AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward

Documenti analoghi

• AToM: Amortized Text-to-Mesh using 2D Diffusion
  di: Qian, Guocheng, et al.
  Pubblicazione: (2024)
• AToM: Adaptive Theory-of-Mind-Based Human Motion Prediction in Long-Term Human-Robot Interactions
  di: Liao, Yuwen, et al.
  Pubblicazione: (2025)
• MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models
  di: Xu, Zunnan, et al.
  Pubblicazione: (2024)
• AToM-Bot: Embodied Fulfillment of Unspoken Human Needs with Affective Theory of Mind
  di: Ding, Wei, et al.
  Pubblicazione: (2024)
• Separate to Collaborate: Dual-Stream Diffusion Model for Coordinated Piano Hand Motion Synthesis
  di: Liu, Zihao, et al.
  Pubblicazione: (2025)