UniSpark-9B multimodal model released, supporting visual question answering and text-to-image generation
Start here
UniSpark-9B model is proposed, with approximately 9B parameters, combining full attention with GatedDeltaNet linear attention, supporting visual question answering, text-to-image generation, instruction editing, and interleaved image-text prediction, scoring 2470.3 on MME-S and 0.83 on GenEval. The training data includes 159.7M generation samples, 213.4M understanding samples, and 624.8K interleaved sequences.
Written by AI from the reports · updated 6 days ago
Report timeline
Follow the reports to see the event from other sides.
- Hugging Face Daily PapersUniSpark: Exploring Hybrid Attention for Multimodal Understanding and Generation
UniSpark-9B is proposed, a multimodal model with approximately 9B parameters, combining full attention with GatedDeltaNet linear attention, supporting visual question answering, text-to-image generation, instruction editing, and interleaved image-text prediction. It scores 2470.3 on MME-S and 0.83 on GenEval. The training data includes 159.7M generation samples, 213.4M understanding samples, and 624.8K interleaved sequences.
Heat trend for this event
- Current
- 3
- Peak
- 4Nov 13 14:00
- 24h change
- –
The trend compares only sources observed the whole time, so the range may be smaller than the current heat figure. Hover or tap the chart for each hour. Left and right arrow keys move through it.