AI with Papers - Artificial Intelligence & Deep Learning
15.5K subscribers
144 photos
255 videos
14 files
1.34K 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
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿชฌ META's Animated Drawings is out! ๐Ÿชฌ

๐Ÿ‘‰#META unveils an easy-to-use method for animating human-like figures drawn by children.

๐Ÿ˜ŽReview https://bit.ly/3mGeQQv
๐Ÿ˜ŽPaper arxiv.org/pdf/2303.12741.pdf
๐Ÿ˜ŽProject fairanimateddrawings.com
๐Ÿ˜ฑ16๐Ÿฅฐ5๐Ÿ‘4๐Ÿ‘2๐Ÿคฉ2โšก1๐Ÿ”ฅ1๐Ÿพ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿฆ• 6D Non-Prehensile Manipulation ๐Ÿฆ•

๐Ÿ‘‰#META (+CMU) unveils HACMan, novel 6D non-prehensile manipulation of objects

๐Ÿ˜ŽReview https://bit.ly/3NP1jl1
๐Ÿ˜ŽPaper arxiv.org/pdf/2305.03942.pdf
๐Ÿ˜ŽProject hacman-2023.github.io
๐Ÿ‘6๐Ÿ”ฅ4๐Ÿคฏ3๐Ÿ˜ฑ1
๐Ÿฆ™ Llama-2: the Open-Source "ChatGPT" ๐Ÿฆ™

๐Ÿ‘‰GenAI, #Meta unveils Llama-2: a collection of LLMs ranging in scale 7-70B params. Challenging with #chatgpt, but open.

๐Ÿ˜ŽReview https://t.ly/bLJgP
๐Ÿ˜ŽPaper https://t.ly/AOXru
๐Ÿ˜ŽProject https://ai.meta.com/llama
๐Ÿคฏ19โค2๐Ÿ”ฅ1๐Ÿ’ฉ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ˜ Controllable Synthetic Data (extending Image-Net) ๐Ÿ˜

๐Ÿ‘‰#META's PUG, a new generation of interactive environments for representation learning. Extending Image-Net!

๐Ÿ˜ŽReview https://t.ly/nCYs0
๐Ÿ˜ŽPaper arxiv.org/pdf/2308.03977.pdf
๐Ÿ˜ŽProject pug.metademolab.com
๐Ÿ˜ŽCode github.com/facebookresearch/PUG
๐Ÿ”ฅ4โค2๐Ÿ‘1๐Ÿคฉ1
This media is not supported in your browser
VIEW IN TELEGRAM
โ›บFACET: Fairness in Computer Visionโ›บ

๐Ÿ‘‰#META AI opens a large, publicly available dataset for classification, detection & segmentation. Potential performance disparities & challenges across sensitive demographic attributes

๐Ÿ˜ŽReview https://t.ly/mKn-t
๐Ÿ˜ŽPaper arxiv.org/pdf/2309.00035.pdf
๐Ÿ˜ŽDataset https://facet.metademolab.com/
๐Ÿ”ฅ10โค6๐Ÿ‘4๐Ÿ‘1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ”ฅ๐Ÿ”ฅ #META's DINOv2 is now commercial! ๐Ÿ”ฅ๐Ÿ”ฅ

๐Ÿ‘‰Universal features for image classification, instance retrieval, video understanding, depth & semantic segmentation. Now suitable for commercial.

๐Ÿ˜ŽReview https://t.ly/LNrGy
๐Ÿ˜ŽPaper arxiv.org/pdf/2304.07193.pdf
๐Ÿ˜ŽCode github.com/facebookresearch/dinov2
๐Ÿ˜ŽDemo dinov2.metademolab.com/
๐Ÿ”ฅ15๐Ÿ‘3โค1๐Ÿคฏ1๐Ÿ˜ฑ1
This media is not supported in your browser
VIEW IN TELEGRAM
โœŒ๏ธ Relighted 3D Hands ๐Ÿคž

๐Ÿ‘‰#META unveils Re:InterHand: a large dataset of relighted 3D interacting hands

๐Ÿ˜ŽReview https://t.ly/I1dQk
๐Ÿ˜ŽPaper arxiv.org/pdf/2310.17768.pdf
๐Ÿ˜ŽProject mks0601.github.io/ReInterHand
๐Ÿ˜ŽData github.com/mks0601/ReInterHand
๐Ÿคฏ8โค1๐Ÿ˜ฑ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ“ Emu: image edit / video gen. ๐Ÿ“

๐Ÿ‘‰#Meta the new SOTA in text-to-video generation and instruction-based image editing

๐Ÿ‘‰ Review https://t.ly/PMTBc
๐Ÿ‘‰ Paper (images): https://lnkd.in/eVadH-QS
๐Ÿ‘‰ Project https://lnkd.in/eG8eWUJY
๐Ÿ‘‰ Paper (video): https://lnkd.in/eVadH-QS
๐Ÿ‘‰ Project https://lnkd.in/eu6Zu6gp
๐Ÿ”ฅ8๐Ÿคฏ2๐Ÿ‘1๐Ÿ˜ฑ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿช–RT Humanoid from Head-Mounted Sensors๐Ÿช–

๐Ÿ‘‰#META (+CMU) announced SimXR, a method for controlling a simulated avatar from info obtained from AR/VR headsets

๐Ÿ‘‰Review https://t.ly/Si2Mp
๐Ÿ‘‰Paper arxiv.org/pdf/2403.06862.pdf
๐Ÿ‘‰Project www.zhengyiluo.com/SimXR/
โค12โšก1๐Ÿ‘1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸงคHOT3D Hand/Object Tracking๐Ÿงค

๐Ÿ‘‰#Meta opens a novel egocentric dataset for 3D hand & object tracking. A new benchmark for vision-based understanding of 3D hand-object interactions. Dataset available ๐Ÿ’™

๐Ÿ‘‰Review https://t.ly/cD76F
๐Ÿ‘‰Paper https://lnkd.in/e6_7UNny
๐Ÿ‘‰Data https://lnkd.in/e6P-sQFK
๐Ÿ”ฅ9โค3๐Ÿ‘3๐Ÿ‘2๐Ÿคฏ1