Search

Tag: #multimodal-ai55 results

蘋果 AirPods AI 相機即將量產

根據 Mark Gurman 報導，蘋果配相機的 AirPods 即將進入初期量產測試。原型機處於設計驗證階段，可提供低解析視覺輸入給 Siri，例如從食材建議食譜。不用於拍照而是情境 AI 輔助。

The VergeMedia•May 7#wearables#multimodal-ai#vision-input

Nothing 計畫 AI 眼鏡與耳機

Nothing 據報將推出內建相機的 AI 智慧眼鏡。搭配 AI 驅動耳機。盼設計透明並以招牌風格發光。

Digital TrendsMedia•Mar 31#ai-glasses#wearables#multimodal-ai

ChatGPT 語音模式證明真正有用

作者先前因捏造答案而忽略 ChatGPT 語音模式。最近測試發現 7 種真正有用的應用。語音模式在準確性和實用性上大幅改善。

ZDNet AIMedia•Mar 10#voice-interaction#productivity-tools#multimodal-ai

BrowseComp-V³ Benchmark for Multimodal Agents

BrowseComp-V³ is a new benchmark with 300 challenging questions for evaluating multimodal browsing agents on deep multi-hop reasoning across text and visuals. It features subgoal-driven process evaluation and publicly searchable evidence for reproducibility. Experiments reveal state-of-the-art models achieve only 36% accuracy, highlighting integration bottlenecks.

ArXiv AIResearch•Feb 16#research#browsecomp#multimodal-ai

GameDevBench Evaluates Game Dev Agents

GameDevBench offers 132 multimodal game development tasks from tutorials. Agents struggle, with top solving 54.5%; tasks demand code and asset handling. Simple image/video feedback improves performance up to 47.7%.

ArXiv AIResearch•Feb 12#research#gamedevbench#v1