Mk1.5 adds video localization, expands into audio and audio-visual understanding
AkshatS07 · x · 2026-09-25
Version Mk1.5 expands perceptual understanding across modalities and fidelity: it adds video localization and extends into audio and audio-visual understanding. The team also shows improved egocentric understanding, reasoning, and cross-embodiment applications, with demos available on their blog.
Related event: Mk1.5 Real-Time Multimodal Reasoning Model Launches with 2-5x Lower Latency(4 posts)→
More from Multimodal
- Claude Opus 5.5 stuns at motion video: creates electronic remix of a classic song, beat-synced — op7418 · 2026-09-26
- Opus 5.5 One-Shots an Entire SaaS Intro Video for $7, Sparking Designer Job Fears — nidhanshusharma · 2026-09-26
- Open-source reshaker turns Claude Code into a podcast studio that clones hosts and auto-cuts episodes — LeviTurk · 2026-09-26
- Qwen3-TTS Hits SageMaker JumpStart: Zero-Shot Voice Cloning From Seconds of Audio — AWS ML Blog · 2026-09-26
- AI Series Account MeanOrangeCat Teams With Showrunner for New Adventure Season — charis_ai · 2026-09-26
- Choreographer Uses Suno v6 to Turn Movement Into Music in Debut Music Video — suno · 2026-09-26