MegaParts, a scalable autoregressive 3D generation framework to address this challenge by combining structured sequence modeling with a token-efficient vector-quantized shape tokenizer, achieves higher mesh quality than baseline autoregressive and diffusion models and suggests that LLM native token-efficient autoregressive modeling is a compelling alternative to diffusion for large-scale part-aware 3D generation.
Abstract
Part-aware 3D object generation is essential for graphics applications such as controllable modeling, editing, and articulation, where objects are represented as coherent assemblies of semantic parts. However, existing part-aware generation methods, do not scale well to highly complex objects. As the number of parts increases, generating detailed geometry becomes prohibitively expensive in token length and memory. We introduce MegaParts, a scalable autoregressive 3D generation framework to address this challenge by combining structured sequence modeling with a token-efficient vector-quantized shape tokenizer. Our tokenizer learns discrete latent representations for part-level geometry by minimizing token usage subject to high-fidelity reconstruction, enabling adaptive-length tokenization based on geometric complexity. On top of this compact representation, we train a large language model to generate object bounding boxes, part bounding boxes, and part shape tokens within a unified structured sequence. Combined with efficient long-context training strategy, our token-efficient formulation scales to objects with up to 300 parts and sequence lengths up to 256k tokens. This substantially extends the scale of part-aware 3D generation while preserving compositional structure and enabling fine-grained part-level control. Our method achieves higher mesh quality than baseline autoregressive and diffusion models, showing that compressed discrete part tokens improve not only scalability but also the achievable fidelity of generated geometry. These results suggest that LLM native token-efficient autoregressive modeling is a compelling alternative to diffusion for large-scale part-aware 3D generation. The project page is available at https://expmaster.github.io/megaparts_webpage.
Large-model-based point-to-CAD generation holds immense potential for advancing industrial design and enhancing 3D modeling efficiency. However, most existing methods approach the problem as a general point-cloud encoding and token prediction task, neglecting the tokenization and supervision specifically for CAD-relate...
Jian Gao, Kai-Lin Bi, Jia-Min Xu et al.· 0 citations
Compact token sequences are essential for efficient 3D generation. However, existing 3D tokenizers typically organize latent representations either over spatial regions or as fixed-size sets of global tokens, both suffering sharp reconstruction degradation when compressed to extremely low token budgets. In this paper,...
Mingda Lin, Weijie Wang, Zeyu Zhang et al.· 0 citations
This work proposes a foundation-feature Gaussian driving world model that unifies scene understanding, language-grounded reasoning, controllable 4D editing, and multi-modal generation within a single framework and introduces a foundation-feature Gaussian tokenizer that directly distills Qwen/SigLIP visual-language feat...
Tianchen Deng, Xue-Feng Chen, Shuang Wu et al.· 0 citations
This work proposes a framework for detailed object-level reasoning across multiple objects with three components: MO3D, an instruction dataset requiring fine-grained multi-object comparison; Multi-3DLLM, using a minimal Patch-Interaction Transformer (PIT) that models inter-/intra-object relationships while preserving l...
K. Ide, Ryousuke Yamada, Yue Qiu et al.· 2026 IEEE/CVF Conference on...· 1 citation· ⚡1
UniPart, a feed-forward cross-modal 3D Transformer that conditions CLIP text embedding, is introduced, a feed-forward cross-modal 3D Transformer that achieves strong zero-shot results on open-vocabulary part benchmarks and transfers to language-conditioned part grasping in real world.
Xinqiang Yu, Zekun Qi, Jia-Wei He et al.· 0 citations
Text-guided 3D building generation holds tremendous application potential, yet existing generative models typically output inseparable single meshes or non-interactive rendered representations. While procedural modeling can generate editable buildings with hierarchical structures, rule authoring is laborious, and even...