Uni-Mo generates 7,488 language-annotated quadruped motions via LLM prompts and video diffusion, lifts them to 3D trajectories, and trains policies achieving 96.7% real-robot success on 392 sampled motions.
hub
Xue Bin Peng, Yunrong Guo, Lina Halper, Sergey Levine, and Sanja Fidler
20 Pith papers cite this work, alongside 345 external citations. Polarity classification is still indexing.
20
Pith papers citing it
345
external citations · external index
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
MPC-Injection biases off-policy RL locomotion policies toward controller-induced behavior basins by injecting MPC transitions into the replay buffer.
A two-stage generative model (Graph CVAE + flow matching) learns topology-agnostic motion codes from a new 5k-topology dataset and retargets video motion to arbitrary unseen skeletons.
A hybrid neural policy operating in impulse space enables physics-based characters to track exaggerated, dynamically infeasible motions that standard DRL methods cannot stabilize.
BeyondMimic combines compact motion tracking with a unified guided latent diffusion model to master diverse agile behaviors from human demos and solve unseen downstream tasks via test-time classifier guidance.
SCORE constrains sim RL to the support of a real-data policy via flow steering, raising average success on eight dexterous tasks from 37.8% to 89.9%.
CoorDex distills privileged body and hand motion teachers into proprioceptive latent priors and composes them via shared-context residual RL heads to enable continuous high-DoF dexterous loco-manipulation.
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.
TAGA learns terrain-aware active gaze behaviors for humanoid robots via RL alone, enabling generalizable locomotion with 1.2m real-world gap traversal.
A multi-condition latent diffusion model transfers human motion styles to diverse humanoid robot contents with physics regularizations, achieving 96% success in real-robot trials on Unitree G1.
ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical comparisons of online and offline-to-online RL algorithms.
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
A behavior-constrained RL framework with receding-horizon credit assignment learns high-performance control policies that stay aligned with expert behavior in race car simulation.
GuideWalk unifies traversability-aware navigation and terrain-adaptive locomotion into a single policy for humanoid robots via teacher distillation and RL refinement.
T-GMP learns a terrain-conditioned latent motion manifold via CVAE from demonstrations and integrates it into an adversarial pipeline with a foothold penalty for versatile, natural humanoid locomotion.
M3imic unifies heterogeneous motion modalities via encoders into a shared latent space for a single RL-trained whole-body controller achieving high sim success and sim-to-real transfer on Unitree G1.
MuGen learns a generative latent representation of multi-skill humanoid locomotion from heterogeneous human data using VQ-VAEs and RL, then distills a deployable policy that tracks unseen motions and reuses the latent space.
An end-to-end policy learns robust humanoid locomotion directly from noisy depth images via high-fidelity sensor simulation, vision-aware distillation from privileged maps, and terrain-specific multi-critic reward shaping.
Excessive sim2real focus impedes robotics policy learning via simulator lock-in; a kinematics-only sim2sim2real paradigm is proposed to restore exploration.
citing papers explorer
-
Unleashing Infinite Motion: Scaling Expressive Quadrupedal Motion via Generative Video Priors
Uni-Mo generates 7,488 language-annotated quadruped motions via LLM prompts and video diffusion, lifts them to 3D trajectories, and trains policies achieving 96.7% real-robot success on 392 sampled motions.
-
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.
-
TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation
A two-stage generative model (Graph CVAE + flow matching) learns topology-agnostic motion codes from a new 5k-topology dataset and retargets video motion to arbitrary unseen skeletons.
-
Neural Assistive Impulses: Synthesizing Exaggerated Motions for Physics-based Characters
A hybrid neural policy operating in impulse space enables physics-based characters to track exaggerated, dynamically infeasible motions that standard DRL methods cannot stabilize.
-
BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion
BeyondMimic combines compact motion tracking with a unified guided latent diffusion model to master diverse agile behaviors from human demos and solve unseen downstream tasks via test-time classifier guidance.
-
Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience
SCORE constrains sim RL to the support of a real-data policy via flow steering, raising average success on eight dexterous tasks from 37.8% to 89.9%.
-
CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation
CoorDex distills privileged body and hand motion teachers into proprioceptive latent priors and composes them via shared-context residual RL heads to enable continuous high-DoF dexterous loco-manipulation.
-
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.
-
TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion
TAGA learns terrain-aware active gaze behaviors for humanoid robots via RL alone, enabling generalizable locomotion with 1.2m real-world gap traversal.
-
Bionic Human-Motion Style Transfer for Physically Executable Whole-Body Control of Humanoid Robots
A multi-condition latent diffusion model transfers human motion styles to diverse humanoid robot contents with physics regularizations, achieving 96% success in real-robot trials on Unitree G1.
-
ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders
ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical comparisons of online and offline-to-online RL algorithms.
-
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
-
Behavior-Constrained Reinforcement Learning with Receding-Horizon Credit Assignment for High-Performance Control
A behavior-constrained RL framework with receding-horizon credit assignment learns high-performance control policies that stay aligned with expert behavior in race car simulation.
-
GuideWalk: Learning Unified Autonomous Navigation and Locomotion for Humanoid Robots across Versatile Terrains
GuideWalk unifies traversability-aware navigation and terrain-adaptive locomotion into a single policy for humanoid robots via teacher distillation and RL refinement.
-
T-GMP: Terrain-conditioned Generative Motion Priors for Versatile and Natural Humanoid Locomotion
T-GMP learns a terrain-conditioned latent motion manifold via CVAE from demonstrations and integrates it into an adversarial pipeline with a foothold penalty for versatile, natural humanoid locomotion.
-
M3imic: Learning a Versatile Whole-Body Controller for Multimodal Motion Mimicking
M3imic unifies heterogeneous motion modalities via encoders into a shared latent space for a single RL-trained whole-body controller achieving high sim success and sim-to-real transfer on Unitree G1.
-
MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots
MuGen learns a generative latent representation of multi-skill humanoid locomotion from heterogeneous human data using VQ-VAEs and RL, then distills a deployable policy that tracks unseen motions and reuses the latent space.
-
Now You See That: Learning End-to-End Humanoid Locomotion from Raw Pixels
An end-to-end policy learns robust humanoid locomotion directly from noisy depth images via high-fidelity sensor simulation, vision-aware distillation from privileged maps, and terrain-specific multi-critic reward shaping.
-
Too Much of a Good Thing: When sim2real Efforts Impede Policy Learning (And What to Do About It)
Excessive sim2real focus impedes robotics policy learning via simulator lock-in; a kinematics-only sim2sim2real paradigm is proposed to restore exploration.
- A Differentiable Ray-Wave Framework for Hybrid Refractive-Diffractive System Modeling and Optimization