AI News Unveiling EVA-CLIP-18B: A Leap Forward in Open-Source Vision and Multimodal AI Models Feb 16, 20243 min read
AI News Salesforce AI Researchers Propose BootPIG: A Novel Architecture that Allows a User to Provide Reference Images of an Object in Order to Guide the Appearance of a Concept in the Generated Images Feb 15, 20243 min read
AI News Meet EscherNet: A Multi-View Conditioned Diffusion Model for View Synthesis Feb 14, 20242 min read
AI News This AI Paper from China Introduce InternLM-XComposer2: A Cutting-Edge Vision-Language Model Excelling in Free-Form Text-Image Composition and Comprehension Feb 14, 20242 min read
AI News Meet MouSi: A Novel PolyVisual System that Closely Mirrors the Complex and Multi-Dimensional Nature of Biological Visual Processing Feb 13, 20243 min read
AI News This AI Paper Proposes Two Types of Convolution, Pixel Difference Convolution (PDC) and Binary Pixel Difference Convolution (Bi-PDC), to Enhance the Representation Capacity of Convolutional Neural Network CNNs Feb 13, 20244 min read
AI News Advancing Vision-Language Models: A Survey by Huawei Technologies Researchers in Overcoming Hallucination Challenges Feb 12, 20243 min read
AI News Pinterest Researchers Present an Effective Scalable Algorithm to Improve Diffusion Models Using Reinforcement Learning (RL) Feb 12, 20243 min read
AI News Microsoft Researchers Introduce StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis Feb 6, 20243 min read
AI News TikTok Researchers Introduce ‘Depth Anything’: A Highly Practical Solution for Robust Monocular Depth Estimation Feb 6, 20243 min read
AI News Meet CompAgent: A Training-Free AI Approach for Compositional Text-to-Image Generation with a Large Language Model (LLM) Agent as its Core Feb 5, 20242 min read
AI News Researchers from ETH Zurich and Microsoft Introduce EgoGen: A New Synthetic Data Generator that can Produce Accurate and Rich Ground-Truth Training Data for EgoCentric Perception Tasks Feb 5, 20242 min read
