These researchers get a plethora of smaller self-similar sub-models to train in tandem with their primary model Youtube: youtu.be/3o3CG6wbwm8 ArXiv: arxiv.org/abs/2408.01031 Bytez: bytez.com/docs/arxiv/240… alphaXiv: alphaxiv.org/abs/2408.01031

Students at Stanford have built alphaXiv, an open discussion forum for arXiv papers. Think of it as 𝕏 for research.

alphaxiv.org

alphaXiv is like community notes for AI papers. It also looks like a useful resource for finding good papers, insights, and research ideas. Definitely worth checking out! Here is my 10 min overview of alphaXiv: youtu.be/2YSOPncByt4 Web: alphaxiv.org I spend a

Thanks for sharing! We plan on expanding to bioRxiv/medRxiv in the near future. Would love to get your thoughts, please DM us!

Contrary to the current deep learning hype, when it comes to predicting chaotic systems lightweight ML methods actually perform better YouTube: youtu.be/g4VpfWNelI4 ArXiv: arxiv.org/abs/2407.20158 Bytez: bytez.com/docs/arxiv/240… alphaXiv: alphaxiv.org/abs/2407.20158

Thanks for sharing! Vercel has been great for us

Introducing TaskGen, an open-sourced task-based, memory-infused LLM agentic framework that uses an Agent to break down a task into subtasks and assigns each subtask to either an equipped function or another Agent. Talk directly with JohnTanChongMin and the TaskGen team here!

JohnTanChongMin Leave your thoughts and comments here! alphaxiv.org/abs/2407.15734…

Site Updates! - faster, more consistent load times - support for older paper IDs: /math, /hep-th, /cs, /gr-qc - improvements to claiming your paper with ORCID

Sharing an idea that offers an exciting use case of the AI Scientist from Sakana AI! Rather than generating new ideas, one can adapt the code to pick a paper and test its results. "Reproducibility as a platform." Thanks lakshaytalkstocomputer and Cong Lu for the insight!

This paper lets auto-regressive decoders "think ahead" by cross-attending to sentence embeddings created with a diffusion model YouTube: youtu.be/z7d0_dLTtLw arXiv.org: arxiv.org/abs/2408.04220 Bytez: bytez.com/docs/arxiv/240… alphaXiv: alphaxiv.org/abs/2408.04220

Join Our Team 🚀 We're looking for a full-time full-stack/backend engineer to continue growing the platform and fulfill our mission of open & interactive research. If you have an excellent webdev background and align with our mission, please DM us or email [email protected]!