Ming-Shu Chen

The DeepSeek-V4.1-Flash model, a multimodal Mixture-of-Experts model with 552B backbone parameters and support for contexts of up to one million tokens, is introduced, substantially improving cost efficiency for agentic workloads and pushing the limits of KV cache compression.

MOSS-VL achieves a staggering 66.0 average score in proactive alerting, far surpassing the best baseline by nearly 30 points.

MOSS-Audio achieves state-of-the-art performance in audio understanding tasks by effectively integrating temporal cues and deep acoustic features, setting a new benchmark for audio-language models.

Achieve controllable and scalable speech generation with MOSS-TTS, enabling zero-shot voice cloning and long-form synthesis.

A purely Transformer-based audio tokenizer, pre-trained on 3M hours of data, leapfrogs existing codecs and even enables a fully autoregressive TTS model to outperform cascaded systems.

Open-source MOVA lets you generate synchronized, high-quality video and audio—including realistic lip sync—without relying on closed-source systems.