AI with Papers - Artificial Intelligence & Deep Learning
15K subscribers
95 photos
236 videos
11 files
1.26K links
All the AI with papers. Every day fresh updates on Deep Learning, Machine Learning, and Computer Vision (with Papers).

Curated by Alessandro Ferrari | https://www.linkedin.com/in/visionarynet/
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ’ͺ Muscles in Action with #AI πŸ’ͺ

πŸ‘‰Muscles in Action (MIA): learn to incorporate muscle activity into human motion representations

😎Review https://t.ly/hUKub
😎Paper arxiv.org/pdf/2212.02978.pdf
😎Project musclesinaction.cs.columbia.edu
πŸ”₯7πŸ‘2πŸ‘2🀯1
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ‘— Multimodal Neural Designer πŸ‘—

πŸ‘‰ Multimodal #AI that can generate novel fashion images conditioned on text, keypoints, and sketches

😎Review https://t.ly/zVk70
😎Paper arxiv.org/pdf/2304.02051.pdf
😎Code github.com/aimagelab/multimodal-garment-designer
πŸ₯°6❀4🀩3πŸ”₯2⚑1
This media is not supported in your browser
VIEW IN TELEGRAM
🧱 Generating Scenes from Touch 🧱

πŸ‘‰#AI for synthesizing images from tactile signals (and vice versa) and apply it to a number of visuo-tactile synthesis tasks

😎Review https://t.ly/Gxr0L
😎Paper https://arxiv.org/pdf/2309.15117.pdf
😎Project https://fredfyyang.github.io/vision-from-touch
😎Code https://github.com/fredfyyang/vision-from-touch
🀯9πŸ‘6❀1πŸ”₯1πŸ‘1😱1
This media is not supported in your browser
VIEW IN TELEGRAM
🌱 Making LLaMA See and Draw 🌱

πŸ‘‰Tencent #AI planted a SEED of Vision in Large Language Model. Making LLaMA see 'n' draw stuff.

😎Review https://t.ly/QiCAv
😎Paper arxiv.org/pdf/2310.01218.pdf
😎Code github.com/AILab-CVC/SEED
❀8πŸ‘4🀯3πŸ”₯1
πŸ“Š TextPSG: PSG from Text πŸ“Š

πŸ‘‰A novel problem in #AI: Panoptic Scene Graph Generation from Purely Textual Descriptions (Caption-toPSG)

😎Review https://t.ly/UXEmk
😎Paper arxiv.org/pdf/2310.07056.pdf
😎Project vis-www.cs.umass.edu/TextPSG
😎Code github.com/chengyzhao/TextPSG
πŸ”₯9❀5πŸ‘3🀩1
πŸ¦Ήβ€β™€οΈ Snap's Hyper-Realistic Human πŸ¦Ήβ€β™€οΈ

πŸ‘‰New diffusive #AI by Snap that generates in-the-wild human images with hyper-realism. Swipe the gallery, NUTS!πŸ‘‡

😎Gallery https://t.ly/cG74X
😎Paper arxiv.org/pdf/2310.08579.pdf
😎Project snap-research.github.io/HyperHuman
😎Code github.com/snap-research/HyperHuman
πŸ‘4πŸ”₯1🀯1😱1🀩1🀣1
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ₯»SF: Towards Virtual ClothπŸ₯»

πŸ‘‰SEA AI Lab unveils a novel #AI to recovery the garment sewing patterns from daily photos for #AR / #VR worlds

😎Review https://t.ly/MwpAV
😎Project https://sewformer.github.io/
😎Paper https://arxiv.org/pdf/2311.04218.pdf
😎Code https://github.com/sail-sg/sewformer
πŸ‘4πŸ”₯2πŸ₯°2πŸ‘2🀯1🀩1
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ”₯ Hu.ma.ne #AI Pin is out! πŸ”₯

πŸ‘‰Hu.ma.ne just launched #AI Pin: the new standalone AI-powered screenless device. Running on the GPT-4 LLMs, suitable for real-time translation. #AI-powered camera and laser projector

😎 More https://t.ly/IvoN7
❀6πŸ”₯4πŸ’©2πŸ‘1😱1
This media is not supported in your browser
VIEW IN TELEGRAM
🧱 Material Palette from Images 🧱

πŸ‘‰A novel problem in #AI: material extraction from a real-world image without any prior knowledge 🀯

πŸ‘‰Discussion https://t.ly/AIWs-
πŸ‘‰Paper https://lnkd.in/dBFAVWPF
πŸ‘‰Project https://lnkd.in/dV5jK8Sm
πŸ‘‰Code https://lnkd.in/dNhMnfFb
πŸ‘‰Dataset (coming) ...
❀9πŸ‘2πŸ”₯1πŸ₯°1🀯1
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ‘‘ HD Generative #AI With No $$πŸ‘‘

πŸ‘‰DemoFusion: a novel approach for HD image generation w/ no money. Progressive Upscaling, Skip Residual, & Dilated Sampling to achieve higher-resolution ever πŸ”₯

πŸ‘‰Review https://t.ly/sIqDV
πŸ‘‰Paper https://lnkd.in/deDt-zcK
πŸ‘‰Project https://lnkd.in/dFGj47Xw
πŸ‘‰Code https://lnkd.in/dY3UcXwp
πŸ‘4❀2🀯2πŸ‘1😱1
This media is not supported in your browser
VIEW IN TELEGRAM
🍑 Animate Anyone: new SOTA! 🍑

πŸ‘‰Alibaba unveils Animate Anyone: novel #AI for transforming character images into animated videos controlled by desired pose sequences. Animating any character image into a video, unconstrained by specific domains πŸš€

πŸ‘‰Review https://t.ly/qCahZ
πŸ‘‰Paper https://lnkd.in/d-zi8EZ6
πŸ‘‰Project https://lnkd.in/djwjQRvq
πŸ‘‰Repo https://lnkd.in/dDMkjnKz
🀯22πŸ‘8πŸ”₯4⚑1❀1😱1
πŸƒReplaceAnything: demo is out!πŸƒ

πŸ‘‰ReplaceAnything: ultra-high quality content replacement. The ultimate #AI solution for human, clothing & background replacement to change the e-commerce experience for vendors.

πŸ‘‰Review https://t.ly/FMyvf
πŸ‘‰Project https://lnkd.in/dcyZvP2b
πŸ‘‰ModelScope https://lnkd.in/dU4x4nE6
πŸ‘‰Hugging Face https://lnkd.in/dn3uXWgd
πŸ‘‰Empty report https://lnkd.in/dcuGXd6c
πŸ‘‰Paper coming?
❀11πŸ‘3πŸ‘2😍1
πŸ’₯ Announcing #Py4Ai ConferenceπŸ’₯

πŸ‘‰ Super proud to unveil #Py4AI, the newest conference dedicated to exploring the depths of Python & AI. Py4AI is a 1-day free event for Python and Artificial Intelligence developers.

π“π‘πž 𝐟𝐒𝐫𝐬𝐭 π›πšπ­πœπ‘ 𝐨𝐟 𝐬𝐩𝐞𝐚𝐀𝐞𝐫𝐬:
πŸš€Merve Noyan | #HuggingFace πŸ€—
πŸš€Gabriele Lombardi | ARGO Vision
πŸš€Amanda Cercas Curry | Uni. Bocconi
πŸš€Piero Savastano | Cheshire Cat AI
πŸš€Francesco Zuppichini | Zurich Insurance
πŸš€Andrea Palladino, PhD | Sr. Data Scientist

πŸ‘‰ More: https://www.linkedin.com/posts/visionarynet_py4ai-py4ai-python-activity-7152928716988243968-pOUn?utm_source=share&utm_medium=member_desktop
πŸ‘10πŸ‘2❀1πŸ₯°1🀯1
🧠350+ Free #AI Courses by #Google🧠

πŸ‘‰350+ free courses from #Google to become professional in #AI & #Cloud. The full catalog (900+) includes a variety of activity: videos, documents, labs, coding, and quizzes. 15+ supported languages. No excuse.

βœ…π†πžπ§πžπ«πšπ­π’π―πž π€πˆ
βœ…πˆπ§π­π«π¨ 𝐭𝐨 π‹π‹πŒπ¬
βœ…π‚π• 𝐰𝐒𝐭𝐑 𝐓𝐅
βœ…πƒπšπ­πš, πŒπ‹, π€πˆ
βœ…π‘πžπ¬π©π¨π§π¬π’π›π₯𝐞 π€πˆ

πŸ‘‰Review: https://t.ly/517Dr
πŸ‘‰Full list: https://www.cloudskillsboost.google/catalog?page=1
❀13πŸ‘3πŸ‘2🍾2πŸ”₯1
This media is not supported in your browser
VIEW IN TELEGRAM
🚦(add) Anything in Any Video🚦

πŸ‘‰ XPeng Motors announced Anything in Any Scene: novel #AI for realistic video simulation that seamlessly inserts any object into an existing dynamic video. Strong emphasis on realism, the objects in the BBs don't exist. Source Code released πŸ’™

πŸ‘‰Review https://t.ly/UYhl0
πŸ‘‰Code https://lnkd.in/gyi7Dhkn
πŸ‘‰Paper https://lnkd.in/gXyAJ6GZ
πŸ‘‰Project https://lnkd.in/gVA5vduD
πŸ”₯12🀯6πŸ‘5πŸ₯°1
This media is not supported in your browser
VIEW IN TELEGRAM
🐺 Diffusion Game Engine 🐺

πŸ‘‰#Google unveils GameNGen: the first game engine powered entirely by a neural #AI that enables real-time interaction with a complex environment over long trajectories at HQ. No code announced but I love it πŸ’™

πŸ‘‰Review https://t.ly/_WR5z
πŸ‘‰Paper https://lnkd.in/dZqgiqb9
πŸ‘‰Project https://lnkd.in/dJUd2Fr6
πŸ”₯10πŸ‘5❀2πŸ‘1
This media is not supported in your browser
VIEW IN TELEGRAM
🌳 HD Video Object Insertion 🌳

πŸ‘‰VideoAnydoor is a novel zero-shot video object insertion #AI with high-fidelity detail preservation and precise motion control. All-in-one: video VTON, face swapping, logo insertion, multi-region editing, etc.

πŸ‘‰Review https://t.ly/hyvRq
πŸ‘‰Paper arxiv.org/pdf/2501.01427
πŸ‘‰Project videoanydoor.github.io/
πŸ‘‰Repo TBA
πŸ”₯8❀2πŸ’©2πŸ‘1🀩1😍1
πŸ’™ Announcing #Py4AI 2025 πŸ’™

πŸ‘‰ The second edition of Py4AI conference is official! An all-day, fully free, event for #AI & #Python lovers.

π“π‘πž 𝐟𝐒𝐫𝐬𝐭 π›πšπ­πœπ‘ 𝐨𝐟 𝐬𝐩𝐞𝐚𝐀𝐞𝐫𝐬:
πŸš€Dana Aubakirova | Hugging FaceπŸ€—
πŸš€Yunhao Liu & Ruoya Sheng | ByteDanceπŸ”₯
πŸš€Alice Casiraghi | 🌏🌎🌍
πŸš€Luca Arrotta, PhD | DatapizzaπŸ•
πŸš€Valeria Zuccoli | Bettini Srl
πŸš€Mirco Planamente | ARGO Vision
πŸš€Daniele Zonca | Red Hat

πŸ‘‰ Info & registration: https://t.ly/37wWj
❀7⚑1πŸ‘1πŸ”₯1🀩1