GTR: Gated Token Recurrence for Efficient Dense Prediction
GTR introduces a softmax-free recurrent vision backbone reaching 58.9 box AP on COCO with sub-2ms latency, targeting high-resolution dense prediction and edge deployment.
Stories per day · 30 days
2 RSS
3 stories, newest first · one card per story
Stories tagged #edge-deployment
PrismML Releases Ternary Bonsai 2 27B: A 5.9 GB Apache 2.0 Model Retaining 98.2% of Qwen3.8 27B Performance
PrismML released Ternary Bonsai 2 27B, a 5.93 GB Apache 2.0 ternary-weight model retaining 98.2% of Qwen3.8 27B's benchmark performance.
15
Retention-Constrained Post-Training Quantization of Cellpose-SAM for Stem Cell Microscopy
Quantization study shows W8A16 and mixed W4/W8 preserve Cellpose-SAM segmentation on stem-cell microscopy, while ternary quantization fails on 169 of 176 fields.