AI News Meta AI Introduces Token-Shuffle: A Simple AI Approach to Reducing Image Tokens in Transformers Apr 27, 20253 min read
AI News Long-Context Multimodal Understanding No Longer Requires Massive Models: NVIDIA AI Introduces Eagle 2.5, a Generalist Vision-Language Model that Matches GPT-4o on Video Tasks Using Just 8B Parameters Apr 22, 20254 min read
AI News Advancing Vision-Language Reward Models: Challenges, Benchmarks, and the Role of Process-Supervised Learning Apr 7, 20253 min read
AI News VideoMind: A Role-Based Agent for Temporal-Grounded Video Understanding Apr 2, 20253 min read
AI News TokenBridge: Bridging The Gap Between Continuous and Discrete Token Representations In Visual Generation Mar 28, 20253 min read
AI News IBM and Hugging Face Researchers Release SmolDocling: A 256M Open-Source Vision Language Model for Complete Document OCR Mar 23, 20253 min read
AI News This AI Paper Introduces R1-Onevision: A Cross-Modal Formalization Model for Advancing Multimodal Reasoning and Structured Visual Interpretation Mar 18, 20253 min read
AI News STORM (Spatiotemporal TOken Reduction for Multimodal LLMs): A Novel AI Architecture Incorporating a Dedicated Temporal Encoder between the Image Encoder and the LLM Mar 13, 20253 min read
AI News Salesforce AI Proposes ViUniT (Visual Unit Testing): An AI Framework to Improve the Reliability of Visual Programs by Automatically Generating Unit Tests by Leveraging LLMs and Diffusion Models Mar 8, 20254 min read
AI News This AI Paper Introduces UniTok: A Unified Visual Tokenizer for Enhancing Multimodal Generation and Understanding Mar 3, 20254 min read
AI News Google DeepMind Research Releases SigLIP2: A Family of New Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Feb 26, 20254 min read
AI News Microsoft Researchers Present Magma: A Multimodal AI Model Integrating Vision, Language, and Action for Advanced Robotics, UI Navigation, and Intelligent Decision-Making Feb 21, 20254 min read
AI News LLMDet: How Large Language Models Enhance Open-Vocabulary Object Detection Feb 16, 20253 min read
