robot to solve the problem. Out-of-the-box thinking: Get the problem to solve itself. Example: Self-solving Rubik's Cube by @takashikaburagi | 1.1× | 0 | 1.3k | 275 | 69 |
| 95 | Apr 21, '20 | Oil should learn to code. | 1.0× | 0 | 1.5k | 253 | 10 |
| 96 | Dec 6, '21 | This must be where the Bayesians meet up on the weekends | 1.0× | 0 | 1.6k | 194 | 33 |
| 97 | Mar 4, '19 | Using deep learning to implement linear regression | 1.0× | 0 | 1.3k | 290 | 16 |
| 98 | Aug 9, '20 | One year after building rock solid technical infrastructure for your machine learning research project | 1.0× | 0 | 1.5k | 193 | 49 |
| 99 | May 25, '22 | i feel seen | 0.9× | 0 | 1.4k | 143 | 25 |