🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

DLBCN 2022 will be on Monday 19th December at UPC Campus Nord. Calls for talks and posters are open until October 21. sites.google.com/view/dlbcn2022… Submit your work and help Barcelona growing as a deep learning capital. #DLBCN

Tomorrow at 10am (Tel Aviv Time), I will be presenting our work on Event-based Image Deblurring at #MIPI workshop at #ECCV2022. Don't miss it! 😜

A quick thread on a ‘simple’ problem: denoising x = u + e Noisy signal = x Clean signal = u Gaussian iid noise = e Two well-known approaches: MAP: Maximum a-posteriori MMSE: Minimum mean square error They don’t coincide, but share several interesting properties 1/4

World Cup: 1 - Ph.D.: 0

I'll present this work on Thursday in New Orleans at #NeurIPS2022 !! See u there ☀️👾

New course announcement! Math for Machine Learning and Data Science. Designed to make learning AI's math easy: ∙ Linear algebra ∙ Probability & Stats ∙ Calculus Will help learners build better ML systems and pass job interviews! deeplearning.ai/courses/mathem…

Adrià Recasens (Adrià Recasens) from @DeepMind presents how to predict the trajectories of football players beyond the camera field of view. #DLBCN nature.com/articles/s4159…

The color palette of an image is the 3D empirical distribution of the pixels. Optimal transport allows one to interpolate between palettes. en.wikipedia.org/wiki/Palette_(… optimaltransport.github.io

We have one more position for a 2023 summer applied science intern. If interested DM me. Amazon Science #Seattle #MachineLearning #ComputerVision #NLP #LLM

BAAI (Beijing Academy of AI) releases Aquila: a Chinese/English open source LLM with 7B and 33B models. github.com/FlagAI-Open/Fl…

Face0: Instantaneously Conditioning a Text-to-Image Model on a Face paper page: huggingface.co/papers/2306.06… present Face0, a novel way to instantaneously condition a text-to-image generation model on a face, in sample time, without any optimization procedures such as fine-tuning or

Love this problem statement! Reconstruct the world from retinal reflections: world-from-eyes.github.io The original paper from 2004 by Nishino and Nayar was a super inspiring example of creative research for me: cave.cs.columbia.edu/projects/categ… Great to see a 3D version of it!!

😂😂😂

Apple Maps is undeniably stunning!

Announcing the Deep Learning Barcelona Symposium 2023 on Thursday December 21st. 5th edition !!

Functions f : ℝⁿ→ℝⁿ of the “pseudo-linear” form f(x) = A(x) x are common. For example: pixel-adaptive filters like non-local means; attention mechanism in transformers; even a convolutional layer with relu nonlinearity Gradient of this f(x) has a form worth remembering:

Got a batch of blurry pictures from last vacation? "Blind Motion Deblurring with Pixel-Wise Kernel Estimation via Kernel Prediction Networks" by Guillermo Carbajal 泰兴上课/泰兴上门/泰兴上门服务/泰兴外卖/泰兴外送员/泰兴外送媛/泰兴服务 José Lezama Pablo Musé from Universidad de la República is now on Early Access! ieeexplore.ieee.org/document/10271…

Major improvements to Personas come with visionOS 26 - with striking expressivity and sharpness, a full side profile view, and more accurate hair, lashes, and complexion