Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
RefCOCO+
anchor
Findings
IC-163
LLaVA-1.5, LLaVA-Next, and GPT-4V show near-zero accuracy on GUI grounding benchmarks while achieving 50-85 on general image grounding (RefCOCO+), indicating a failure mode specific to GUI grounding scenarios
[eval]
IC-236
Zero-shot Grounding-DINO and Florence-2 show a significant performance gap on referring expression comprehension compared to their fine-tuned versions
[eval]
IC-237
A zero-shot Llama 3 8B, when prompted to select the best bounding box from VLM candidates without fine-tuning, produces results nearly identical to the VLM alone
[eval]