AIBullisharXiv – CS AI · 10h ago7/10
🧠
Flame3D: Zero-shot Compositional Reasoning of 3D Scenes with Agentic Language Models
Flame3D introduces a training-free framework that enables large language models to reason about 3D scenes compositionally without requiring 3D-specific training data. The system represents scenes as editable visual-textual memories and allows agents to synthesize custom spatial programs at inference time, achieving competitive results on existing benchmarks while opening new possibilities for multi-hop spatial reasoning.