Trajectory forecasting using Ultralytics YOLO26 + MovingPandas 😍 Predicting motion isn’t just about tracking; it’s about estimating velocity and projecting future positions based on trajectory patterns. Here, I combined YOLO26 with movingpandas to build a forecasting

2026，知识工作，危。 --- 龙虾 agent 干活是真卖力啊，别说比一般员工好使，我自己也望尘莫及。 在 notion 里面建了一个视频库，里面是最近五六年来和娃一起看过的、筛选过的近 2000 个知识视频。 按照目前的进度，龙虾一天就能全部处理完。

Many tried, most failed. But this is the first skin enhancer I've used that actually makes characters look real. Meet Vellum from OpenArt It's now a staple in my workflow. I won't start a project without it:

次世代の4D表現 やっと出来るようになった 4次元 ＋ 実写 ＋ CG ＋ AI の技術を融合させました💪

it's time to drop three new #opensource robotic hands! this time with tactile sensors! Tweak it, 3D print it, and use them in your robotics and physical AI research! Here are some wild examples ↓↓↓

Not into Hollywood. Not into Netflix. But this? This got me hooked. 🎞️ 南天门计划 (Project Nantianmen) Part 1. China's aerospace strategy... visualized by AI for the world to see. ✨🚀 And it's speaking Mandarin. 🇨🇳 🎙️softmangavibes

终于！3月22日凌晨微信官方下场做clawedbot！ 安装方法如下： 1、确认电脑和手机的微信版本是最新版本，手机端是iOS 8.0.70 2、打开电脑，mac打开终端，输入npx -y atencent-weixin/openclaw-weixin-cli@latest install 3、执行后，电脑会自动检测你本地的 OpenClaw Peter Steinberger 🦞

NVIDIA's Kimodo is the release of the week 🔥 Prompt the timeline whatever your want like: "a person walks forward" → "a person starts jumping", hit Generate, and watch a 3D character do it in seconds (700hrs of pro mocap training. Works on human + robot skeletons. Super fast

A Monday morning question for you: Challenge yourself to do something out of your normal routine. What is one thing you can do this week that is different than what you do on a normal week?

Uni-1 is here! A new kind of model that thinks and generates pixels simultaneously. Less artificial. More intelligent.

Today Mirror Mirror AI is launching the marketplace where fashion models license their likeness and brands get stunning AI-generated imagery featuring real people. Commercially licensed, model-approved. Try our platform: mirrormirrorai.com As a fashion model I used to

Mecka is excited to power EgoVerse: a growing ecosystem for robot learning from egocentric human data Proven across 4 leading research labs, EgoVerse data consistently boosts robot performance We release the tools for anyone to collect data, inference/train, and contribute! 🧵

Extremely proud of the team Luma🔥❤️🎊 Having so much fun playing with Uni-1 and seeing so many cool results internally. The model can do so many things and is REALLY SO GOOD. Also Uni-1 is the first model that actually makes my face right😜 (instead of turning it into

Today, we’re releasing a feature that allows Claude to control your computer: Mouse, keyboard, and screen, giving it the ability to use any app. I believe this is especially useful if used with Dispatch, which allows you to remotely control Claude on your computer while you’re

Seedance 2.0 のOmni referenceを使っております １発で狙った生成をしてくれました😲

The Noodle Master 🎬 Seedance 2.0 Prompt shared below

Using Uni-1 by Luma to create consistent and correct PBR/Normal/Displacement map, combining with triplanar/image projections to boost asset creation speed while maintaining quality. Made by: Tony Hou

My latest computer vision project - Tennis🎾 Featuring: -Player, ball, racquet detection -Player poses -Exclusion zones to kill false positives -Interpolation and smoothing for clean ball trails All running at over 30FPS!

Humans can see in high-res, high-FPS in real-time. Why can't VLMs? Introducing AutoGaze: ViTs/VLMs "gaze" only at key video regions! Up to 4-100x token savings, 19x speedup, and enables scaling to 4K-res 1K-frame videos. 📄 arxiv.org/abs/2603.12254 🌐 autogaze.github.io 🤗

In Chinese, AI is Love.