HiDream.ai founder Mei Tao used the World Laureates Forum to propose 'Agentic Omnimodal World Models,' arguing that the LLM, multimodal and embodied model tracks will ultimately converge, with an LLM as the decision brain and an omni-model as the world simulator. The vision is backed by the HiDream-O1 model family and HiHarness platform, with applications sketched in embodied data synthesis and life sciences, but it remains a high-level framework without verifiable technical detail or quantitative results.
Omnimodal Model
全模态模型
A model capable of processing and understanding multiple modalities like text, images, and audio within a single architecture.
Curated Intelligence
AMD has officially acquired Fei-Fei Li's spatial intelligence startup World Labs for $8.2 billion. The deal integrates the Atlas omni-model architecture to address sparse reconstruction challenges in robotics and design, bolstering AMD's vertical integration in spatial computing and AI infrastructure.
Alibaba's Tongyi Qianwen team released Qwen3.8-Omni-Flash, a new native omni-modal model focused on enhancing agentic planning and tool use in audio-video scenarios. Supporting 1M context length, it achieves over 25% average score improvement across 29 benchmarks compared to its predecessor, while reducing API audio input costs by more than 98%, significantly lowering the barrier for multimodal agent deployment.
OpenAI has released a system card addendum detailing the native image generation capabilities of GPT-4o. Embedded within the omnimodal architecture, this feature offers superior instruction following, text rendering, and image transformation compared to DALL·E 3. The document primarily addresses marginal risks introduced by these new capabilities and outlines the safety mitigations implemented.