A framework called Policy-as-Data generates task-oriented synthetic HOI data via RL policies in physics simulators, retargets it, and trains diffusion models that generalize to unseen objects and long horizons.
Rl from physical feedback: Align- ing large motion models with humanoid control
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
PHASOR factorizes motion into an FFT-based phase manifold and pose branch with semantic distillation to produce a cross-embodiment, human-anchored action embedding space for humanoid robots.
Humanoid-LLA converts unconstrained natural language commands into stable whole-body motions for humanoid robots using a unified motion vocabulary and two-stage supervised-plus-reinforcement fine-tuning.
citing papers explorer
-
PHASOR: Phase-Anchored Universal Action Representations for Humanoid Embodiments
PHASOR factorizes motion into an FFT-based phase manifold and pose branch with semantic distillation to produce a cross-embodiment, human-anchored action embedding space for humanoid robots.
-
Commanding Humanoid by Free-form Language: A Large Language Action Model with Unified Motion Vocabulary
Humanoid-LLA converts unconstrained natural language commands into stable whole-body motions for humanoid robots using a unified motion vocabulary and two-stage supervised-plus-reinforcement fine-tuning.