mlsanityData to 14 Oct 2026

C·ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters

arXiv 2309.11351 ↗First posted 20 Sep 2023cs.GR cs.AI cs.LGcited by 55

Not on the map. Why?

Abstract (arXiv)

We present C·ASE, an efficient and effective framework that learns conditional Adversarial Skill Embeddings for physics-based characters. Our physically simulated character can learn a diverse repertoire of skills while providing controllability in the form of direct manipulation of the skills to be performed. C·ASE divides the heterogeneous skill motions into distinct subsets containing homogeneous samples for training a low-level conditional model to learn conditional behavior distribution. The skill-conditioned imitation learning naturally offers explicit control over the character's skills after training. The training course incorporates the focal skill sampling, skeletal residual forces, and element-wise feature masking to balance diverse skills of varying complexities, mitigate dynamics mismatch to master agile motions and capture more general behavior characteristics, respectively. Once trained, the conditional model can produce highly diverse and realistic skills, outperforming state-of-the-art models, and can be repurposed in various downstream tasks. In particular, the explicit skill control handle allows a high-level policy or user to direct the character with desired skill specifications, which we demonstrate is advantageous for interactive character animation.

Key facts. Cited by 55 papers in the map (data through 14 Oct 2026). Builds on 35 of its 54 references that are in the map. First posted on arXiv 20 Sep 2023.

Builds on

35 of 54 references.

References · 35

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  5. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  6. 2016Generative Adversarial Imitation Learningcited by 1,597
  7. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  8. 2022Human Motion Diffusion Modelcited by 1,080
  9. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  10. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 715
  11. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 533
  12. 2017Overcoming Exploration in Reinforcement Learning with Demonstrationscited by 340
23 more
  1. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  2. 2021Robust Motion In-betweeningcited by 229
  3. 2021Stochastic Scene-Aware Motion Predictioncited by 203
  4. 2018DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skillscited by 163
  5. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 117
  6. 2019MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policiescited by 108
  7. 2018Neural probabilistic motor primitives for humanoid controlcited by 97
  8. 2023CALM: Conditional Adversarial Latent Models for Directable Virtual Characterscited by 94
  9. 2022Towards Diverse and Natural Scene-aware 3D Human Motion Synthesiscited by 91
  10. 2022PYSKL: Towards Good Practices for Skeleton Action Recognitioncited by 83
  11. 2020Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesiscited by 64
  12. 2021Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimationcited by 62
  13. 2023Interactive Character Control with Auto-Regressive Motion Diffusion Modelscited by 55
  14. 2019Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Spacecited by 54
  15. 2023PADL: Language-Directed Physics-Based Character Controlcited by 48
  16. 2023NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimationcited by 45
  17. 2022TORE: Token Reduction for Efficient Human Mesh Recovery with Transformercited by 41
  18. 2023Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstructioncited by 41
  19. 2020UniCon: Universal Neural Controller For Physics-based Character Motioncited by 40
  20. 2021HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representationcited by 35
  21. 2020MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistencycited by 31
  22. 2022ControlVAE: Model-Based Learning of Generative Controllers for Physics-Based Characterscited by 22
  23. 2022Action-conditioned On-demand Motion Generationcited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 23; 2025: 20; 2026: 8.

55 papers.

Sort:

By area:

  1. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 168
  2. 2024MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpaintingcited by 116
  3. 2023TLControl: Trajectory and Language Control for Human Motion Synthesiscited by 94
  4. 2023EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generationcited by 89
  5. 2025Go to Zero: Towards Zero-shot Motion Generation with Million-scale Datacited by 68
  6. 2024CoMo: Controllable Motion Generation through Language Guided Pose Code Editingcited by 67
  7. 2024Taming Diffusion Probabilistic Models for Character Controlcited by 57
  8. 2024Part123: Part-aware 3D Reconstruction from a Single-view Imagecited by 55
  9. 2025TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenizationcited by 51
  10. 2023Disentangled Clothed Avatar Generation from Text Descriptionscited by 33
  11. 2024LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environmentcited by 33
  12. 2024SkillMimic: Learning Basketball Interaction Skills from Demonstrationscited by 30
38 more
  1. 2024SMPLOlympics: Sports Environments for Physically Simulated Humanoidscited by 29
  2. 2025Ready-to-React: Online Reaction Policy for Two-Character Interaction Generationcited by 28
  3. 2025SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrationscited by 25
  4. 2024PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarioscited by 24
  5. 2024Strategy and Skill Learning for Physics-based Table Tennis Animationcited by 20
  6. 2024Learning Multi-Modal Whole-Body Control for Real-World Humanoid Robotscited by 16
  7. 2024Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimickingcited by 16
  8. 2024SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generationcited by 12
  9. 2025CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objectscited by 12
  10. 2025MOSPA: Human Motion Generation Driven by Spatial Audiocited by 12
  11. 2023H-GAP: Humanoid Control with a Generalist Plannercited by 11
  12. 2025Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction Generationcited by 11
  13. 2026InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactionscited by 11
  14. 2024Generative Motion Stylization of Cross-structure Characters within Canonical Motion Spacecited by 10
  15. 2024DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Imagecited by 9
  16. 2025AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learningcited by 9
  17. 2024Diffusion Models are Efficient Data Generators for Human Mesh Recoverycited by 8
  18. 2024MotionWavelet: Human Motion Prediction via Wavelet Manifold Learningcited by 8
  19. 2024FORCE: Physics-aware Human-object Interactioncited by 7
  20. 2025ModSkill: Physical Character Skill Modularizationcited by 7
  21. 2025Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimizationcited by 7
  22. 2025EgoReAct: Egocentric Video-Driven 3D Human Reaction Generationcited by 7
  23. 2025Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputscited by 6
  24. 2025Learning to Ball: Composing Policies for Long-Horizon Basketball Movescited by 6
  25. 2026TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Sizecited by 5
  26. 2025CBIL: Collective Behavior Imitation Learning for Fish from Real Videoscited by 4
  27. 2024CigTime: Corrective Instruction Generation Through Inverse Motion Editingcited by 3
  28. 2024ChatDyn: Language-Driven Multi-Actor Dynamics Generation in Street Scenescited by 3
  29. 2025Versatile Multimodal Controls for Expressive Talking Human Animationcited by 3
  30. 2025Feature-Based vs. GAN-Based Learning from Demonstrations: When and Whycited by 2
  31. 2025Learning to Control Physically-simulated 3D Characters via Generating and Mimicking 2D Motionscited by 2
  32. 2024Dynamic Realms: 4D Content Analysis, Recovery and Generation with Geometric, Topological and Physical Priorscited by 1
  33. 2024ELMO: Enhanced Real-time LiDAR Motion Capture through Upsamplingcited by 1
  34. 2025Environment-aware Motion Matchingcited by 1
  35. 2026Generalizing from References using a Multi-Task Reference and Goal-Driven RL Frameworkcited by 1
  36. 2026EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agentscited by 1
  37. 2026MIND: Multi-Scale Intent Diffusion for Text-Driven Physics-Based Humanoid Controlcited by 1
  38. 2026MoSAT: Human Motion Generation from Spatial Audio and Textual Descriptioncited by 1

50 most cited of 55 All 55 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
  2. 2021AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
  3. 2025Versatile Physics-based Character Control with Hybrid Latent Representation
  4. 2025SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control
  5. 2021A GAN-Like Approach for Physics-Based Imitation Learning and Interactive Character Control
  6. 2023MAAIP: Multi-Agent Adversarial Interaction Priors for imitation from fighting demonstrations for physics-based characters
  7. 2021Visual Adversarial Imitation Learning using Variational Models
  8. 2023Synthesizing Physical Character-Scene Interactions