Unknown
AI researcher commenting on Vidi2's benchmark-beating performance versus competitors
How media typically covers Anna Zhang
Directly quoted in these articles
ByteDance's Vidi2 multimodal video model outperforms GPT-5 and Gemini 3 Pro on video understanding benchmarks, enabling temporal retrieval, spatio-temporal grounding, and intelligent video editing for videos up to 30 minutes long.
“AI researcher commenting on Vidi2's benchmark-beating performance versus competitors”