paper
Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking
paperactiveprovisional
humanoid-gpt-scaling-data-and-structure-for-zero-shot-motion-tracking-232090a3·1 events·first seen 13d agoAliases: Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking
Co-occurring entities
More like this (12)
Humanoid-GPTEvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal NavigationHuman-AI Teaming Through the Lens of CalibrationBehavioral Trajectory Tracking Framework3D trackingScaling Laws for Neural Language ModelsEntity Trackingzero-shot learningKinematic Pose TrajectoryWatch, Remember, Reason: Human-View Video Understanding with MLLMsGPT-4o vision fine-tuningq0: Primitives for Hyper-Epoch Pretraining
Recent events (1)
Humanoid-GPT: GPT-style Transformer trained on 2B-frame motion corpus for zero-shot humanoid control
Researchers introduce Humanoid-GPT, a causal Transformer pre-trained on a 2-billion-frame retargeted motion corpus that unifies major mocap datasets with large-scale in-house recordings for whole-body humanoid control. The model achieves zero-shot generalization to unseen motions and control tasks, overcoming the agility-generalization trade-off seen in prior MLP-based trackers. Scaling analyses demonstrate a new performance frontier for dynamic motion tracking without task-specific fine-tuning.