Artificial Intelligence l l AI Updates
Open in Telegram
News about AI & DL & ML!!! Admin: @Gayrat_Tangriberganov
Show more1 611
Subscribers
-224 hours
-17 days
+630 days
Posts Archive
π GitHub_Link
βοΈ Molmo 2: State-of-the-art video understanding, pointing, and trackingπ₯
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Vid2Haircut: 3D Strand-Based Hairstyle Reconstruction from Videoπ₯
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ SAM 3D Body: Robust Full-Body Human Mesh Recoveryπ₯
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration π₯
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Self-Supervised LiDAR Ground Segmentationπ₯
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Accelerated Diffusion Models:
From Theory to Interactive World Models
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding π―
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Enhancing Hands in 3D Whole-Body Pose Estimation with Conditional Hands Modulator
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ HiDream-O1-Image π₯π₯π₯
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ CAPYBARA: A Unified Visual Creation Model π₯
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ A Modular Deep Learning for Reactive Chemistry π§ͺπ§¬π₯
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ PersonaLive: Expressive Portrait Image Animation for Live Streaming π₯
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Depth Anything at Any Conditionπ₯
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ SAPIENS2: Scaleπ₯ Semanticsπ₯ Fidelityπ₯
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Video Analysis and Generation via a Semantic Progress Function π₯
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator π₯
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detectionπ₯
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
Available now! Telegram Research 2025 β the year's key insights 
