RT Seongsik Kim: Re 2. (Real time fact checking) - The Interaction Models hear you speak and fact-checks you in real time — like having a teammate wh...
I’ve been telling people this a lot today: I enjoy so much working with people who care about what they are building and craftsmanship. It is a privi...
On-policy distillation provides an elegant way to use the teacher model as a process reward model to provide dense reward while preventing SFT style "...
GPUs are expensive and setting up the infrastructure to make GPUs work for you properly is complex, making experimentation on cutting-edge models chal...
Looking through those little hidden gem stories in the footnote, you will find it so inspiring that researchers with interests on the same topic are a...
RT Alexander Kirillov: We have been working hard for the past 6 months on what I believe is the most ambitious multimodal AI program in the world. It ...
I still find it mysterious whether and how intelligence and capabilities transfer between domains and skills - from meta learning during early days to...
Probably the first product Thinky will build is a full panel of dials that researchers can use to physically adjust all the hparams during training. W...
Giving your models more time to think before prediction, like via smart decoding, chain-of-thoughts reasoning, latent thoughts, etc, turns out to be q...
When a new dataset comes out, I get excited and check it out and then only realize that this is another meta-mixed dataset combining a collections of ...