# Branch-Centric Tokenization and Test-Time Augmentation for Skeleton Generation

arXiv: https://arxiv.org/abs/2609.06218 · HTML: https://mlsanity.com/paper/2609.06218/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 49 references that are in the map.
- First posted on arXiv 5 Sep 2026.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [graph2vec: Learning Distributed Representations of Graphs](https://mlsanity.com/paper/1707.05005/) (2017)
- [Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation](https://mlsanity.com/paper/2306.17115/) (2023)
- [Better Aggregation in Test-Time Augmentation](https://mlsanity.com/paper/2011.11156/) (2020)
- [Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context](https://mlsanity.com/paper/1805.04623/) (2018)
- [Shortformer: Better Language Modeling using Shorter Inputs](https://mlsanity.com/paper/2012.15832/) (2020)
- [Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation](https://mlsanity.com/paper/2002.09103/) (2020)
- [Learning Loss for Test-Time Augmentation](https://mlsanity.com/paper/2010.11422/) (2020)
- [Learning Skeletal Articulations with Neural Blend Shapes](https://mlsanity.com/paper/2105.02451/) (2021)
- [RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets](https://mlsanity.com/paper/2502.09615/) (2025)
- [One Model to Rig Them All: Diverse Skeleton Rigging with UniRig](https://mlsanity.com/paper/2504.12451/) (2025)
- [MagicArticulate: Make Your 3D Models Articulation-Ready](https://mlsanity.com/paper/2502.12135/) (2025)
- [Puppeteer: Rig and Animate Your 3D Models](https://mlsanity.com/paper/2508.10898/) (2025)
- [Predicting Animation Skeletons for 3D Articulated Models via Volumetric Nets](https://mlsanity.com/paper/1908.08506/) (2019)
- [The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models](https://mlsanity.com/paper/2108.06084/) (2021)
- [Anymate: A Dataset and Baselines for Learning 3D Object Rigging](https://mlsanity.com/paper/2505.06227/) (2025)
- [DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters](https://mlsanity.com/paper/2411.17423/) (2024)
- [Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters](https://mlsanity.com/paper/2411.18197/) (2024)
- [Morig: Motion-aware rigging of character meshes from point clouds](https://mlsanity.com/paper/2210.09463/) (2022)
- [HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset](https://mlsanity.com/paper/2412.02317/) (2024)
- [Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization](https://mlsanity.com/paper/2506.11430/) (2025)
- [Animator-Centric Skeleton Generation on Objects with Fine-Grained Details](https://mlsanity.com/paper/2604.20539/) (2026)
- [Skin Tokens: A Learned Compact Representation for Unified Autoregressive Rigging](https://mlsanity.com/paper/2602.04805/) (2026)
- [Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models](https://mlsanity.com/paper/2602.09713/) (2026)

## Abstract (arXiv)

Automatic skeleton generation involves predicting both joint positions and skeletal connectivity. However, existing approaches struggle to encode branch structures into token sequences and do not use test-time computation effectively. We study these choices within a unified autoregressive framework. First, we introduce branch-centric tokenization, a branch-aware representation that places structurally related elements next to each other and encodes connectivity directly in the sequence. Compared with standard BFS-style serialization, this representation yields more compact sequences. Second, we introduce view-augmented generation, a test-time augmentation procedure that applies axis-aligned rotations to the input mesh, maps all predictions back to a common frame, and selects the final skeleton based on mesh coverage and consistency among predictions from different views. Experiments show that our method achieves better skeleton prediction accuracy than state-of-the-art methods. In particular, our method reduces the CD-J2B error by 16.9% on the Articulation-XL2.0 dataset compared to the strongest directly comparable baseline, Auto-Connect. Qualitative results on in-the-wild meshes further demonstrate generalization across diverse inputs.