Lately I’ve been asking myself: what might artificial intelligence be good for besides answering questions and writing code? My answer is the latent spaces within AIs themselves will become a new medium for creativity. https://t.co/qsxBMmK4En
I wanted to share something I built over the last few weeks: https://t.co/QRqMK9CpTR is a massive isometric pixel art map of NYC, built with nano banana and coding agents.
I didn't write a single line of code.
Banana Canvas ✏️⬜️ Experimenting with interacting with a model entirely through pixels. Made w/ Nano Banana Pro + Gemini 3 in @GoogleAIStudio 5x video screencap ⏩ Link + code in thread 🧵
Hangzhou is insane. Just look at what these kids do. They casually made a fleet of trash-catching trash cans for a 3 minute video. 232 likes as of now. And all their stuff is like this.
What makes such interfaces not survive mass market adoption? All of them get inevitably normalized. Gestures replaced with popup menu actions, sidebars, toolbars, breadcrumbs and other "user friendliness". Why can't we have Pro interfaces that require learning?
🚀 Struggling with the lack of high-quality data for AI-driven human-object interaction research? We've got you covered! Introducing HUMOTO, a groundbreaking 4D dataset for human-object interaction, developed with a combination of wearable motion capture, SOTA 6D pose estimation vision models, LLM, and the professional refining works of multiple animation studios.
HUMOTO features:
✅ Over 700 diverse daily activities
✅ Interactions with 60+ objects, 70+ articulated parts.
✅ Fine-grained text annotations
✅ Detailed hand and finger movements
We hope HUMOTO will fuel your Humanoid AI research and drive new advancements!
For research or commercial license inquiries, please contact [email protected].
Explore the dataset: 👉 HUMOTO Dataset Website https://t.co/ybzdvvQoSr
Learn more: 👉 HUMOTO Project Page https://t.co/VwppPErlub
@jacinth_lu@qixing_huang
#AI #HumanObjectInteraction #HumanoidAI #MotionCapture #HUMOTO #AdobeResearch
Black Mirror vibes, working for real 😉
Quick & dirty prototype that turns photos into walkable 3D worlds.
Exploring how to bring vintage photos to life in Mixed Reality using Monocular 3D Estimation
Walk inside photos using a Quest 3 demo:
👉 https://t.co/VqAV4bxH2w
playing with turning photos into receipts on https://t.co/CZOy7Fx9ll
ceramic mug $4.50
tablecloth $6.50
student loan debt $164.282.00
someone please help me budget this my family is dying