ReActor jointly optimizes motion retargeting and RL policy training with an approximate gradient to generate physically consistent robot motions from human references using only sparse body correspondences.
In: 2024 IEEE/RSJ Int
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Cross-domain transfer of remote-sensing HSI foundation models improves proximal sensing semantic segmentation over in-domain training and narrows the gap to cross-modality methods on the HS3-Bench benchmark.
Embodied LLM agents exhibit emergent collaborative behaviors indicating mental models of partners in a color-matching game, detected via LLM judges and supported by positive user feedback.
A genetic algorithm evolves neural network weights to enable autonomous 3D navigation and pathing in Minecraft parkour challenges.
citing papers explorer
-
ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting
ReActor jointly optimizes motion retargeting and RL policy training with an approximate gradient to generate physically consistent robot motions from human references using only sparse body correspondences.
-
Cross-Domain Transfer of Hyperspectral Foundation Models
Cross-domain transfer of remote-sensing HSI foundation models improves proximal sensing semantic segmentation over in-domain training and narrows the gap to cross-modality methods on the HS3-Bench benchmark.
-
Evaluating Generative Models as Interactive Emergent Representations of Human-Like Collaborative Behavior
Embodied LLM agents exhibit emergent collaborative behaviors indicating mental models of partners in a color-matching game, detected via LLM judges and supported by positive user feedback.
-
Neuromorphic Control for 3D Navigation in Minecraft Using Genetic Algorithms
A genetic algorithm evolves neural network weights to enable autonomous 3D navigation and pathing in Minecraft parkour challenges.