@cadytxu
Account based inUnited States!
About this account
- Account based in
- United States
- Connected via
- United States App Store
X says this location may be affected by a proxy or VPN.
Account-level information from X, not a live location or the device used for a specific post.
we built a tiny society of AI agents using the antigravity sdk🛸 they talk, they mingle, they have no idea they're being watched... (and yes that's me 😅)
Cady Xu retweeted
ML optimizes via mathematical gradients; Loop Engineering needs textual "gradients"!
Introducing ToolGrad: an agentic framework that continuously generates, evaluates, and refines tool-use trajectories with textual “gradients”. #ACL2026
🧵👉 zhongyi-zhou.github.io/toolg…
Cady Xu retweeted
How can we accurately evaluate whether an AI model has generated a genuinely novel concept?
Is there a widely accepted benchmark for measuring machine creativity or invention?
Cady Xu retweeted
Today at Google I/O, we introduced Gemini 3.5 Flash! It has become an integral part of our daily research cycle and works with all the tools we have at Google.
We used a team of agents in Antigravity 2.0 to recreate the original AlphaZero research paper and build a playable version. They coded the reinforcement learning pipeline in JAX/Flax, trained a ResNet model from scratch via self-play on multi-TPU pods, and shipped a full-stack web app so you can play against it, from just 2 prompts. .
Here’s what else makes 3.5 Flash special 🧵
📊 The impact: In our evaluation, users saw a 36.2% boost in objective listening comprehension and a significantly reduced cognitive load in adversarial acoustic environments.
📄 Read the paper: arxiv.org/abs/2603.10465
Excited to share our #CHI2026 paper: MoXaRt: Audio-Visual Object-Guided Sound Interaction for XR! 🎛️
Can visual context help us interact with sound in noisy #XR environments? We built a system that uses visual anchors (like faces or instruments) to separate overlapping sounds in real time. 👇
🔗 cadyxu.com/projects/moxart/
Bringing AI off the screen and into the real world. 🚀 Catch my talk on Agentic AI & Wearable Systems tomorrow at 1:45 PM (Track C2) at the Silicon Valley WiE Conference! See you there 👋 #svwie #ai #agentic #WomenInTech 👇
The 2026 Silicon Valley Women in Engineering Conference is this weekend on March 21! Are you ready to explore with us? Our theme this year is Engineering Beyond Imagination!
Check out updated info at 2026.siliconvalleywie.org/
#svwie #svwie2026 #exploreengineering #networking
Cady Xu retweeted
🚨BREAKING: Google just dropped a new tool for generating academic illustrations for AI Scientists
It's called PaperBanana.
Here's what it does (49 page PDF):
Cady Xu retweeted
Join our fun workshop at CHI ‘26 in Barcelona. We will discuss and ideate on new ideas on wearables for personalized health and well-being. See the CfP poster.
ALT The poster of the CHI ‘26 workshop entitled “Everyday Wearable for Personalized Health and Well-being”
check this out,, amazing work from google xr!
Check out #XRBlocks on xrblocks.github.io/ and try live demos of amazing #WebAI + #WebXR experiences! Have a novel #XR + #AI use case? Contribute to github.com/google/xrblocks and get highlighted!!