BREAKING
NVIDIA Open-Sources LocateAnything-3B
Parallel Box Decoding Replaces Token-by-Token
1
Old: sequential tokens
↓
2
PBD: one parallel step
↓
3
Lower latency
12.7 BPS on a Single H100
LocateAnything-3B
12.7
Rex-Omni
5
Qwen3-VL
1.1
0
%
LVIS F1 vs Rex-Omni
0
%
COCO mean F1
0
ScreenSpot-Pro SOTA
One Model, Many Tasks
Capabilities
●
Open-vocab detection
●
GUI and OCR grounding
●
Document layout parsing
Notes
●
Research-only license
●
Eagle VLM family
●
Runs on consumer GPUs
Lightweight, Fast Detection Goes Open
AI NEWS BLITZ
NVIDIA has released a 3-billion-parameter detection model that locates anything from text.