AI News Stylus: An AI Tool that Automatically Finds and Adds the Best Adapters (LoRAs, Textual Inversions, Hypernetworks) to Stable Diffusion based on Your Prompt May 10, 20243 min read
AI News Researchers at NVIDIA AI Introduce ‘VILA’: A Vision Language Model that can Reason Among Multiple Images, Learn in Context, and Even Understand Videos May 5, 20243 min read
AI News InternVL 1.5 Advances Multimodal AI with High-Resolution and Bilingual Capabilities in Open-Source Models Apr 30, 20243 min read
AI News Google AI Proposes MathWriting: Transforming Handwritten Mathematical Expression Recognition with Extensive Human-Written and Synthetic Dataset Integration and Enhanced Model Training Apr 25, 20243 min read
AI News Researchers at Microsoft Introduces VASA-1: Transforming Realism in Talking Face Generation with Audio-Driven Innovation Apr 20, 20243 min read
AI News OmniFusion: Revolutionizing AI with Multimodal Architectures for Enhanced Textual and Visual Data Integration and Superior VQA Performance Apr 15, 20243 min read
AI News Sigma: Changing AI Perception with Multi-Modal Semantic Segmentation through a Siamese Mamba Network for Enhanced Environmental Understanding Apr 10, 20243 min read
AI News This AI Paper from China Proposes a Novel Architecture Named-ViTAR (Vision Transformer with Any Resolution) Apr 5, 20242 min read
AI News NVIDIA AI Research Proposes Language Instructed Temporal-Localization Assistant (LITA), which Enables Accurate Temporal Localization Using Video LLMs Mar 31, 20243 min read
AI News MathVerse: An All-Around Visual Math Benchmark Designed for an Equitable and In-Depth Evaluation of Multi-modal Large Language Models (MLLMs) Mar 26, 20242 min read
AI News Researchers from Stanford and Google AI Introduce MELON: An AI Technique that can Determine Object-Centric Camera Poses Entirely from Scratch while Reconstructing the Object in 3D Mar 21, 20242 min read
AI News Synth2: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings by Researchers from Google DeepMind Mar 16, 20242 min read
AI News Revolutionizing Robotic Surgery with Neural Networks: Overcoming Catastrophic Forgetting through Privacy-Preserving Continual Learning in Semantic Segmentation Mar 11, 20243 min read
