ぺりゃ🚗
@peryaudotrain as many neural nets as possible 🚀
Similar User
@semiexp
@namonakiaccount
@Respect2D
@hogeover30
@pepsin_amylase
@hirose_golf
@akensho
@kawatea03
@eomole
@kyuridenamida
@okaduki
@ir5
@shora_kujira16
@Mi_Sawa
@__math
Whoa, this is Temporal Gaussian Hierarchy (TGH). This AI can real-time render long volumetric videos in 1080p at 450 fps on a single RTX 4090 GPU. And 18,000 frames (around 10 minutes) long 🤯 7 wild demos: 1. Real-time demos on MobileStage dataset
🚀 Introducing the Byte Latent Transformer (BLT) – An LLM architecture that scales better than Llama 3 using byte-patches instead of tokens 🤯 Paper 📄 dl.fbaipublicfiles.com/blt/BLT__Patch… Code 🛠️ github.com/facebookresear…
Waymo's market share is now equal to Lyft within SF. Incredible. Network effects is one of the best sources of defensibility. But it's proven to be not that important in ridesharing. You need a minimum network size, but once you have that, there are diminishing returns. In…
In case it was unclear before, it is clear now: GM are a bunch of dummies.
A new tutorial on RL by Kevin Patrick Murphy, a Research Scientist at Google DeepMind who also wrote several comprehensive, well-regarded textbooks on ML/DL. This ought to be a good read 👀
The inventors of flow matching have released a comprehensive guide going over the math & code of flow matching! Also covers variants like non-Euclidean & discrete flow matching. A PyTorch library is also released with this guide! This looks like a very good read! 🔥
I am happy to announce that the first draft of my RL tutorial is now available. arxiv.org/abs/2412.05265
何この人… →留学時代に旅行した南アのソウェト。薄暗い時間帯に十数人の青年に囲まれました。うち数人はナイフを持っている。少林寺拳法の演武を、大声を発しながらやったら相手がひるんだ。全力疾走で20分間くらい走って逃げて命拾いしました アジア開銀総裁 神田真人 nikkei.com/article/DGKKZO…
OpenAI has added support for RLHF finetuning of their models!
Welcome PaliGemma 2! 🤗 Google released PaliGemma 2, best vision language model family that comes in various sizes: 3B, 10B, 28B, based on Gemma 2 and SigLIP, comes with transformers support day-0 🎁 Saying this model is amazing would be an understatement, keep reading ✨
Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image. 🖼️ These types of large-scale foundation world models could enable future agents to be trained and evaluated in an endless number of virtual environments. →…
Introducing 🛹 RollingDepth 🛹 — a universal monocular depth estimator for arbitrarily long videos! Our paper, “Video Depth without Video Models,” delivers exactly that, setting new standards in temporal consistency. Check out more details in the thread 🧵
United States Trends
- 1. Terry 26,3 B posts
- 2. Browns 20 B posts
- 3. Amad 189 B posts
- 4. Sam Hubbard 1.472 posts
- 5. Manchester 290 B posts
- 6. Lamar 23,7 B posts
- 7. Mac Jones 1.859 posts
- 8. #RaiseHail 6.288 posts
- 9. Myles Garrett 1.095 posts
- 10. T'Vondre Sweat 2.225 posts
- 11. $CUTO 13,1 B posts
- 12. #ChiefsKingdom 3.705 posts
- 13. Titans 18,3 B posts
- 14. Jayden Daniels 4.996 posts
- 15. Gmail 18,2 B posts
- 16. #MUFC 97,7 B posts
- 17. #RavensFlock 2.058 posts
- 18. Bateman 8.609 posts
- 19. #MCIMUN 102 B posts
- 20. Poyer N/A
Something went wrong.
Something went wrong.