FGVC11 at @CVPR is just 5 days away! Don't miss our exciting lineup of speakers: @SachitMenon, @phillip_isola, @ZhongingAlong, @lschmidt3, & Sharmishtaa Seshamani. Starting 8:45am June 18th in Summit 326! https://t.co/a1mcqEfcTK
Excited to share that the paper of my last summer internship at NEC Lab, "AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving," has been accepted by CVPR-2024! In short, we created the first Automatically Improved Data Engine (AIDE) to scale up the Autonomous Vehicle (AV) system on handling safety-critical novel object detection, which exhibits great scaling law with increasing amounts of unlabeled data! Huge thanks to all my mentors from the Media Analytics Department at NEC Lab! More details are coming soon! #CVPR2024
I'm seeking PhD students for a summer internship at NEC Labs. You'll work on automated ML pipelines for autonomous driving, focusing on using simulations and VLM/LLM to enhance perception and prediction.
Please apply here and email me: https://t.co/IeLmVvFknX
I'm looking for summer research interns at NEC Labs. You will be working on the following topics: 2D/3D detection/segmentation, open-world recognition, continual learning, domain generalization, etc. Please contact me and apply here if you are interested!
https://t.co/gcVEGeAM4i
Why does ChatGPT work so well? Is it “just scaling up GPT-3” under the hood? In this 🧵, let’s discuss the “Instruct” paradigm, its deep technical insights, and a big implication: “prompt engineering” as we know it may likely disappear soon:👇
NeRFs are getting attention these days!
However widespread adoption is still slow. But why?
It comes down to a) file size and b) rendering.
An engineer's viewpoint:
TLDR: NeRFs are fundamentally a bad fit for today's edge device architectures.
Let's explain that in detail:
1/
Semantic segmentation is not limited to a fixed label set! Happy introduce LSeg, a novel model that can dynamically handle arbitrary label sets on the fly with varying length, content, and order 🌻
Paper: https://t.co/WgI2qw1WAd
Demo: https://t.co/jxVEkyxWjy
Our recent work appeared on BMVC is now on arXiv https://t.co/baTt4dFr7T (w/ @MajiSubhransu). We use coarsely labeled data to improve semi-supervised learning on fine-grained classification.