OpenAI
Multimodal AI Advances on Four Fronts in May 2025
Thinking Machines Lab previewed real-time interaction models for continuous audio and video input, while Perceptron released…
Thinking Machines Lab previewed real-time interaction models for continuous audio and video input, while Perceptron released…
Thinking Machines Lab previewed real-time multimodal interaction models, Perceptron released a video analysis model priced 80–90%…
Thinking Machines introduced real-time interaction models that process voice and video simultaneously, while Perceptron launched video…
Multimodal AI made significant strides this week with Thinking Machines previewing real-time interaction models and Perceptron…
AI models trained on different data types are converging toward identical internal representations of reality as…
Multimodal AI achieved major advances in May 2026, with Thinking Machines unveiling real-time interaction models for…