🔗 GitHub_Link

An Explainability Method for Vision Transformers via Feature Formation Sensitivity

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

Karpathy released a new 💥tutorial💥 where he trains a LLM from scratch in pure C without PyTorch or cPython.

Starts with GPT-2 training on CPU/fp32 in only ~1,000 lines of clean code.

It compiles and runs instantly, and exactly matches the PyTorch reference implementation.

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

💥Mini-Gemini💥

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

💥WonderJourney: Going from Anywhere to Everywhere💥

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link
🔗 Tutorial_Link

💥Real-Time Dwell Time Analysis💥

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

SMART Counter System for Retail Shops

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 Project_Page_Link

A Large Language Model That Can Speak and Listen

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link
🔗 Demo_Link
🔗 Tutorial_Link

Foundational Models for State-of-the-Art Speech and Text Translation by Meta

🔘 Speech-to-speech translation (S2ST)
🔘 Speech-to-text translation (S2TT)
🔘 Text-to-speech translation (T2ST)
🔘 Text-to-text translation (T2TT)
🔘 Automatic speech recognition (ASR)

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

💥MobileVLM💥
Strong and Open Vision Language Assistant for Mobile Devices

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

Build 💥LLM💥 (From Scratch)

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

Machine Learning and AI Beyond the Basics Book

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

Efficient Streaming Language Models with Attention Sinks

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GiHub_Link

Large Language Models Are Zero Shot Time Series Forecasters

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

Port of Suno AI's Bark in C/C++ for fast inference

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

whisper.cpp package for the Swift Package Manager

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

MMM: Generative Masked Motion Model

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

GMD: Controllable Human Motion Synthesis via Guided Diffusion Models

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link

YOLOv8.2.0 released by Ultralytics 🔥

💥New Features💥

🔘 New models: introduced support for YOLOv8-World, YOLOv8-World-v2 YOLOv9-C, and YOLOv9-E.

🔘 Performance optimizations: achieved 40% faster ultralytics imports faster batch same_shapes and immediate checkpoint serialization.

🔘 New features: added per-class object counting, and queue management utilities.

🔘 Enhanced export capabilities: improved export support, including OpenVINO 2023.3 updates, TensorRT 10 support, and fixes for TFLite, ONNX, and OpenVINO exports.

🔘 CI/CD improvements: enhanced Ultralytics Actions using OpenAI GPT-4 for PR summaries and introduced self-hosted Raspberry Pi 5 CI.

Join my channel:
👇👇👇👇👇👇
https://t.me/Artificial_Intelligence_Updates