youming.deng

CS Ph.D. Student @Cornell | a fan of @ChipotleTweets | Previous Visiting @EPFL and @ucmerced | B.Eng. @WHU_1893

[youming.deng @denghilbert]

We present the SOTA feed-forward 3DGS pipeline Selfi, which was accepted by #CVPR2026

Project Page: https://t.co/3T31XcnkpD

[Jihan Yang @jihanyang13]

Camera pose matters for video understanding!

Today's MLLMs excel at recognizing activities, but still struggle with the underlying space and ego/object dynamics in video. We trace this gap to a missing piece: camera pose.

Introducing Cambrian-P: a multimodal LLM natively grounded in camera pose. (1/n)

[Tobias Fischer @TobiasFischer11]

Do 3D reconstruction transformers really need a billion parameters, or are most of those layers just doing the same thing over and over?

Introducing Déjà View: a single transformer block, looped K times, that matches or beats models 8–10× its size with lower compute. 🧵

[youming.deng @denghilbert]

@YichuanM congrats. that's so cool!

[youming.deng @denghilbert]

bunch of bullshit

[Dr. Manabendra Saharia @m_saharia]

Yesterday, I was giving an intro talk to our dept's new PhD students. Technical things aside, my number 1 suggestion has remained the same over the years: Treat your PhD like a job.

- Avoid 1.5h lunch and three tea breaks.
- Avoid gossiping and loitering at work.
- Lab at 9 am and leave at 6 pm. Being productive till 11 pm in the lab is a lie people till themselves when their day starts at 1 PM.

Everything worth doing can be done with high intensity focus during work hours. And having fun in life is the secret to being productive in a marathon.

[Curry Flurry 😈 @BabyFaceDubs]

Oracle crowd was a devils pit man

[Impressions @impression_ists]

Vincent van Gogh, Novels and Rose

[Songyou Peng @songyoupeng]

Yay, finally! Introducing Vision Banana🍌 from @GoogleDeepMind, our unified model that outperforms SoTA specialist models on various vision tasks!

By treating 2D/3D vision tasks as image generation, we unlock a new foundation for CV.

Project page: https://t.co/GQgRi6mWwC

(1/5)

[Gene Chou @gene_ch0u]

Introducing CityRAG!

We wanted video generative models to be grounded in the real world — if I’m in London, I want to look around and actually see Big Ben.

CityRAG generates videos of cities featuring real buildings and roads, with arbitrary weather, people, and cars. 1/N

page: https://t.co/jxMSX5Ik7F
paper: https://t.co/So2V9hyB4D

[youming.deng @denghilbert]

@TongPetersb @sainingxie @ylecun @mengyer @YiMaTweets @LukeZettlemoyer @liuzhuang1234 big congrats, Dr. Tong!!

[Art Guide @ArtGuide_db]

Vincent van Gogh
Sunflowers, 1888

[youming.deng @denghilbert]

Super cool. Self-improving makes model better and better!

[Qianqian Wang @QianqianWang5]

Most multi-view reconstruction models need full supervision. We show they can self-improve without any ground truth labels.

Introducing SelfEvo: Self-Improving 4D Perception via Self-Distillation. Up to +36.5% in video depth, +20.1% in camera estimation, zero annotation.

[Natalie Khalil @natalienkhalil]

Basically

[youming.deng @denghilbert]

@Haotianxue_GT @junyi42 🙌🙌

[youming.deng @denghilbert]

Our paper was selected as an oral presentation in #CVPR2026

[youming.deng @denghilbert]

We present the SOTA feed-forward 3DGS pipeline Selfi, which was accepted by #CVPR2026

Project Page: https://t.co/3T31XcnkpD

[Scott @Havenlust]

Claude Monet

[youming.deng @denghilbert]

@Haozheng_Yu thanks haozheng!

[youming.deng @denghilbert]

@justachetan thx aditya!

[youming.deng @denghilbert]

@CMHungSteven thx!

[L'Art Impressioniste @allontanarsio]

Claude Monet