Patrick Poirson

Computer Vision/Machine Learning. PhD student at UNC Chapel Hill

[Georgia Gkioxari @georgiagkioxari]

Congratulations to Kaiming and ResNet. ResNet is 10 years old but Kaiming remains as young and brilliant as ever! We are deeply grateful for you and for everything you have done for computer vision, Kaiming (though he refuses to be on social media)

[Patrick Poirson @patrickpoirson]

@giffmana @JohnBallsase @MTSlive FAIR was so good at vision back then. Also Microsoft always fumbles. Both were briefly at MSR and MSRA

[China Research Collective @CRC_8341]

Interview w/ The Smartest Kid in the World: Deng Mingyang (邓明扬)

2nd year PhD student in MIT under He Kaiming (何恺明)

ICPC Gold medal 🥇 (1st place)

Putnam Fellow (Top 5)

IOI Gold Medal🥇 (1st place)

IMO Gold Medal🥇

Translated interview here: https://t.co/zKF3O826Lz

[The White House @WhiteHouse]

Power to the Players

[Patrick Poirson @patrickpoirson]

@jcjohnss @drfeifei @karpathy @cs231n Those were the good ole days! The lectures, assignments, and notes were amazing. Thank you all for putting together and freely sharing such a wonderful course. It had a big impact on my life.

[Kwot Sin @kwotsin]

very intelligent 😀

[Patrick Poirson @patrickpoirson]

@giffmana @generatorman_ai Feel like I used to be pretty good at this but it's more challenging now that author lists are much longer.

Jifeng Dai, Liang-Chieh Chen, Han Hu are a few names that would grab my attention

[Patrick Poirson @patrickpoirson]

@_jasonwei Kaiming He

[Patrick Poirson @patrickpoirson]

@xichen_pan @sainingxie @j1h0u @ImSNShukla @felixudr @iam_aashusingh @zhuokaiz @shlokkkk @zhiyangx11 @JiuhaiC Really great work, thanks for sharing!

FYI: looks like there is a typo "we employ Qwen2.5-VL
3B (Bai et al., 2025) to generate instructions" vs Appendix "For the data curation part, we use Qwen/Qwen2-VL-7B-Instruct"

Which one is correct?

[Patrick Poirson @patrickpoirson]

@giffmana @y0b1byte Maybe this? https://t.co/kARuYKgwuH

[Patrick Poirson @patrickpoirson]

@LxthuL 😻 great job fellas. So close

[Patrick Poirson @patrickpoirson]

@CSProfKGD https://t.co/Q58mWpVfVk

[Serge Belongie @SergeBelongie]

Incredible example of AR+AI. Small field of view, but still very inspiring. Congratulations on this milestone @Snap

[Xiaolong Wang @xiaolonw]

Is tracking task necessary for learning to track? Our new work on self-supervised correspondence learning shows it is not! By simply comparing two video frames, without negative pairs, the correspondence can emerge for tracking objects and pixels.

https://t.co/fmgCAiqWq4
(1/n)

[Mohit Bansal @mohitban47]

Congrats Jie @jayleicn on being awarded the @AdobeResearch Fellowship!! 🥳 🎉 #ProudAdvisor

PS. Jie works on diverse aspects of vision+language research (esp. videos) & will be on the job market next year 🙂

(cc tlberg; @uncnlp)

https://t.co/sdG5cXcY76

https://t.co/Gklry77COs

[Kosta Derpanis (sabbatical in Zurich) @CSProfKGD]

"Snap looks to enhance augmented reality features with acquisition of British research lab Ariel AI"

For those not familiar with Ariel #AI, the startup includes Iasonas Kokkinos, George Papandreou, and Stefanos Zafeiriou 🇬🇷

https://t.co/LMf8oRH0xM

https://t.co/MZ9wbpRL2P

[Patrick Poirson @patrickpoirson]

@abursuc Very important papers for distilling what is actually important for a problem. My least favorite papers propose a "new task" (not actually new) with weak baselines.

[Xiaolong Wang @xiaolonw]

How to train very deep ConvNets without residual blocks? Our ICML paper on Deep Isometric Learning successfully trains 100-layer ConvNets without any shortcut connections nor normalization layers (BN/GN) on ImageNet.

Paper: https://t.co/mxMJO1Wub9
Code: https://t.co/8Omd8SYYS9

[Patrick Poirson @patrickpoirson]

@sunniesuhyoung For vision I would recommend Computer Vision: Models, Learning, and Inference (Free) and An Invitation to 3D Vision

[Jared Heinly @JaredHeinly]

At @EveryPointIO we recently developed a real-time 3D reconstruction method that runs on an iPhone. At first we're measuring stockpiles to provide instant answers to @stockpilereport customers. Excited to explore other applications that can benefit from real-time 3D insights!