LLM2R: From Large Language Models to 3D Reassemblers
Overview
LLM2R is a new method for 3D part assembly that uses a pretrained decoder-only large language model (LLM) to predict the rigid SE(3) transformations of parts. It encodes parts into geometric tokens using a Point-BERT encoder and a Q-Former, then processes the sequence with a causal LLM adapted with LoRA. A learnable summary token block aggregates the entire assembly, and a part-aware pose head predicts rotation and translation. LLM2R achieves the highest part accuracy and success rate on PartNet categories, the best rotation and translation errors on PartNeXt, and the lowest translation error and fastest inference on Breaking Bad.
From arXiv Robotics — research abstracts
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Evidence dependency changes (3)
- 2026-10-30T23:04:21.650Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T23:04:02.058Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-15T19:20:36.551Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalLLM2R: From Large Language Models to 3D Reassemblers
LLM2R is a new method for 3D part assembly that uses a pretrained decoder-only large language model (LLM) to predict the rigid SE(3) transformations of parts. It encodes parts into geometric tokens using a Point-BERT encoder and a Q-Former, then processes the sequence with a causal LLM adapted with LoRA. A learnable summary token block aggregates the entire assembly, and a part-aware pose head predicts rotation and translation. LLM2R achieves the highest part accuracy and success rate on PartNet categories, the best rotation and translation errors on PartNeXt, and the lowest translation error and fastest inference on Breaking Bad.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).