1️⃣Byte Latent Transformer: Patches Scale Better Than Tokens
what: train llama on raw bytes without a fixed vocabulary. - dynamically patches bytes usign local small encoder - main decoder process these patch in AR setting - local deocder makes next byte prediction. paper:https://arxiv.org/abs/2412.09871
2️⃣Large Concept Models: Language Modeling in a Sentence Representation Space
what: work with entire sentences as "concepts" through SONAR embeddings. - quite similar with the first paper here, but it merges tokens into high dim embeddings - working with sentence-level embeddings directly.
3️⃣GenCast predicts weather and the risks of extreme conditions with state-of-the-art accuracy
what: Created a diffusion model for probabilistic weather forecasting that generates 15-day predictions with 12-hour steps how: - It aggregates two previous timesteps to predict the next weather state - Instead of directly sampling weather state, it generates residuals (differences) relative to the previous state. - Артемий в канале AI для Всех сделал ревью на русском, почитайте.
my thoughts: Looks like we're finally getting closer to how humans actually process language, not just crunching tokens like robots. Whether it's patching bytes or bundling tokens into sentence embeddings, this hierarchical approach seems to be the way forward. GenCast - is just super interesting adoption of modern AI to real problems in natural science.
1️⃣Byte Latent Transformer: Patches Scale Better Than Tokens
what: train llama on raw bytes without a fixed vocabulary. - dynamically patches bytes usign local small encoder - main decoder process these patch in AR setting - local deocder makes next byte prediction. paper:https://arxiv.org/abs/2412.09871
2️⃣Large Concept Models: Language Modeling in a Sentence Representation Space
what: work with entire sentences as "concepts" through SONAR embeddings. - quite similar with the first paper here, but it merges tokens into high dim embeddings - working with sentence-level embeddings directly.
3️⃣GenCast predicts weather and the risks of extreme conditions with state-of-the-art accuracy
what: Created a diffusion model for probabilistic weather forecasting that generates 15-day predictions with 12-hour steps how: - It aggregates two previous timesteps to predict the next weather state - Instead of directly sampling weather state, it generates residuals (differences) relative to the previous state. - Артемий в канале AI для Всех сделал ревью на русском, почитайте.
my thoughts: Looks like we're finally getting closer to how humans actually process language, not just crunching tokens like robots. Whether it's patching bytes or bundling tokens into sentence embeddings, this hierarchical approach seems to be the way forward. GenCast - is just super interesting adoption of modern AI to real problems in natural science.
BY the last neural cell
Warning: Undefined variable $i in /var/www/group-telegram/post.php on line 260
He floated the idea of restricting the use of Telegram in Ukraine and Russia, a suggestion that was met with fierce opposition from users. Shortly after, Durov backed off the idea. Ukrainian forces have since put up a strong resistance to the Russian troops amid the war that has left hundreds of Ukrainian civilians, including children, dead, according to the United Nations. Ukrainian and international officials have accused Russia of targeting civilian populations with shelling and bombardments. Messages are not fully encrypted by default. That means the company could, in theory, access the content of the messages, or be forced to hand over the data at the request of a government. "We're seeing really dramatic moves, and it's all really tied to Ukraine right now, and in a secondary way, in terms of interest rates," Octavio Marenzi, CEO of Opimas, told Yahoo Finance Live on Thursday. "This war in Ukraine is going to give the Fed the ammunition, the cover that it needs, to not raise interest rates too quickly. And I think Jay Powell is a very tepid sort of inflation fighter and he's not going to do as much as he needs to do to get that under control. And this seems like an excuse to kick the can further down the road still and not do too much too soon." Despite Telegram's origins, its approach to users' security has privacy advocates worried.
from tw
