AI News This AI Paper Introduces MAETok: A Masked Autoencoder-Based Tokenizer for Efficient Diffusion Models Feb 10, 20253 min read
AI News ByteDance Proposes OmniHuman-1: An End-to-End Multimodality Framework Generating Human Videos based on a Single Human Image and Motion Signals Feb 5, 20253 min read
AI News Introducing GS-LoRA++: A Novel Approach to Machine Unlearning for Vision Tasks Jan 26, 20253 min read
AI News Content-Adaptive Tokenizer (CAT): An Image Tokenizer that Adapts Token Count based on Image Complexity, Offering Flexible 8x, 16x, or 32x Compression Jan 11, 20253 min read
AI News ByteDance Research Introduces 1.58-bit FLUX: A New AI Approach that Gets 99.5% of the Transformer Parameters Quantized to 1.58 bits Jan 1, 20252 min read
AI News Microsoft and Tsinghua University Researchers Introduce Distilled Decoding: A New Method for Accelerating Image Generation in Autoregressive Models without Quality Loss Dec 27, 20244 min read
AI News Meta AI Releases Apollo: A New Family of Video-LMMs Large Multimodal Models for Video Understanding Dec 22, 20243 min read
AI News Microsoft AI Research Introduces OLA-VLM: A Vision-Centric Approach to Optimizing Multimodal Large Language Models Dec 17, 20244 min read
AI News ByteDance Introduces Infinity: An Autoregressive Model with Bitwise Modeling for High-Resolution Image Synthesis Dec 12, 20243 min read
AI News Google DeepMind Just Released PaliGemma 2: A New Family of Open-Weight Vision Language Models (3B, 10B and 28B) Dec 7, 20243 min read
AI News ShowUI: A Vision-Language-Action Model for GUI Visual Agents that Addresses Key Challenges in UI Visual and Action Modeling Dec 2, 20244 min read
AI News Researchers from NVIDIA and MIT Present SANA: An Efficient High-Resolution Image Synthesis Pipeline that Could Generate 4K Images from a Laptop Nov 27, 20244 min read
