High-noise SNR training lifts layout adherence in flow-matching models
Shifting training toward high noise raised synthetic layout adherence from 25.9% to 80.8% and COCO Average Precision from 1.0 to 57.3.
Stories per day · 30 days
Relatedace-brain1embodied-ai1flow-matching1flux1grpo1image-evaluation1image-generation1image-synthesis1multimodal1qwen1snr1viescore21vlm1
3 stories, newest first · one card per story
Stories tagged #spatial-grounding
ACE-Brain-0.6 fine-tune beats GPT-6 Astra on four grounding benchmarks
Fine-tuning Qwen3.5-9B on about 1.5 million samples scored 75.41 versus Astra's 73.68.
VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations
VIEScore2 scores generated images and localizes defects on a grid, beating Gemini-3-Flash on correlation.