AI with Papers - Artificial Intelligence & Deep Learning
15.4K subscribers
143 photos
255 videos
14 files
1.33K links
All the AI with papers. Every day fresh updates about #DeepLearning, #MachineLearning, LLMs and #ComputerVision

Curated by Alessandro Ferrari | https://www.linkedin.com/in/visionarynet/

#artificialintelligence #machinelearning #ml #AI
Download Telegram
πŸ”₯πŸ”₯ Sunday mood πŸ”₯πŸ”₯
🀣32❀2
🎸Another BRIXEL in the Wall 🎸

πŸ‘‰BRIXEL allows the user to produce high-resolution feature maps using the DINOv3 backbone without requiring large amounts of compute. Repo releasedπŸ’™

πŸ‘‰Review https://t.ly/fZPwC
πŸ‘‰Paper arxiv.org/pdf/2511.05168
πŸ‘‰Repo github.com/alexanderlappe/BRIXEL
🀩7🀯3πŸ”₯2❀1πŸ‘1😍1
This media is not supported in your browser
VIEW IN TELEGRAM
🐼Pixel-Dense Embedding🐼

πŸ‘‰FlowFeat is a novel high-resolution and multi-task feature representation that embeds a distribution of plausible apparent motions, or motion profiles. Repo available under πŸ’™

πŸ‘‰Review https://t.ly/aUx_U
πŸ‘‰Paper arxiv.org/pdf/2511.07696
πŸ‘‰Project tum-vision.github.io/flowfeat
πŸ‘‰Repo github.com/tum-vision/flowfeat
πŸ”₯4πŸ‘3❀2
🍿🍿🍿
🀯17πŸ”₯8πŸ‘2❀1πŸ‘1
🚨 Announcement 🚨

I’ve received numerous reports of people blatantly copying my content on LinkedIn just to get a few likes.

Let me be very clear: I put a great deal of time and effort into reviewing papers and creating original, meaningful content. It’s disappointing to see professionals (some of whom are even members of this group or my connections) resorting to plagiarism instead of contributing their own ideas.

πŸ‘‰ Starting today, I’ll be removing these connections from LinkedIn and banning such individuals from this group.

πŸ“’ I also encourage everyone to report these cases whenever you come across them. Every single report helps stop this bad habit and keeps our community fair, respectful, and authentic.
❀53πŸ‘19πŸ‘14😒1
This media is not supported in your browser
VIEW IN TELEGRAM
🟩 Foundational Humanoid 🟩

πŸ‘‰#NVIDIA unveils SONIC a novel foundational model for high-precision teleoperation & interactive control capabilities (running, jumping, crawling) with natural human-like movements. Code announcedπŸ’™

πŸ‘‰Review https://t.ly/_3wnt
πŸ‘‰Paper https://lnkd.in/dctfShu8
πŸ‘‰Project https://lnkd.in/d_inmA2p
🀯8❀4πŸ”₯2
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ”₯Depth Anything 3 is outπŸ”₯

πŸ‘‰ByteDance unveils Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from arbitrary visual inputs, with or without known camera poses. Repo under Apache 2.0πŸ’™

πŸ‘‰Review https://t.ly/AOPu7
πŸ‘‰Paper arxiv.org/pdf/2511.10647
πŸ‘‰Project https://lnkd.in/dnByyn2z
πŸ‘‰Repo https://lnkd.in/daCVz_4a
πŸ‘‰Demo https://lnkd.in/dKUZiJt
πŸ”₯10❀6πŸ‘1πŸ‘1