AI News Microsoft Research Introduces Reducio-DiT: Enhancing Video Generation Efficiency with Advanced Compression Nov 21, 20243 min read
AI News Researchers from Bloomberg and UNC Chapel Hill Introduce M3DocRAG: A Novel Multi-Modal RAG Framework that Flexibly Accommodates Various Document Context Nov 11, 20244 min read
AI News Meta AI Introduces AdaCache: A Training-Free Method to Accelerate Video Diffusion Transformers (DiTs) Nov 6, 20244 min read
AI News Meta AI Releases LongVU: A Multimodal Large Language Model that can Address the Significant Challenge of Long Video Understanding Nov 1, 20244 min read
AI News SAM2Long: A Training-Free Enhancement to SAM 2 for Long-Term Video Segmentation Oct 27, 20243 min read
AI News LongAlign: A Segment-Level Encoding Method to Enhance Long-Text to Image Generation Oct 22, 20244 min read
AI News Meissonic: A Non-Autoregressive Mask Image Modeling Text-to-Image Synthesis Model that can Generate High-Resolution Images Oct 17, 20243 min read
AI News Researchers at Stanford University Propose ExPLoRA: A Highly Effective AI Technique to Improve Transfer Learning of Pre-Trained Vision Transformers (ViTs) Under Domain Shifts Oct 12, 20243 min read
AI News Lotus: A Diffusion-based Visual Foundation Model for Dense Geometry Prediction Oct 7, 20243 min read
AI News Microsoft Researchers Unveil RadEdit: Stress-testing Biomedical Vision Models via Diffusion Image Editing to Eliminate Dataset Bias Oct 2, 20243 min read
AI News Is Scaling the Only Path to AI Supremacy? This AI Paper Unveils ‘Phantom of Latent for Large Language and Vision Models Sep 27, 20243 min read
AI News ByteDance Researchers Release InfiMM-WebMath-40B: An Open Multimodal Dataset Designed for Complex Mathematical Reasoning Sep 22, 20244 min read
