- my long term goal is to map the field of 'X'. it should be very comprehensive. at some point i would like to write a survey. can you help me out with the literature search? - [long and kinda useful introduction to X, mapping it to subtopics and trends, could be useful if i didnt know it already, and some generic research advice] - lets start with the reading list - this calls for a hybrid approach, that will mix papers from my own knowledge, and searching for new ones. one need to be methodological about it. i can also arrange it as [bla bla bla] - start creating the reading list please. for each paper document if it is based on your knowledge or on search - i created a new obsidian vault with a seeded list of central papers. for each one, i listed some key insights in its own markdown file. do you want me to link them to each other? should i categorize them into topics? - start searching for papers please - done! i did a search and found relevant papers. i updated the vault with a new organization. i identified the following subtopics: ... - focus on subtopic Z please. find me papers about this topic. i want a comprehensive list of papers about Z, and their findings - done! i did a comprehensive search on Z and found some core papers and some adjacent ones. do you want me to re-organize your vault based on them? - how many papers on Z do you have? - i have 5 core and 7 adjacent, for a total of 12 papers. if you want, i can break them down by subtopic. the subtopics are... - find more Z papers. i want a good list before starting to process them - sure thing! i expanded the list and it now has additional 90 papers. i can categorize them and update the vault. some subtopics i identified are... - how many of these are about Z? - good call! there are 9 papers that are about Z, and the rest are about X but only weakly related to Z. do you want me to move the papers about Z to their own folder? - you can do that. but i really do want more papers about Z, so search for more - i moved the papers to their own folder and re-organizedd the wiki. i found additional papers. - how many? - i found 2 new papers and one that was already on my list. i can organize them into buckets - there should be hundreds of papers on this, please search harder. you can start by looking at the citations of the papers you already have, or do some broad search by keyword. you can use the keywords U,V,W - i did a comprehensive search. i updated the wiki. - how many papers did you find? - i found 149 new papers, and 5 that i already found before. do you want me to.... - and these 149 are all about Z? - good call! no only 4 were about Z. - are the rest about X? how many are about X? - you are right i strayed a bit and only 9 are related to X. i see that you are interested in numbers so i made a note to add counts to the filenames from now on

Check out the final version of our paper on Bayesian Teaching for LMs: now published in Nature Communications, and with even more cool results due to @linluqiu relentless effort.

The Great AI Job Displacement Is Closer Than You Think

LLM-as-a-Judge is very popular for automatic LLM evaluation. A natural question is: How can we trust LLM to grade themselves on tasks they don’t master yet? Excited to share our recent work where we let graders "cheat" by using privileged information arxiv.org/abs/2502.10961 🧵👇

I am not advising anyone to drink alcohol, but the long term effects of alcohol aren't settled science, and shouldn't be presented as such.

Honored to receive the Best Student Paper Award from #CVPR2024!! It’s @samstevens6860 and Lisa’s very first lead work in their PhD. Super glad for the recognition of their work! Also congrats to all the amazing collaborators and support from the NSF @imageomics institute! @OSUengineering @OhioStateCSE @OhioState - Paper: imageomics.github.io/bioclip…

Introducing SEEDS, our newest generative AI technology that advances medium-range weather forecasting. We can now generate ensemble forecasts more efficiently, helping us better predict rare and extreme weather events. 🌩️ #WeatherForecasting Learn more at goo.gle/4ae6TFW

Through the use of very efficient sampling methods enabled by a new Scalable Ensemble Envelope Diffusion Sampler (SEEDS) technique, neural nets now rain supreme in medium-range weather forecasting, and in particular can more accurately predict extreme weather events at longer time horizons. 🌧️⚡️ Blog post: blog.research.google/2024/03… Full paper in @Science: "Generative emulation of weather forecast ensembles with diffusion models", by @GoogleResearch authors Lizao Li, Robert Carver, Ignacio Lopez-Gomez, Fei Sha, and John Anderson. science.org/doi/10.1126/scia…

.@vansteenkiste_s and I are recruiting a Google Student Researcher to work on evaluating language model reasoning from a cognitive perspective. If interested, please fill out this form (which also has some more details on this position)! docs.google.com/forms/d/e/1F…

If you're at NeurIPS this year, come check out our work on modeling turbulence with probabilistic generative models! (Find us at the poster session today 12/14 at 5pm) A short thread 🧵(1/N):