Artificial Intelligence l l AI Updates
Open in Telegram
News about AI & DL & ML!!! Admin: @Gayrat_Tangriberganov
Show more1 615
Subscribers
No data24 hours
+47 days
+530 days
Posts Archive
š GitHub_Link
āļø MindOCR: A toolbox of ocr models and algorithms based on MindSpore š„
#OCR
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø GeoLayoutLM: Geometric Pre-training for Visual Information Extraction
#VisualInformationExtraction
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø DocXChain: A Powerful Open-Source Toolchain for Document Parsing and Beyond
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø Visual Text Generation in the Wild
#VisualTextGeneration
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø Visualize menus in seconds with AI š„
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
#ViTs
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø Elysium: Exploring Object-level Perception in Videos via MLLM
#MLLM
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models
#MeshGeneration #LLMs
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory š„āļøš„
#SAM
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø Line Art to 3D with MistoLine & TripoSR š„
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø Consistent Video-to-Video Transfer Using Synthetic Dataset
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø Multi-Modal Prompt š„š
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø AttenCraft: Attention-guided Disentanglement of Multiple Concepts for Text-to-Image Customization
#Text2img
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø Cinemo: Consistent and Controllable Image Animation with Motion Diffusion Models
#DiffusionModels
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø X-Pose: Detecting Any Keypoints š„
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø Thin-Plate Spline-based Interpolation for Animation Line Inbetweening
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø Memory-Efficient Optical Flow via Radius-Distribution Orthogonal Cost Volume
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers
#ViTs #PoseEstimation
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest
#LLMs
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
š GitHub_Link
āļø Training-free Regional Prompting for Diffusion Transformers
#DiffusionModel
Join my channel:
šššššš
https://t.me/Artificial_Intelligence_Updates
Available now! Telegram Research 2025 ā the year's key insights 
