A two-stage reasoning-segmentation method plus a new LLM-generated 3D dataset improves spatial reasoning in 3D multimodal large language models on several benchmarks.
Trajectoryformer: 3d object tracking transformer with predictive trajectory hypotheses
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
-
Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation
A two-stage reasoning-segmentation method plus a new LLM-generated 3D dataset improves spatial reasoning in 3D multimodal large language models on several benchmarks.