Abhishek Yadav

@avis0r

136 Following

102 Followers

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

ted (not lasso) pfp

ted (not lasso)

"bizarre that people started buying more cologne when they stopped seeing other people in person."

11 replies

0 recast

50 reactions

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

🌐 Crypto Market Highlights 🌐 🔹 Market Cap: $3.42T, down 0.42%. Trading volume up 3.74%. 🚀 Top Gainers: Neon EVM, Jasmy, Alchemy Pay. 💰 Bitcoin: Market cap $2.08T, volume up 43.44%. 🔗 Ethereum: Valued at $394.22B, volume up 36.18%. 📰 Key Developments: FDIC revising crypto guidelines. Grayscale seeks Litecoin ETF conversion. New Mexico proposes Bitcoin reserve bill. BlackRock plans Bitcoin ETP in Europe. 🤔 Sentiment: Mixed on X, with optimism around ETF applications and new chains. Stay updated! 📈🔍 #CryptoNews #Bitcoin #Ethereum

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

Abhishek Yadav pfp

0 reply

0 recast

0 reaction

𝚐𝔪𝟾𝚡𝚡𝟾 pfp

𝚐𝔪𝟾𝚡𝚡𝟾

FAST is a robot action tokenizer that simplifies and speeds up robot training. It enables: > 5x faster training compared to diffusion models. > Compatibility with all tested robot datasets. > Zero-shot performance in new environments, including the DROID dataset, successfully controlling robots in various settings with ease. > Simple autoregressive VLAs that match diffusion VLA performance. > Mixed-data VLA training, allowing integration of non-robot data like web data, subgoals, and video prediction. FAST compresses actions using discrete cosine transform, reducing redundancy and enabling efficient VLA training on high-frequency tasks. It scales to complex robot tasks with simple next-token prediction, converging in days instead of weeks. A pre-trained FAST tokenizer based on 1M robot action sequences is available on Hugging Face, working across various robots and supporting mixed-data VLA training. https://huggingface.co/physical-intelligence/fast

0 reply

4 recasts

16 reactions

Abhishek Yadav pfp

0 reply

0 recast

0 reaction