LLM2R: From Large Language Models to 3D Reassemblers

cs.CV, cs.AI, cs.RO

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: 20 pages, 5 figures, 7 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Memory Transformer
• Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following
• CRAG: Can 3D Generative Models Help 3D Assembly?
• PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding
• Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes
• Qwen3 Technical Report
• ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models