List your company

Visual Grounding on RefExp

97AccuracyPLC
-2.73623.15749.0574.943Oct 7, 2022May 11, 2023Dec 13, 2023Jul 17, 2024Feb 18, 2025Sep 22, 2025Apr 27, 2026

Evaluation results

MethodLinks
PLCInput type=Pipelined2022.1097—
VUTInput type=Pipelined, Android view hierarchy=true2022.1094.8—
Pix2Struct-LargeInput type=Pixel-only, Scale=Large2022.1094.2—
Pix2Struct-BaseInput type=Pixel-only, Scale=Base2022.1092.2—
UI BertInput type=Pipelined, Android view hierarchy=true2022.1090.8—
AguvisSize=8B, TTFT ↓ (ms)=119.7, TPOT ↓ (ms/token)=21.22026.0480.9—
GoClick-LSize=0.8B, TTFT ↓ (ms)=91.1, TPOT ↓ (ms/token)=8.32026.0478.2—
OS-ATLAS-4BSize=4B, TTFT ↓ (ms)=137.3, TPOT ↓ (ms/token)=31.42026.0477.1—
UGroundSize=7B, TTFT ↓ (ms)=1034.6, TPOT ↓ (ms/token)=27.92026.0473.6—
GoClick-BSize=0.2B, TTFT ↓ (ms)=37.7, TPOT ↓ (ms/token)=4.12026.0471.9—
OS-ATLAS-8BSize=8B, TTFT ↓ (ms)=137.5, TPOT ↓ (ms/token)=19.92026.0466.5—
Qwen2VL-7BSize=8B, TTFT ↓ (ms)=118.9, TPOT ↓ (ms/token)=21.22026.0464.8—
ShowUISize=2B, TTFT ↓ (ms)=79.7, TPOT ↓ (ms/token)=14.72026.0458.4—
SeeClickSize=10B, TTFT ↓ (ms)=160.4, TPOT ↓ (ms/token)=184.42026.0458.1—
CogAgentSize=18B, TTFT ↓ (ms)=1253.2, TPOT ↓ (ms/token)=208.82026.0435—
Qwen2-VLSize=2B, TTFT ↓ (ms)=58.8, TPOT ↓ (ms/token)=16.42026.0429.2—
GPT-4o2026.0421.8—
Ferret-UISize=8B, TTFT ↓ (ms)=152.5, TPOT ↓ (ms/token)=22.92026.045.5—
Ferret-UISize=3B, TTFT ↓ (ms)=69.5, TPOT ↓ (ms/token)=9.82026.041.1—
CLIP2025.12—13.15
GeoRSCLIP2025.12—8.25
RemoteCLIP2025.12—4.35
SkyCLIP2025.12—11.85
VLM2GeoVecEvaluation Protocol=In-distribution2025.12—32.5
VLM2Vec2025.12—6.65