Ruofei Du

1.9K posts

Ruofei Du banner
Ruofei Du

Ruofei Du

@DuRuofei

Interactive Perception & Graphics Lead/Mgr @Google, inventing novel #interactive #AI in #XR. PhD '18 @umdcs #VR #AR #Graphics #HCI #VisualBlocks #UIST #CHI

San Francisco, CA Katılım Nisan 2011
964 Takip Edilen2.3K Takipçiler
Ruofei Du retweetledi
Jason Mayes
Jason Mayes@jason_mayes·
Introducing VectorSearch.js (star it & I'll continue to work on it) - a #JS lib that allows you to perform semantic search over millions of vectors in ms, & can visualize embeddings too! Runs @Google's popular #EmbeddingGemma model entirely client side! github.com/jasonmayes/Vec…
Jason Mayes tweet media
English
2
11
44
4K
Ruofei Du retweetledi
Jon Barron
Jon Barron@jon_barron·
One of the more interesting and thought provoking research papers I've seen in a while. A system for reading and reimplementing NeRF papers, and it seems to work very well. Pretty easy to extrapolate out from here to what CVPR 2027 papers will look like. seemandhar.github.io/NERFIFY/
Jon Barron tweet media
English
6
56
377
46.3K
mrdoob
mrdoob@mrdoob·
mrdoob tweet media
ZXX
22
1
136
14.3K
Ruofei Du
Ruofei Du@DuRuofei·
Glad that you like it! --- try more creations like "dandelion", "growing vines in your room", and "volleyball game that allow me to catch volleyballs and let the ball collide with environment" :)
🔜 Dallas, TX https://Dwane.in/vCon2026Dallas@lifelongdev

Shouts to @DuRuofei, the XR Blocks and @GeminiApp teams for this XR Gem! With just a prompt, I created a WebXR application of a Coral Reef where if I touch a bubble, it pops! haha Going to try with the Samsung Galaxy XR headset later. More info: developers.googleblog.com/turn-creative-…

English
1
0
4
300
Jiaju Ma
Jiaju Ma@jama1017·
Super excited to see @JeffDean showcase the capabilities of Gemini 3.1 Pro through SVG motion graphics. But as any dev/designer knows, perfect visual generation is rarely one-and-done. It almost always takes endless manual iterations and prompt tweaking to get the result. Check out how we solve this by putting any LLMs/agents inside a verification-based self-improvement loop: mover-dsl.github.io
Jeff Dean@JeffDean

Today, we’re continuing to push the boundaries of AI with our release of Gemini 3.1 Pro. This updated model scores 77.1% on ARC-AGI-2, more than double the reasoning performance of its predecessor, Gemini 3 Pro. Check out the visible improvement in this side-by-side comparison, showing Gemini 3.1 Pro’s crisp animation built with pure code. Read more about today’s 3.1 Pro update: blog.google/innovation-and…

English
3
8
26
2.6K
Ruofei Du retweetledi
Shahram Izadi
Shahram Izadi@izadi_shahram·
What if you could "prompt" your XR app and immerse yourselves in it 🌐✨ While XR development traditionally requires a broad range of skills, Gemini offers a new way to rapidly prototype and explore interactive 3D concepts in real-time. You can now use #Gemini to turn creative ideas into interactive XR experiences on #AndroidXR. See it in action: developers.googleblog.com/turn-creative-… @DuRuofei & Benjamin Hersh
English
3
5
20
571
Ruofei Du retweetledi
Google Research
Google Research@GoogleResearch·
For truly realistic conversational research, we must rethink fully autonomous agent design. DialogLab, our new open-source prototyping framework, uses a human-in-the-loop control strategy to achieve realistic human-AI group simulation, offering a necessary alternative to fully autonomous agents.
English
33
168
1.2K
81.4K
Ruofei Du
Ruofei Du@DuRuofei·
Imagine a future where embodied avatar conversations in #Genie / #StreetView / #Geollery, maybe we'll create a #Westworld? #AI #XR
Google Research@GoogleResearch

For truly realistic conversational research, we must rethink fully autonomous agent design. DialogLab, our new open-source prototyping framework, uses a human-in-the-loop control strategy to achieve realistic human-AI group simulation, offering a necessary alternative to fully autonomous agents.

English
0
1
6
549
Ruofei Du retweetledi
Google Research
Google Research@GoogleResearch·
Evaluations with domain experts found that its "Human Control" mode (where you can edit, accept, or dismiss real-time AI suggestions) was preferred in realism, effectiveness, & engagement. DialogLab transforms dialogue design from rigid scripts to spontaneous, adaptable group dynamics. More: goo.gle/4al5xdB
English
1
10
74
6.8K
Ruofei Du
Ruofei Du@DuRuofei·
Check out #DialogLab -- our open-source UIST 2025 invention to author, test, and verify human-AI conversations for all: designers, researchers, practicing interview skills :) #Agent #XR #AI
Google Research@GoogleResearch

For truly realistic conversational research, we must rethink fully autonomous agent design. DialogLab, our new open-source prototyping framework, uses a human-in-the-loop control strategy to achieve realistic human-AI group simulation, offering a necessary alternative to fully autonomous agents.

English
0
1
7
558
Ruofei Du retweetledi
AK
AK@_akhaliq·
MoCapAnything Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos
English
6
110
822
36.6K

Keşfet

@Google @_seanliu @twi_mar @mrdoob @akirodic @makio64 @HerveStudio @JulieMarting