博客

SeedRealtime 音视频全双工大模型发布：走向全模态自然交互

SeedRealtime 音视频全双工大模型发布：走向全模态自然交互

作为原生音视频全双工大模型，联合理解声音、画面与时序信息，带来边看、边听、边说的自然交互体验

了解更多

一镜成片，随心参考｜Seedance 2.5 正式发布

30 秒长叙事，多模态参考能力、编辑能力全面升级

2026.07.31

从“会说”走向“会创作”｜ Seed Audio 1.0 音频创作模型发布

统一框架下联合建模人声、音效和环境声等音频要素

2026.07.20

不止“生成”，更懂“设计” ｜ Seedream 5.0 Pro 发布

具备智能思考能力、支持高效创作和生产的多模态图像生成模型

2026.07.08

EdgeBench：衡量真实世界环境学习，发现新 Scaling Law

Agent 在环境学习中表现出明显的 log-sigmoid 规律

2026.07.07

精选论文

2026.07.06EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments2026.06.30Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity2026.05.29Task-Focused Memorization for Multimodal Agents2026.05.16Charon: A Unified and Fine-Grained Simulator for Large-Scale LLM Training and Inference2026.04.26MegaScale-Omni: A Hyper-Scale, Workload-Resilient System for MultiModal LLM Training in Production2026.04.22Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation2026.04.15Seedance 2.0: Advancing Video Generation for World Complexity2026.04.11Protenix-v2: Broadening the Reach of Structure Prediction and Biomolecular Design2026.01.27Post-LayerNorm Is Back: Stable, ExpressivE, and Deep2025.12.02GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation