An autoregressive diffusion model with a hybrid explicit-root/latent-body representation generates real-time, controllable 3D human motion from text and spatial constraints.
hub
Resmimic: From general motion tracking to humanoid whole-body loco-manipulation via residual learning
23 Pith papers cite this work. Polarity classification is still indexing.
23
Pith papers citing it
hub tools
years
2026 23representative citing papers
MPC-Injection biases off-policy RL locomotion policies toward controller-induced behavior basins by injecting MPC transitions into the replay buffer.
HumanoidArena is a new benchmark of 7 leg-critical HOI/HSI tasks that evaluates egocentric hierarchical whole-body policies in humanoids and finds performance is strongly conditioned on the low-level GMT used.
MotionDisco discovers long-horizon humanoid loco-manipulation motions from scratch via LLM-guided evolutionary search, trajectory optimization, and pruning, then transfers them to real robots with RL policies.
A humanoid tracking policy is trained with contact-following rewards and trajectory augmentation to decouple physical contact from keypoint geometry, enabling runtime contact control.
Generates 48,000 synthetic VLK trajectories in 3D-reconstructed scenes to train a policy for egocentric perception-based humanoid navigation and object transport, shown on physical Unitree G1 robot.
FADA is a three-stage Planner-IDM method that achieves few-shot domain adaptation for humanoid control by distilling an oracle policy then finetuning only the IDM on short target-domain rollouts via supervised learning.
SceneBot conditions a humanoid tracking policy on motion references and contact labels, using reconstructed scene-interaction data to unify free-space locomotion with contact-rich manipulation and terrain tasks.
OmniContact introduces contact flow as a shared representation of body trajectories and contact signals to learn and chain loco-manipulation meta-skills, reporting 98.7% success on box carrying and 76.5% on push-stack tasks.
A three-stage motion-guided curriculum RL framework trains humanoid robots for soccer shooting, achieving 48.6% lower shot error and 2.96x higher velocity than baselines in simulation and sub-meter accuracy with 13.10 m/s ball speed on a real Unitree G1.
Perceptive BFM grounds human motion priors in robot terrain perception via terrain-conformal reference synthesis and teacher-student transfer from adapted to raw-reference tracking.
Imagine2Real enables zero-shot humanoid-object interaction by unifying motions as 4D point trajectories, tracking only base/hands/object keypoints inside a BFM latent space, and training with progressive simple rewards for mocap deployment.
ExpertGen generates high-success expert policies in simulation from imperfect priors by freezing a diffusion behavior model and optimizing its initial noise via RL, then distills them for real-robot deployment.
AssistMimic is the first multi-agent RL method that successfully tracks assistive human-human interaction motions in simulation by using partner-aware policies, single-agent initialization, dynamic reference retargeting, and contact-promoting rewards.
HAIC enables robust humanoid interactions with underactuated objects by predicting their dynamics from proprioceptive history and using a world model for adaptive control.
VAIC distills a teacher policy into a vision-and-proprioception student policy using recurrent adaptation and decoupled commands, enabling diverse real-robot tasks like box carrying and skateboarding that outperform baselines.
HANDOFF is a distilled mixture-of-experts humanoid whole-body controller that follows a compact task-space interface, matches SOTA velocity tracking, provides large manipulation workspace on Unitree G1, and supports VLM-driven agentic planning with no task-specific data.
A hybrid motion-tracking and imitation-reinforcement pipeline produces a depth-based visuomotor policy that lets humanoids climb varied ladders zero-shot on hardware and perform teleoperated manipulation while climbing.
GRAIL creates over 20,000 synthetic loco-manipulation sequences from known 3D configurations and video priors, then trains policies that achieve 84% pick-up and 90% stair-climbing success on a real Unitree G1 humanoid using only the generated data.
HOIST finetunes a VLA policy from VR demonstrations then applies iterative batched RL to cut translational placement error by 19.9 cm and angular error by 3.56 degrees versus pure VLA on suspended-load manipulation.
A multi-agent large-model framework (Active Spatial Brain + Generalizable Action Cerebellum) enables spatial-aware humanoid whole-body manipulation without task-specific real-robot data.
HandelBot refines simulation policies via physical rollouts and residual RL to achieve precise bimanual piano playing, outperforming direct sim transfer by 1.8x with only 30 minutes of real data across five songs.
SplitAdapter factorizes adaptation into load-aware and dynamics-aware encoders using split world-model objectives, GRL regularization, and hierarchical FiLM, reporting higher full-task success than baselines across 2-6 kg masses and 0-60 cm heights.
citing papers explorer
-
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
An autoregressive diffusion model with a hybrid explicit-root/latent-body representation generates real-time, controllable 3D human motion from text and spatial constraints.
-
MPC-Injection: Biasing Off-Policy Locomotion RL Toward Controller-Induced Behavior Basins
MPC-Injection biases off-policy RL locomotion policies toward controller-induced behavior basins by injecting MPC transitions into the replay buffer.
-
HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning
HumanoidArena is a new benchmark of 7 leg-critical HOI/HSI tasks that evaluates egocentric hierarchical whole-body policies in humanoids and finds performance is strongly conditioned on the low-level GMT used.
-
MotionDisco: Motion Discovery for Extreme Humanoid Loco-Manipulation
MotionDisco discovers long-horizon humanoid loco-manipulation motions from scratch via LLM-guided evolutionary search, trajectory optimization, and pruning, then transfers them to real robots with RL policies.
-
ContactMimic: Humanoid Object Interaction via Contact Control
A humanoid tracking policy is trained with contact-following rewards and trajectory augmentation to decouple physical contact from keypoint geometry, enabling runtime contact control.
-
VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes
Generates 48,000 synthetic VLK trajectories in 3D-reconstructed scenes to train a policy for egocentric perception-based humanoid navigation and object transport, shown on physical Unitree G1 robot.
-
FADA: Few-Shot Domain Adaptation via Dynamics Alignment for Humanoid Control
FADA is a three-stage Planner-IDM method that achieves few-shot domain adaptation for humanoid control by distilling an oracle policy then finetuning only the IDM on short target-domain rollouts via supervised learning.
-
SceneBot: Contact-Prompted General Humanoid Whole Body Tracking with Scene-Interaction
SceneBot conditions a humanoid tracking policy on motion references and contact labels, using reconstructed scene-interaction data to unify free-space locomotion with contact-rich manipulation and terrain tasks.
-
OmniContact: Chaining Meta-Skills via Contact Flow for Generalizable Humanoid Loco-Manipulation
OmniContact introduces contact flow as a shared representation of body trajectories and contact signals to learn and chain loco-manipulation meta-skills, reporting 98.7% success on box carrying and 76.5% on push-stack tasks.
-
RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning
A three-stage motion-guided curriculum RL framework trains humanoid robots for soccer shooting, achieving 48.6% lower shot error and 2.96x higher velocity than baselines in simulation and sub-meter accuracy with 13.10 m/s ball speed on a real Unitree G1.
-
Perceptive Behavior Foundation Model: Adapting Human Motion Priors to Robot-Centric Terrain
Perceptive BFM grounds human motion priors in robot terrain perception via terrain-conformal reference synthesis and teacher-student transfer from adapted to raw-reference tracking.
-
Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors
Imagine2Real enables zero-shot humanoid-object interaction by unifying motions as 4D point trajectories, tracking only base/hands/object keypoints inside a BFM latent space, and training with progressive simple rewards for mocap deployment.
-
ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors
ExpertGen generates high-success expert policies in simulation from imperfect priors by freezing a diffusion behavior model and optimizing its initial noise via RL, then distills them for real-robot deployment.
-
Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning
AssistMimic is the first multi-agent RL method that successfully tracks assistive human-human interaction motions in simulation by using partner-aware policies, single-agent initialization, dynamic reference retargeting, and contact-promoting rewards.
-
HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model
HAIC enables robust humanoid interactions with underactuated objects by predicting their dynamics from proprioceptive history and using a world model for adaptive control.
-
VAIC: Vision-Guided Humanoid Agile Object Interaction Control via Decoupled Commands
VAIC distills a teacher policy into a vision-and-proprioception student policy using recurrent adaptation and decoupled commands, enabling diverse real-robot tasks like box carrying and skateboarding that outperform baselines.
-
HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers
HANDOFF is a distilled mixture-of-experts humanoid whole-body controller that follows a compact task-space interface, matches SOTA velocity tracking, provides large manipulation workspace on Unitree G1, and supports VLM-driven agentic planning with no task-specific data.
-
LadderMan: Learning Humanoid Perceptive Ladder Climbing
A hybrid motion-tracking and imitation-reinforcement pipeline produces a depth-based visuomotor policy that lets humanoids climb varied ladders zero-shot on hardware and perform teleoperated manipulation while climbing.
-
GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors
GRAIL creates over 20,000 synthetic loco-manipulation sequences from known 3D configurations and video priors, then trains policies that achieve 84% pick-up and 90% stair-climbing success on a real Unitree G1 humanoid using only the generated data.
-
HOIST: Humanoid Optimization with Imitation and Sample-efficient Tuning for Manipulating Suspended Loads
HOIST finetunes a VLA policy from VR demonstrations then applies iterative batched RL to cut translational placement error by 19.9 cm and angular error by 3.56 degrees versus pure VLA on suspended-load manipulation.
-
Humanoid Whole-Body Manipulation via Active Spatial Brain and Generalizable Action Cerebellum
A multi-agent large-model framework (Active Spatial Brain + Generalizable Action Cerebellum) enables spatial-aware humanoid whole-body manipulation without task-specific real-robot data.
-
HandelBot: Real-World Piano Playing via Fast Adaptation of Dexterous Robot Policies
HandelBot refines simulation policies via physical rollouts and residual RL to achieve precise bimanual piano playing, outperforming direct sim transfer by 1.8x with only 30 minutes of real data across five songs.
-
SplitAdapter: Load-Aware Humanoid Loco-Manipulation via Factorized Adaptation
SplitAdapter factorizes adaptation into load-aware and dynamics-aware encoders using split world-model objectives, GRL regularization, and hierarchical FiLM, reporting higher full-task success than baselines across 2-6 kg masses and 0-60 cm heights.