TinyGiantVLM, a 64M-parameter RGB-D vision-language model with two-phase training, reached 5th place on the AI City Challenge 2025 warehouse spatial reasoning track.
Jordan and Robert A
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TinyGiantVLM: A Lightweight Vision-Language Architecture for Spatial Reasoning under Resource Constraints
TinyGiantVLM, a 64M-parameter RGB-D vision-language model with two-phase training, reached 5th place on the AI City Challenge 2025 warehouse spatial reasoning track.