arXiv 2610.18604 · cs.CV · 2026-10-13
LLM2R: From Large Language Models to 3D Reassemblers
Zhouhan Zhong, Qiuhong Shen, Xingyi Yang, Jinyi Xu, Xinchao Wang
National University of Singapore
在最新榜 #375 本站收录于 2026-10-24
一句话要点
新加坡国立大学的 LLM2R 把 3D 零件装配当作序列建模，用预训练的仅解码器大模型来做：Point-BERT 编码器加 Q-Former 把每个零件压成一组几何 token，所有零件一起输入，预测每个零件的刚体位姿，以应对零件很多时的整体推理。
NUS's LLM2R casts 3D part assembly as sequence modeling with a pretrained decoder-only LLM: a Point-BERT encoder and Q-Former compress each part into geometric tokens, and all parts are processed together to predict each part's rigid pose, scaling reasoning to objects with many parts.
阅读 arXiv 原文 PDF Hugging Face 讨论
主题与学科
同主题：视觉理解与 3D
- Spectral-Spatial Interpretation ▲753
- VisionHOPE: Visual Backbones as Self-Modifying Learning Systems ▲296
- EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience ▲189
- Holi-World: Building Holistic World Intelligence from Human-Ego Experience ▲172
- DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations ▲161
同主题：大语言模型
- Jeva: System One Models from First Principles 2026-10-13 · ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions 2026-09-24 · ▲273
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels 2026-10-22 · ▲247
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- OmniEdu: Open Foundation Models for Learning and Teaching 2026-09-19 · ▲240
同机构：National University of Singapore
- Toward Recursive Self-Improvement in Physical AI 2026-10-21
- Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? 2026-10-06
- FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation 2026-09-30
- MaLiang-Harness: A Programmable Path to Image and Video Generation 2026-09-28
- Agent Priors-guided Policy Learning 2026-09-28
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。