AI with Papers - Artificial Intelligence & Deep Learning
17.5K subscribers
152 photos
264 videos
14 files
1.39K links
All the AI with papers. Every day fresh updates about #DeepLearning #MachineLearning #LLM & #ComputerVision

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

#AI #chatGPT
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ“Š SOTA Style Transfer ๐Ÿ“Š

๐Ÿ‘‰TeleAI unveils TeleStyle, a lightweight yet effective model for image/video stylization. Built upon Qwen-Image-Edit, TeleStyle leverages the base modelโ€™s robust capabilities in content preservation & style customization. Code & Model released๐Ÿ’™

๐Ÿ‘‰Review https://t.ly/viVR0
๐Ÿ‘‰Paper arxiv.org/pdf/2601.20175
๐Ÿ‘‰Project tele-ai.github.io/TeleStyle/
๐Ÿ‘‰Repo github.com/Tele-AI/TeleStyle
โค10๐Ÿ‘2๐Ÿ”ฅ1๐Ÿคฏ1๐Ÿคฃ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ‘ Metric Anything is out ๐Ÿ‘

๐Ÿ‘‰Metric Anything (Li Auto inc.) is a simple and scalable pretraining framework that learns metric depth from noisy, diverse 3D sources without manually engineered prompts, camera-specific modeling, or task-specific architectures. Impressive. Code announced ๐Ÿ’™

๐Ÿ‘‰Review https://t.ly/54Ccr
๐Ÿ‘‰Paper arxiv.org/pdf/2601.22054
๐Ÿ‘‰Project metric-anything.github.io/metric-anything-io/
๐Ÿ‘‰Repo github.com/metric-anything/metric-anything
๐Ÿ”ฅ10โค5๐Ÿ‘1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸŒˆSegment Any Events by Language๐ŸŒˆ

๐Ÿ‘‰SEAL (by NUS) is the first Semantic-aware Segment Any Events framework that addresses Open-Vocabulary Event Instance Segmentation. Code announced๐Ÿ’™

๐Ÿ‘‰Review https://t.ly/1ZMF0
๐Ÿ‘‰Paper https://arxiv.org/pdf/2601.23159
๐Ÿ‘‰Project https://0nandon.github.io/SEAL/
๐Ÿ‘‰Repo https://github.com/0nandon/SEAL
๐Ÿ”ฅ6โค3๐Ÿ‘1๐Ÿคฏ1
๐Ÿ‘‰RAM prices skyrocketing

๐Ÿ‘‰Me acting like a rich kid.

Let's talk: https://www.linkedin.com/posts/visionarynet_ai-ram-ddr5-activity-7424127924020072448-NbaO
๐Ÿคฃ18โค4๐Ÿ”ฅ1๐Ÿ‘1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸฎCoWTracker: Track-Warping๐Ÿฎ


๐Ÿ‘‰CoWTracker (VGG + META) is a novel dense point tracker that eschews cost volumes in favor of warping. Code/Models under FAIR NC๐Ÿ’™

๐Ÿ‘‰Review https://t.ly/6bAn9
๐Ÿ‘‰Paper https://arxiv.org/pdf/2602.04877
๐Ÿ‘‰Project https://cowtracker.github.io/
๐Ÿ‘‰Repo https://github.com/facebookresearch/cowtracker
โค2๐Ÿ”ฅ2
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸŒˆTrajVG Trajectory-Geometry๐ŸŒˆ

๐Ÿ‘‰TrajVG is a novel reconstruction framework that makes cross-frame 3D correspondence an explicit prediction by estimating camera-coordinate 3D trajectories. Code announced๐Ÿ’™

๐Ÿ‘‰Review https://t.ly/yVi01
๐Ÿ‘‰Paper arxiv.org/pdf/2602.04439
๐Ÿ‘‰Project xingy038.github.io/TrajVG/
๐Ÿ‘‰Repo github.com/xingy038/TrajVG
๐Ÿ”ฅ2โค1