ByteDance Open-Sources Bernini, a Unified Framework for AI Video Editing★ 74
量子位 QbitAI5 days agoReleaseByteDance’s commercial technology team has open-sourced Bernini, a unified framework for AI video generation and editing. Its design separates semantic planning from visual rendering: an MLLM-based planner understands text, source videos, images, and video references, then a DiT-based renderer produces the final video. The released Bernini-R includes inference code and weights, while the full planner-enabled version is still being prepared.
Google 全新「任意對任意」AI 模型 Gemini Omni 實測：效果驚人且近乎無縫★ 85
The Verge AI22 days agoReleaseGoogle recently unveiled a brand-new "anything-to-anything" multimodal AI model — Gemini Omni — whose powerful cross-modal generation and transformation…
Google I/O 2026 重磅發布：Gemini 3.5 Flash、Omni (NanoBanana 影片模型)、Spark 背景 Agent 與 Antigravity 2.0★ 85
Latent Space25 days agoReleaseIn the latest issue of Latent Space AINews, the major announcements from Google I/O 2026 were covered in depth. Google demonstrated its formidable R&D and…
Gemini 推出全新音樂創作功能：整合 Lyria 3 模型，支援文字與圖片生成 30 秒音樂★ 78
Google DeepMind Blog116 days agoReleaseGoogle DeepMind announced today (February 18, 2026) that its popular AI assistant application Gemini has officially integrated its most advanced music…
Google DeepMind 發表全新一代 Gemini 3：開啟主動式 AI 與超強推理的全新智能時代★ 98
Google DeepMind Blog208 days agoReleaseGoogle DeepMind officially unveiled its latest flagship AI model — Gemini 3 — in November 2025. This marks a new milestone for Google in the field of…
Hugging Face 推出 AI Sheets 影像功能：用試算表輕鬆解鎖批次影像處理與多模態分析
Hugging Face Blog236 days agoNew ToolHugging Face has recently released a major update for its innovative spreadsheet AI tool "AI Sheets," officially unlocking powerful image processing…