arXiv:2610.13549 · v2

ELMA: Benchmarking Anaphoric Compositions for Long-Term Text-to-Motion Generation

首次提交 2026-10-09 21:05

版本更新 2026-11-03 14:15

雷达观测 2026-11-04 23:40

摘要

Text-guided long-term human motion generation is essential for applications such as continuously operating digital avatars. Despite recent progress on short clips, existing models struggle with multi-segment instructions that involve anaphora, where constraints established in earlier segments must be preserved over time. In this paper, we introduce a novel task of long-term motion generation from such anaphoric compositions. To address this gap, we present ELMA, an episodic long-term motion dataset with dense segment-level annotations that preserve cross-segment dependencies. Built via a fully automated collection and filtering pipeline, ELMA extracts high-quality, continuous 30-second clips from in-the-wild videos, capturing the episodic narratives necessary for long-range state modeling. Using ELMA, we benchmark representative long-term motion generation models under independent and anaphoric instruction settings, and study whether contextual fine-tuning improves long-range state modeling. Our extensive experiments provide insights into the capabilities and limitations of existing models in handling context-dependent instructions. These findings highlight the challenge of modeling cross-segment dependencies and offer valuable directions for developing more coherent and semantically consistent long-term motion generation models.

作者备注：Accepted at NeurIPS 2026 Evaluations & Datasets Track