Category: Multimodal AI

• Abandoning Manual Annotation! Chinese Team Proposes Self-Evolution Algorithm for Multimodal Large Models
• Xiaohongshu Open-Sources First Multimodal Large Model, dots.vlm1, Performance Rivals SOTA!
• Do Multimodal Large Language Models Truly 'Understand' the World? — Unveiling Core Knowledge Deficits in MLLMs
• The More Reasoning, The More Hallucinations? The "Hallucination Paradox" of Multimodal Reasoning Models
• Say Less 'Wait', Do More: NoWait Reshapes Large Model Inference Paths
• Think While Drawing! Multimodal Reasoning Achieves Significant Improvement!
• R1-like Training No Longer Just Focuses on Result Correctness! CUHK Launches SophiaVL-R1 Model
• The First Multimodal Dedicated Slow-Thinking Framework! Outperforms GPT-o1 by Nearly 7 Percentage Points, Reinforcement Learning Teaches VLM to "Think Twice"
• OPA-DPO: An Efficient Solution for the Hallucination Problem in Multimodal Large Models
• Thinking with Images Only: Reinforcement Learning Forges a New Reasoning Model Paradigm, Maximizing Complex Scene Planning!
• More Capable Than Gemini Diffusion! The First Multimodal Large Diffusion Language Model MMaDA Released, Achieving Strong Reasoning and High Controllability
• Understanding RAG, Agent, and Multimodality: Industry Practices and Future Trends
• Multimodal Large Models Collectively Fail, GPT-4o Only 50% Safety Pass Rate: SIUO Reveals Cross-Modal Safety Blind Spots
• Interview with Step Ahead's Duan Nan: "We Might Be Touching the Upper Limit of Diffusion's Capability"
• Matches Claude 3.7 at 1/8th the Cost: "European OpenAI" Mistral AI Releases New Multimodal Model