开启时会模糊预览图，关闭后正常显示
it's crazy how fast this industry moves feels like YEARS since I was using cursor exclusively, but for the first part of 2025 i was crushing it (still love you, cursor)
TLDR; I make software with AI and talk about it. Serial internet biz builder with multiple 6 & 7 figure exits. Always learning.
If you want the full deep dive (with visuals + demo + and fine-tuning instructions), watch my new video: https://t.co/TDdhedJiDn
Data Science Director at Agoda | Ex-TOP-20 on Kaggle | Playing with robots for fun
Another problem during the inference is non-smooth motion because of the chunking. Model predicts the next chunk, executes it, and then pauses to predict the next one (video below, x3 speed). If you try to predict a chunk before the previous one is executed, it can lead to fatal mistakes if the model jumps to a new action mode while executing a very different one. The solution is inpainting - that is often used in image generation. We can predict the next chunk while the old one is being executed, but we force this new prediction to match the end of the previous chunk exactly. The result is a much smoother motion without jumps and pauses, and higher performance and throughput of the model.
If you want the full deep dive (with visuals + demo + and fine-tuning instructions), watch my new video: https://t.co/TDdhedJiDn
Pi0.5 by @physical_int is one of the best open-source end-to-end robotics policies right now 🤖 It’s an upgraded version of Pi0. And the most recent PI advancements are built on top of it. Let's discuss how it works:
What changed vs Pi0? - FAST tokenization - there was an optional FAST version on Pi0, but for Pi0.5, it is an essential part of the training - System 2 - following the Hi Robot paper, Pi 0.5 is using its VLM part as a reasoning high-level system 2 to reason and plan complex tasks - Better training recipe and a couple of smaller tweaks.
Sure, money doesn’t buy happiness, but it does solve a lot of annoying problems. It’s like the wise saying: “Better to be rich than poor.”
I build stuff. On my way to making $1M 💰 My projects 👇
刚刚刷到藏师傅的推，突然发现⋯ ListenHub 荣登 2025年知乎年度 AI 产品榜单。 没想到获奖也没人通知一下的😂 感谢知乎和答主朋友们的厚爱。 元旦有个惊喜礼物送给大家。
完整榜单在这里 https://t.co/K2iUBftFtO
