3D-R1 uses a synthetic chain-of-thought cold start plus GRPO reinforcement learning with perception, semantic, and format rewards, and reports best published results across 3D dense captioning, QA, grounding, dialogue, reasoning, and planning.
Title resolution pending
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
-
3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding
3D-R1 uses a synthetic chain-of-thought cold start plus GRPO reinforcement learning with perception, semantic, and format rewards, and reports best published results across 3D dense captioning, QA, grounding, dialogue, reasoning, and planning.