Artificial Intelligence l l AI Updates

🔗 GitHub_Link HydraTutorial at AutoML Fall School 2023 Join my channel: 👇👇👇👇👇👇 https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link SMARTS (Scalable Multi-Agent Reinforcement Learning Training School) is a simulation platform for multi-agent reinforcement learning (RL) and research on 💥 autonomous driving 💥 Join my channel: 👇👇👇👇👇👇 https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link VanillaNet is an innovative neural network architecture that focuses on simplicity and efficiency. Moving away from complex features such as shortcuts and attention mechanisms, VanillaNet uses a reduced number of layers while still maintaining excellent performance. This project showcases that it's possible to achieve effective results with a lean architecture, thereby setting a new path in the field of computer vision and challenging the status quo of foundation models. Join my channel: 👇👇👇👇👇👇 https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link LLMTuner: 💥Fine-Tune Llama💥, Whisper, and other LLMs with best practices like LoRA, QLoRA, through a sleek, scikit-learn-inspired interface. Join my channel to stay updated! 👇👇👇👇👇👇 https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link Official PyTorch implementation of "Contrastive Denoising Score(CDS) for Text-guided Latent Diffusion Image Editing" Stay updated on the latest and most exciting AI news! Join my channel for a firsthand look at groundbreaking innovations: 👇👇👇👇👇👇 https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models Stay updated on the latest and most exciting AI news! Join my channel for a firsthand look at groundbreaking innovations: 👇👇👇👇👇👇 https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link Official Pytorch implementation of "Visual Style Prompting with Swapping Self-Attention" Stay updated on the latest and most exciting AI news! Join my channel for a firsthand look at groundbreaking innovations: 👇👇👇👇👇👇 https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models 🚀 Join the journey on my Telegram channel for more intriguing insights: 👇👇👇👇👇👇 https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering Stay updated on the latest and most exciting AI news! Join my channel for a firsthand look at groundbreaking innovations: 👇👇👇👇👇👇 https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link Domain Expansion of Image Generators offers a groundbreaking perspective on enhancing pretrained generative models. The ability to seamlessly integrate numerous new domains while preserving the original knowledge presents a transformative approach to model versatility and efficiency, potentially reshaping the landscape of generative model applications. 🚀 Join the journey on my Telegram channel for more intriguing insights: 👇👇👇👇👇 https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link DreamCraft3D pioneers a groundbreaking approach to 3D content generation, overcoming consistency challenges with innovative techniques like score distillation and Bootstrapped Score Distillation. The alternating optimization strategy showcases a synergistic relationship between 3D scene representation and diffusion models, resulting in remarkable photorealistic renderings and a noteworthy leap in the state-of-the-art. Stay updated on the latest and most exciting AI news! Join my channel for a firsthand look at groundbreaking innovations: 👇👇👇👇👇👇 https://t.me/Artificial_Intelligence_Updates

🔗GitHub_Link 🔗Tutorial_Link OpenNLPLab team is re-inventing the Large Language Model (LLM), and released an official implementation of TransNormerLLM. The opened weights of TransNormerLLM are now accessible to individuals, creators, researchers and businesses of all sizes so that they can experiment, innovate and scale their ideas responsibly. Another beneficial point is that release contains the TransNormerLLM model implementation, the open-source weights and the starting code for Supervised 💥Fine-tuning💥 (SFT). Stay updated on the latest and most exciting AI news! Join my channel for a firsthand look at groundbreaking innovations: 👇👇👇👇👇👇 https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link Exploring the fascinating world of text-based colorization! Uncover the magic of adding vibrant hues to images using descriptive text cues. Dive into the realm where words bring colors to life, making the ordinary extraordinary. 🚀 Join the journey on my Telegram channel for more intriguing insights: 👇👇👇👇👇 https://t.me/Artificial_Intelligence_Updates

🔗 GitHub_Link ExposureDiffusion: Learning to Expose for Low-light Image Enhancement

🔗 GitHub_Link Collection of recent deep learning based compression works, e.g., image/video compression

🔗 GitHub_Link iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer.

🔗 GitHub_Link StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On

🔗 GitHub_Link AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head

🔗 GitHub_Link Stable Diffusion Web UI Pixelization #pixelization #StableDiffusion

TripoSR is on of the state-of-the-art open-source models. It is a fast feedforward 3D reconstruction from a single image, collaboratively developed by Tripo AI and Stability AI. #3D-reconstruction