AToM uses GPT-4Vision-generated preference scores to fine-tune MotionGPT with IPO and LoRA, improving event-level alignment for integrity, temporal order, and frequency in text-to-motion generation.
Lan- guage2pose: Natural language grounded pose forecasting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward
AToM uses GPT-4Vision-generated preference scores to fine-tune MotionGPT with IPO and LoRA, improving event-level alignment for integrity, temporal order, and frequency in text-to-motion generation.