AI News Meet Gen4Gen: A Semi-Automated Dataset Creation Pipeline Using Generative Models Mar 6, 20243 min read
AI News CMU Researchers Unveil Groundbreaking AI Method for Camera Pose Estimation: Harnessing Ray Diffusion for Enhanced 3D Reconstruction Mar 6, 20242 min read
AI News BigGait: Revolutionizing Gait Recognition with Unsupervised Learning and Large Vision Models Mar 5, 20243 min read
AI News Revolutionizing Image Quality Assessment: The Introduction of Co-Instruct and MICBench for Enhanced Visual Comparisons Mar 5, 20243 min read
AI News UC Berkeley Researchers Introduce the Touch-Vision-Language (TVL) Dataset for Multimodal Alignment Mar 4, 20243 min read
AI News Google AI Introduces VideoPrism: A General-Purpose Video Encoder that Tackles Diverse Video Understanding Tasks with a Single Frozen Model Mar 4, 20242 min read
AI News Harmonizing Vision and Language: Advancing Consistency in Unified Models with CocoCon Mar 3, 20243 min read
AI News Meet Swin3D++: An Enhanced AI Architecture based on Swin3D for Efficient Pretraining on Multi-Source 3D Point Clouds Mar 2, 20243 min read
AI News Meet CoLLaVO: KAIST’s AI Breakthrough in Vision Language Models Enhancing Object-Level Image Understanding Mar 1, 20243 min read
AI News Apple Researchers Propose MAD-Bench Benchmark to Overcome Hallucinations and Deceptive Prompts in Multimodal Large Language Models Mar 1, 20242 min read
AI News Revolutionizing 3D Scene Modeling with Generalized Exponential Splatting Feb 28, 20243 min read
AI News Meta Releases Aria Everyday Activities (AEA) Dataset: An Egocentric Multimodal Open Dataset Recorded Using Project Aria Glasses Feb 27, 20243 min read
AI News ByteDance Proposes Magic-Me: A New AI Framework for Video Generation with Customized Identity Feb 26, 20243 min read
