Another good example from mono depth: DepthAnythingV2 uses a teacher supervised only on synthetic data (600k) and students are distilled from its predictions on web images (62M).
Real-world GT is noisy, so fitting to limited, but perfect synthetic data is better for teacher accuracy.
16.07.2025 21:57 — 👍 1 🔁 0 💬 0 📌 0
Threw it at o3 and after thinking for 12 min (!!) it gave “O Canada” and A major. You can take a look at the full chain of thought here (chatgpt.com/share/6871b3...). Some highlights:
12.07.2025 01:03 — 👍 4 🔁 0 💬 0 📌 0
Maybe I'm not familiar enough with tokenizers, but is this different than just using a very small bottleneck dimensionality in SiamMAE? There seems to be something special about using precisely one token (specifically the [CLS] token?), but it's not immediately obvious why.
10.07.2025 18:36 — 👍 0 🔁 0 💬 0 📌 0
PhD Student at Cornell. Working in Vision and Graphics. justachetan.github.io
Research Assistant @ Princeton Computational Imaging Lab exploring Inverse Generation for Perception | Princeton CS '24 | https://tanushreebanerjee.github.io/
(she/her)
Google Chief Scientist, Gemini Lead. Opinions stated here are my own, not those of Google. Gemini, TensorFlow, MapReduce, Bigtable, Spanner, ML things, ...
AI professor at Caltech. General Chair ICLR 2025.
http://www.yisongyue.com
https://Answer.AI & https://fast.ai founding CEO; previous: hon professor @ UQ; leader of masks4all; founding CEO Enlitic; founding president Kaggle; various other stuff…
Professor at Columbia. Computer Vision and Machine Learning
www.dgp.toronto.edu/~hertzman
Research Scientist Meta/FAIR, Prof. University of Geneva, co-founder Neural Concept SA. I like reality.
https://fleuret.org
Interpretable Deep Networks. http://baulab.info/ @davidbau
Robotics/Perception Prof at Georgia Tech; Chief AI Officer at Verdant Robotics. Stints at Skydio, B*8, Reality Labs, Google Research. https://dellaert.github.io
DeepMind Professor of AI @Oxford
Scientific Director @Aithyra
Chief Scientist @VantAI
ML Lead @ProjectCETI
geometric deep learning, graph neural networks, generative models, molecular design, proteins, bio AI, 🐎 🎶
Official account for the IEEE/CVF International Conference on Computer Vision. #ICCV2025 Honolulu 🇺🇸 Co-hosted by @natanielruiz @antoninofurnari @yaelvinker @CSProfKGD
Official account for IEEE/CVF Conference on Computer Vision & Pattern Recognition. Hosted by @deblinaml @jbhaurum & @CSProfKGD
📍🌎 🔗 cvpr.thecvf.com 🎂 June 19, 1983
Official Account for the European Conference on Computer Vision (ECCV) #ECCV2026, Malmo 🇸🇪 Hosted by @jbhaurum and @CSProfKGD
Computer Vision & Machine Learning
📍 Pioneer Centre for AI, University of Copenhagen
🌐 https://www.belongielab.org
boris with 10 r's (handles with fewer r's were taken). ML for weather (prev health) @ Google. into guitars, sci fi, parenting, lolz. i make rock music for kids: https://open.spotify.com/artist/43Np3yVcbFcW4Uyn9C2MPe?si=gsh99-beRTSafXO_PxaSgg
creations with code and networks
Generative AI and computer graphics at Aalto University & NVIDIA Research. @ellis.eu Fellow. https://users.aalto.fi/~lehtinj7
