Ana Santos, CFO of Schneider Electric Canada, and one of the judges for the #SchneiderGoGreen finals wishes the top 8 teams a special good luck for their presentations on September 10th! She'll see you there! #WhatsYourBoldIdea? spr.ly/6016GqegI

Top 16 finalists, are you ready? Saulo Spaolanse, Andean Cluster President at Schneider Electric and judge for this year's competition shares his thoughts and excitement for the finals! Good luck!! 🎉 spr.ly/6010GqeIr #WhatsYourBoldIdea #SchneiderGoGreen

As NeurIPS Conference #NeurIPS2021 deadline approaches, I've consolidated some technical writing tips. Succinct answers to each of the questions, Voila, you have a crisp Introduction! Expand on prior work, intuition/tech details, & expts for the rest ensuring the why is always clear

Workshop begins in ~1.5 hours at 7am EDT / 1pm CEST. Don't miss all the invited speakers + papers + challenge results! Featured in #CVPR Daily magazine! rsipvision.com/CVPR2021-Wedne… YouTube livestream open to everyone: youtube.com/watch?v=bwIgpx… Schedule here: eval.vision.rwth-aachen.de/rvsu-workshop2…

Excited to present our work on temporal instance filling for video instance segmentation with Harvard VCG and Hanspeter Pfister at the Robust Video Scene Understanding Workshop. Drop by for any questions or a quick chat at the poster session! #CVPR2021

For safe driving with LiDAR perception, let's consider "Lidar Panoptic Segmentation in an Open World" to attention to both unknown and known things and stuff! See our IJCV work by Anirudh Chakravarthy Meghana, Peiyun Hu Laura Leal-Taixe Deva Ramanan Aljosa link.springer.com/article/10.100…

New Paper!! We try to understand why some LMs self-improve their reasoning while others hit a wall. The key? Cognitive behaviors! Read our paper on how the right cognitive behaviors can make all the difference in a model's ability to improve with RL! 🧵1/13

Found out why some AI models learn from RL while others just stare blankly: turns out you need to show them the reasoning 'moves' first! We isolate the specific 'moves' that need to be introduced in a model's training! Paper: arxiv.org/abs/2503.01307

a month too late but super excited to have joined the Amazon AGI SF research lab building Nova Act 🚀 we're just getting started and so much more to come! if you're in the bay and working on agents, feel free to DM!

Tokasaurus is out! Happy Throughput Thursday to those who celebrate :)