
Automatic Music Transcription (AMT) converts an audio recording into symbolic notes, usually MIDI. Single-instrument transcription already works reasonably well. However, transcribing a full multi-instrument mix stays difficult. Kyutai and Mirelo team now release MuScriptor to close that gap. It is an open-weight model trained on real, multi-instrument recordings across many genres. This article explains how MuScriptor works, what the benchmarks show, and how to run it. What is MuScriptor
Automatic music transcription converts audio recordings into symbolic musical notation, usually in MIDI format. While transcribing single instruments works reasonably well, transcribing full multi-instrument mixes has remained difficult. MuScriptor is an open-weight decoder-only transformer model designed to close this gap by converting audio into MIDI-like tokens for pitch, timing, and instrument through a three-stage training process using synthetic data, real recordings, and reinforcement learning. The model achieves significant improvements over existing baselines, with a Multi F1 score of 48.2 compared to 21.9 for the previous best system, and is released in three size variants with inference code and a web interface for practical use.

Robbyant, the embodied AI unit inside Ant Group, has released the LingBot-VA 2.0.The first embodied-native foundation model. It describes a video-action foundation model for generalist robot manipulation. The research team pretrains the whole stack for embodiment instead of fine-tuning a video generator. What is LingBot-VA 2.0? Most video-action models reuse two components built for digital content creation. One is a reconstruction-oriented VAE. The other is a bidirectional video-diffusio

Most wearable health models are built one outcome at a time. That approach breaks down at thirty-five endpoints. Labels are expensive and retrospective annotation is infeasible. Google Research introduced SensorFM, a foundation model for wearable health pre-trained on more than 1 trillion minutes of sensor data from 5 million people. https://arxiv.org/pdf/2605.22759 What is SensorFM? SensorFM is a Large Sensor foundation Model for wearable time-series representation learning. It ing
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on Maven