How AutoRL works, in a nutshell: – The user describes the model they want
Ex: "A model that detects spelling and grammar errors" – OSS models generate a system prompt that will be used a) to generate, and b) for RULER to rank outputs – We generate input data, and RL a model!
RESEARCH
-
AutoRL: Automated Reinforcement Learning for Model Generation
By
–
-

Test-of-Time Award Paper on Neural Networks Research
By
–
Link to our paper in 02015: https://
arxiv.org/abs/1508.04025. and slide deck of my test-of-time award talk here: https://
drive.google.com/file/d/15SeWBS
iRjQlOBwGz65dO2SuxL6N58Lro/view?usp=sharing
… -

Attention Mechanism Paper Wins Test-of-Time Award
By
–
It’s my great honor to have just received the test-of-time award at #ACL2025 from @aclmeeting for our paper “Effective Approaches to Attention-based Neural Machine Translation” (joint work with @hyhieu226 and @chrmanning at EMNLP 2015). It’s the immediate second “attention”
-
Learning on Graphs 2024 Proceedings Published on PMLR
By
–
Volume 269 https://
proceedings.mlr.press/v269/ Proceedings of Learning on Graphs 2024 Is now available on PMLR. -

GEPA: Reflective Prompt Evolution Outperforms Reinforcement Learning
By
–
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning Agrawal et al.: https://
arxiv.org/abs/2507.19457 #ArtificialIntelligence #DeepLearning #MachineLearning -
MATLAB Campus License Available for University Students
By
–
Thank you for your interest in MATLAB! Your university may have a Campus License. You can find out more here: https://
spr.ly/6013fpErJ If you have other questions, please contact our team here: -
SciSpace Agent: AI Exclusively Built for Scientific Community
By
–
10/
— Kirk Borne (@KirkDBorne) 30 juillet 2025
Thanks for reading this thread on @SciSpace_ Agent — the first AI built exclusively for the scientific community, unlike general-purpose #AI implementations.https://t.co/RSwJ1LbJS110/
Thanks for reading this thread on @scispace Agent — the first AI built exclusively for the scientific community, unlike general-purpose #AI implementations. -
Meta Superintelligence Website Content Extraction Tutorial
By
–
Have fun: curl -s https://www.meta[.]com/superintelligence/ | pandoc -f html -t markdown | grep -i "open"
-

End Research Drudgery with SciSpace Agent Automation
By
–
9/
𝗘𝗻𝗱 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗱𝗿𝘂𝗱𝗴𝗲𝗿𝘆! 𝗥𝗲𝗰𝗮𝗽𝘁𝘂𝗿𝗲 𝟭𝟬𝟬'𝘀 𝗼𝗳 𝗵𝗼𝘂𝗿𝘀 𝗼𝗳 𝗽𝗿𝗲𝗰𝗶𝗼𝘂𝘀 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝘁𝗶𝗺𝗲. Find out more about SciSpace Agent and get started today to fast-track your research workflows and breakthroughs here: -
SciSpace Agent: AI Super Agent Co-Scientist for Lab Research
By
–
7/
— Kirk Borne (@KirkDBorne) 30 juillet 2025
@SciSpace_ Agent is an AI super agent co-scientist that works just like a member of your lab, using the same tools you use. pic.twitter.com/Va4AsMVlY47/ @scispace Agent is an AI super agent co-scientist that works just like a member of your lab, using the same tools you use.