Yunzhi Lin

MLE @tiktok_us, Ph.D. @GeorgiaTech

[Yunzhi Lin @lyz14115]

@Kay2289123 感觉和搜广推的模型开发流程也很像？

[Chris Paxton @chris_j_paxton]

I am in the "scaling won't work yet" camp, but there are concrete things we can do to change that. Nice article + summary

[Jingfeng Yang @JingfengY]

These days many NLP researchers worry about future research directions after GPT4 comes out. These are my suggestions, which have been shared in several of my talks last month. Full slides: https://t.co/gh9vsfcHqE . Many points are similar to what @_jasonwei suggested.

[Soumith Chintala @soumithchintala]

The temporal consistency is crazy good.
Finally, vid2vid that is production-quality!

[Yunzhi Lin @lyz14115]

@wgussml Great idea. Just had a try and it was amazing.

[william @wgussml]

It's here!!🎉🚀🎉

Say hello to GhostWrite - Your ChatGPT powered AI email assistant 👻

GhostWrite automates your inbox w/ AI replies, email, and summaries. Write emails 20x faster & get to inbox 0️⃣ w/ GW!

🔗https://t.co/cAA02SiaCz

Retweet & comment below for unlimited access!

[Yunzhi Lin @lyz14115]

@yifengzhu_ut Cool. I am using the same coffee machine 😂

[Shane Gu @shaneguML]

Real2sim and neural-amortized simulators will revolutionize anything real (e.g. movie, realistic 3D games, robotics)

[Manuel Sainsily @ManuVision]

I finally got access to the @LumaLabsAI beta! A brand new iOS mobile app and web experience to capture and share #NeRFs (#NeuralRadianceFields).

I made a video breakdown of the process so you can discover the user-friendly interface!

View my #NeRF here:
https://t.co/5QUy8E7tbN

[Yunzhi Lin @lyz14115]

@njtangchao96 @2022Iros Awesome. Big congrats!

[Yunzhi Lin @lyz14115]

Great to be featured in @GTrobotics. Thanks to all my collaborators who make this possible. Can't wait to see my friends in Philadelphia this May.

[Robotics@GT @GTrobotics]

.@GeorgiaTech_ECE | Prof. Vela & the Intelligent #Vision & #Automation Team Presenting @ieee_ras_icra May 24th "Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image" in #Perception 4 #Robotics Grasping & Manipulation I
https://t.co/fqT153ddlt

[AK @_akhaliq]

Block-NeRF: Scalable Large Scene Neural View Synthesis
abs: https://t.co/xDa1bmJaCJ
project page: https://t.co/IQTnknxTuK

[Chip Huyen @chipro]

Takeaway from @karpathy's CVPR talk:

The most successful ML projects in prod (Tesla, iPhone, Amazon drones, Zipline) are where you own the entire stack.

They iterate not just ML algorithms but also:
- how to collect/label data
- infrastructure
- hardware ML models run on

[Fu-Jen Chu @FuJenChu1]

Awesome! Thanks #arXiv_Daily for selecting our GKNet paper to be today's recommendation!

Download our dataset today!: https://t.co/nLSoEhtR4j
First attempt to train our robot!: https://t.co/H8qzM0Y1FX

[Jia-Bin Huang @jbhuang0604]

Sharing tips on preparing your presentation slides

Just attend many thesis presentations and qual exams at the end of the semester. I compiled some common pitfalls here and hopefully would be helpful to some.

Check out the thread 🧵below!

[Jia-Bin Huang @jbhuang0604]

Sharing ideas on how to disseminate your research.

"I am THRILLED to share that our paper is accepted to ..."

Congrats! So what's next? No one is going to browse through the list of thousands of accepted papers. Ain't nobody got time for that.

Check out 🧵below for examples.

[AK @_akhaliq]

ShaRF: Shape-conditioned Radiance Fields from a Single View
pdf: https://t.co/IHYBOSXNn1
abs: https://t.co/TzHHoHRhUs
project page: https://t.co/VXqCcUg5J3

[Matthias Niessner @MattNiessner]

We made a website of our TUM AI Lecture series:
https://t.co/YGzuE2Buah

- Videos of all previous speakers online!
- Schedule with upcoming speakers!

Talks are always streamed live on Friday's (see links above) - 9am PST / 6pm CET.

Really cool talks - must watch -:)

[Ken Goldberg @Ken_Goldberg]

A high-quality dataset of 696 common household objects that @GoogleResearch 3D-scanned is now available under @creativecommons license for researchers in robot simulation and perception: https://t.co/TMTOvdAmCm

[Daniel Duckworth @duck]

Our paper, “NeRF in the Wild”, is out! NeRF-W is a method for reconstructing 3D scenes from internet photography. We apply it to the kinds of photos you might take on vacation: tourists, poor lighting, filters, and all. https://t.co/lawLB4eEup (1/n)