AI RESEARCH
Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs
arXiv CS.AI
•
ArXi:2606.01215v1 Announce Type: cross Current 3D spatial reasoning methods face a fundamental trade-off: neuro-symbolic 3D (NS3D) concept learners achieve interpretable reasoning through compositional programs but are constrained to closed-set concept vocabularies and simple programs; end-to-end 3D multi-modal LLMs (3D MLLMs) could handle complex natural language and open-vocabulary concepts but suffer from black-box reasoning without explicit spatial verification. We