Runyi Yu

9

Papers

90

Total Citations

Papers (9)

GAIA: Zero-shot Talking Avatar Generation

InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation

Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation

SkillMimic: Learning Basketball Interaction Skills from Demonstrations

Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation

On the Global Optima of Kernelized Adversarial Representation Learning

LaPE: Layer-adaptive Position Embedding for Vision Transformers with Independent Layer Normalization

Locality Guidance for Improving Vision Transformers on Tiny Datasets