Paper2comic

@demishassabis @IsomorphicLabs @maxjaderberg

@demishassabis @IsomorphicLabs @maxjaderberg

The drug design engine we’re building at @IsomorphicLabs is extending the SOTA further across key benchmarks, showing huge progress in accuracy and capabilities critical for in-silico drug discovery. Incredible work from @maxjaderberg and the entire team at Isomorphic Labs!

A short comic to explain the idea from the paper “IsoDDE : The Isomorphic Labs Drug Design Engine unlocks a new frontier beyond AlphaFold”. ⚠️ This comic simplifies and exaggerates some concepts for easier understanding and may contain inaccuracies. For precise details, please refer to the original Blog @IsomorphicLabs Paper : isomorphiclabs.com/articles/the-i…

A short comic to explain the idea from the paper “Learning to Reason in 13 Parameters : TinyLoRA”. ⚠️ This comic simplifies and exaggerates some concepts for easier understanding and may contain inaccuracies. For precise details, please refer to the original paper. Original research by @jxmnop Paper : arxiv.org/abs/2602.04118

A short comic to explain the idea from the paper “EchoJEPA: A Latent Predictive Foundation Model for Echocardiography”. ⚠️ This comic simplifies and exaggerates some concepts for easier understanding and may contain inaccuracies. For precise details, please refer to the original paper. 📷 Original research by @alifmunim 📷x.com/alifmunim/stat…📷 Paper: arxiv.org/abs/2602.02603

🎨 A short comic to explain the idea from the paper “ReasonCACHE: Teaching LLMs To Reason Without Weight Updates”. ⚠️ This comic simplifies and exaggerates some concepts for easier understanding and may contain inaccuracies. For precise details, please refer to the original paper. 📄 Original research by @sharut_gupta 🧵 Related post: x.com/sharut_gupta/s… 📄 Paper: arxiv.org/abs/2602.02366

A short comic to explain the idea from the paper “Residual Context Diffusion Language Models (RCD)”. This comic simplifies and exaggerates some concepts for easier understanding and may contain inaccuracies. For precise details, please refer to the original paper. Original research by @Harman26Singh Related post: x.com/Harman26Singh/… Paper: arxiv.org/abs/2601.22954

@KuangYilun @YashDagad @randall_balestr @ylecun

@KuangYilun @YashDagad @randall_balestr @ylecun Turning complex papers into easy comics is my recent project. They involve some simplification and exaggeration, so experts might find them a bit lacking—but I hope it makes the research easier for everyone to understand.

How do we build sparsity into JEPA representations by design, while preserving task-relevant information? Introducing Rectified LpJEPA, a JEPA architecture that learns sparse, non-negative, informative representations through principled distributional regularization. 📐 📄 Paper: arxiv.org/abs/2602.01456 💻 Code: github.com/YilunKuang/rec… 📝 Blog: yilunkuang.github.io/blog/2026/rect… (1/n)

@grok @HNethatla92187 @arrakis_ai

@grok @HNethatla92187 @arrakis_ai I made comic about this. I hope ordinary people like me can understand it a little bit better.

SWE-bench Verified 93.7% ?!

@lmthang @quocleix @thtrieu_ @gjb_ai @DawsenHwang @jj_at_brown @kimshmath @Carlein90 @nurijunsu @AcerFur @kaiyinghou

@lmthang @quocleix @thtrieu_ @gjb_ai @DawsenHwang @jj_at_brown @kimshmath @Carlein90 @nurijunsu @AcerFur @kaiyinghou

This is the second paper from our series “Semi-Autonomous Mathematics Discovery with Gemini: A Case Study on the Erdős Problems”. Our agent #aletheia powered by #DeepThink cracked 13 ‘Open’ Erdős problems: 5 novel autonomous solutions, and 8 through existing literature. It was a lot of fun as the world went crazy on Erdős problems while we patiently scanned over 700 problems :) Paper link and more details below.

@lmthang Huge respect for the breakthrough with Aletheia! I made this comic to visualize the 'relay race' between humans and AI described in your research. It's slightly simplified and dramatized for easy reading, but I wanted to share the brilliance of your paper with everyone.

There has been so much noise on AI for Math research. We have been working on research-level math for over a year (in parallel with our IMO Olympiad math effort) and obtained many results including solving Erdős problems (and beyond!). We haven't shared much in the past yet as we want to do things responsibly with respect to the math community. We're almost done! Yesterday, we released the first paper in our series: Solving a generalized version of Erdős-1051 problem! More to come! #DeepThink