← Search

Guorui Song

2 accepted papers

2026

The Quest for Generalizable Motion Generation: Data, Model, and Evaluation

ICLR 2026poster

Despite recent advances in 3D human motion generation (MoGen) on standard benchmarks, existing models still face a fundamental bottleneck in their generalization capability. In contrast, adjacent generative fields, most notably video generation (ViGen), have demonstrated remarkable generalization in…

Cited by 0SourcecodeScholar
2026

UniMo: Unified Motion Generation and Understanding with Chain of Thought

AAAI 2026technical

Existing 3D human motion generation and understanding methods often exhibit limited interpretability, restricting effective mutual enhancement between these inherently related tasks. While current unified frameworks based on large language models (LLMs) leverage linguistic priors, they frequently en

Cited by 0SourcePDFScholar