Search the whole AI landscape.

PE

PerceptionDLM

Model · ByteDance

1

Diffusion-based vision-language model from PKU MSALab and ByteDance that captions multiple image regions in parallel.

2B-parameter open-weights video-language model that writes scene descriptions and timestamped event captions.

MO

Mobius

Model

1

Unified motion-language model for text-to-motion, motion captioning, completion and editing, from HKUST and Tencent Games.

Google DeepMind research model that transcribes sign language from video into text captions.

MI

MiDashengLM-Gen

Model · Xiaomi

1

Xiaomi's LLM-driven model that generates mixed audio scenes (speech, music, SFX, ambience) from structured text captions.

MS

Microsoft Streaming Transcription Model

Model · Microsoft

1

Microsoft AI's streaming speech-to-text model for near real-time transcription, succeeded by MAI Transcribe 2.

SL

Sign language to text model

Model · Google DeepMind

1

Google DeepMind model that translates sign language from a phone camera into text, starting with American Sign Language.