charig yang

Research Scientist @isomorphiclabs (prev: @meta, @oxford_vgg) 🇹🇭

[charig yang @chaaarig]

!!!!

[#CVPR2026 @CVPR]

Announcing the official #CVPR2026 Best Paper Award Winner! 🏆 Congratulations to the authors for their landmark contributions to the field!👏👏

[charig yang @chaaarig]

I'll be in Rio 🇧🇷 if you are interested to chat!

[Isomorphic Labs @IsomorphicLabs]

Heading to @ICLR? If you're interested in building frontier AI to tackle some of the biggest challenges in science, talk to us about our open ML Engineer, ML Research Engineer and ML Research Scientist roles.

Our hiring managers will be in Rio from 23-27 April. Register in the comments to meet them for a 1:1 chat.
@chaaarig, @mgarort_, @aosokin_ml, @rampasek, @amyxlu, @barthelemymp

[Max Jaderberg @maxjaderberg]

The Iso team has cooked something incredible: our new technical report unveils the latest results from our drug design engine, the IsoDDE, progressing far beyond AlphaFold 3. This breaks new ground compared to AF and other similar methods by a significant degree across all key benchmarks. 1/7

[charig yang @chaaarig]

I'm in San Diego for #NeurIPS! I'll be around to chat anything @IsomorphicLabs, at Google booth [Thursday 15:45], and will be presenting a paper from my past life with @meta_aria on reading with smart glasses [Poster on Friday 16:30]. See you around!

https://t.co/Mu0cxpZN9c

[AI at Meta @AIatMeta]

Reading Recognition in the Wild: A Dataset for Understanding Human Behaviors During Reading from an Egocentric Sensor Suite

This large multimodal dataset features video, eye gaze, and head pose sensor outputs, created to help solve the task of reading recognition from wearable devices. Notably, this is the first egocentric dataset to feature high-frequency eye-tracking data collected at 60 Hz.

Explore ➡️ https://t.co/TK8BPu4yjk

[Visual Geometry Group (VGG) @Oxford_VGG]

Many Congratulations to @jianyuan_wang, @MinghaoChen23, @n_karaev, Andrea Vedaldi, Christian Rupprecht and @davnov134 for winning the Best Paper Award @CVPR for "VGGT: Visual Geometry Grounded Transformer" 🥇🎉 🙌🙌 #CVPR2025!!!!!!

[charig yang @chaaarig]

@giffmana @kirillov_a_n @polynoamial thanks for still remembering this after all these times! i had so much fun working on it

[charig yang @chaaarig]

@ftm_guney @WeidiXie thank you for the kind words!

[charig yang @chaaarig]

Excited to be in Milan for #ECCV2024 to present our Oral paper tomorrow!

Made to Order: Discovering monotonic temporal changes via self-supervised video ordering.

with @WeidiXie and Andrew Zisserman.

[charig yang @chaaarig]

@WeidiXie [Paper] https://t.co/EdoXWpXwbC
[Project Page] https://t.co/R0k4jQ0IsM

[charig yang @chaaarig]

@WeidiXie We show examples on many domains, both object and environmental changes: natural videos, camouflages, satellite images, longitudinal medical images.

[Oral] 6B - Video Understanding (Thursday 13:50, Auditorium)
[Poster] 6 (Thursday PM), Poster 117 (right by the escalator!)

[Dreaming Tulpa 🥓👑 @dreamingtulpa]

SAM + Optical Flow = FlowSAM

FlowSAM can discover and segment moving objects in a video and outperforms all previous approaches by a considerable margin in both single and multi-object benchmarks 🔥

https://t.co/qjaMQOYtlN

[Lucas Beyer (bl16) @giffmana]

This quote from @demishassabis is my favourite take on the "engineering vs science" debates in AI yet:

AI is an engineering science: unlike in natural sciences, the phenomenon you're studying doesn't exist in nature, so you have to build it first, and then you can study.

[charig yang @chaaarig]

no lights, because attention is all you need @ transformers for vision workshop #cvpr2022 (jokes aside, great talks!)

[charig yang @chaaarig]

@abidlabs @Gradio @huggingface thanks for the suggestions :) just did ⏰

[charig yang @chaaarig]

In a week's time I will be attending #CVPR2022 in person to present our timely project on telling the time **without** manual annotations. Hope to see people this time!

It's About Time: Analog Clock Reading in the Wild

w/ @WeidiXie and Andrew Zisserman

https://t.co/38y644Mk49

[Autonomous Intelligent Machines & Systems @Oxford @aims_oxford]

Congratulations to @chaaarig who won best presentation and @jacksonmattt @shreshthmalik for best poster at the Joint CDT student conference with Bristol, Lincoln and Edinburgh CDTs @aims_oxford @UniofOxford

[AK @_akhaliq]

Temporal Alignment Networks for Long-term Video
abs: https://t.co/8VRuU21Lgg