Artificial Intelligence l l AI Updates
Open in Telegram
News about AI & DL & ML!!! Admin: @Gayrat_Tangriberganov
Show more1 614
Subscribers
No data24 hours
+47 days
+530 days
Posts Archive
π GitHub_Link
βοΈ Torch2Chip (MLSys, 2024)
Torch2Chip is an End-to-end Deep Neural Network compression toolkit designed for prototype accelerator designer for algorithm-hardware co-design with high-degree of algorithm customization.
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
Convert your favorite LLM into an embedding model with LLM2Vec. Perform RAG with your model for generation and retrieval. Follow simple 2-step process for conversion:
1) Load the desired LLM into llm2vec package for conversion to embedding model.
2) Perform MNTP supervised or SIMCSE unsupervised training for better results on retrieval tasks.
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Hand Sign Detection
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
π Tutorial_Link
βοΈ Classwise line graphs + analytics using Ultralytics πΊπ₯
#YOLO
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π Project_page
βοΈ GenWarp: Single Image to Novel Views with
Semantic-Preserving Generative Warping
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ MegActor: Harness the Power of Raw Video for Vivid Portrait Animation
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Low Latency Automotive Vision with Event Cameras
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π Project_page
βοΈ Flow-Guided Online Stereo Rectification for Wide Baseline Stereo
#DepthEstimation
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Physically-Based Lighting for 3D Generative Models of Cars
#GAN
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ TEACH: Temporal Action Compositions for 3D Humans
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
πΎTennis AnalysisπΎ
βοΈ This project analyzes Tennis players in a video to measure their speed, ball shot speed and number of shots. This project will detect players and the tennis ball using YOLO and also utilizes CNNs to extract court keypoints.
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ LLMParser: LLMParser is a simple and flexible tool to classify and extract structured data from text with large language models.
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ PyTorch in Rust
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Everything-about-LLMs
#LLMs
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ FlashFace: Human Image Personalization with High-fidelity Identity Preservation
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ VILA - A multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Self-supervised Amodal Video Object Segmentation
#ObjectSegmentation
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Assignment-Space-Based Multi-Object Tracking and Segmentation
#ObjectTracking #Segmentation
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
π GitHub_Link
βοΈ Context-Aware Relative Object Queries to Unify Video Instance and Panoptic Segmentation
#VideoSegmentation # InstanceSegmentation #PanopticSegmentation
Join my channel:
ππππππ
https://t.me/Artificial_Intelligence_Updates
Available now! Telegram Research 2025 β the year's key insights 
