Liquid AI releases experimental d1-omni-600M multimodal model
Overview
Liquid AI has released d1-omni-600M, an experimental 600M-parameter model that handles text plus image or audio input.
It combines LFM2.5-Encoder-350M with vision and audio encoders and leads the company's text benchmark comparison on toxicity detection and paraphrase identification. The post suggests uses such as voice-command routing, on-device moderation, and intent classification.
Written by AI from one article, by Liquid AI
Check the sources:
Article timeline
Follow the coverage from different perspectives. Times are ET.
- Liquid AILiquid AI releases d1-omni-600M, a 600M multimodal model for on-device tasks.
AILiquid AI has released d1-omni-600M, an experimental 600M-parameter model that handles text plus image or audio input. It combines LFM2.5-Encoder-350M with vision and audio encoders and leads the company's text benchmark comparison on toxicity detection and paraphrase identification. The post suggests uses such as voice-command routing, on-device moderation, and intent classification.
Heat trend
Not enough continuous observations to show a trend yet.