Xun Yang

4 papers University of Science and Technology of China

• AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models
• EgoBlind: Towards Egocentric Visual Assistance for the Blind
• EverybodyDance: Bipartite Graph–Based Identity Correspondence for Multi-Character Animation
• Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation