LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction
cs.RO, cs.GR
Submitted: 2026-09-17
Updated: 2026-09-19
Project page: https://neu-vi.github.io/LYRIC
Terminology
Sources
- Is Conditional Generative Modeling all you need for Decision-Making?
- Green-VLA: Staged Vision-Language-Action Model for Generalist Robots
- Training Diffusion Models with Reinforcement Learning
- $\pi_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
- Diffusion Posterior Sampling for General Noisy Inverse Problems
- LoRA: Low-Rank Adaptation of Large Language Models
- Planning with Diffusion for Flexible Behavior Synthesis
- ContactMimic: Humanoid Object Interaction via Contact Control
- InterReal: A Unified Physics-Based Imitation Framework for Learning Human-Object Interaction Skills
- LessMimic: Long-Horizon Humanoid Interaction with Unified Distance Field Representations
- SimGenHOI: Physically Realistic Whole-Body Humanoid-Object Interaction via Generative Modeling and Reinforcement Learning
- Flow Matching for Generative Modeling
- Universal Humanoid Motion Representations for Physics-Based Control
- Absolute Coordinates Make Motion Generation Easy
- SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control
- Surface Keypoint Representation for Multi-Object and Articulated Human-Object Interaction Generation
- Diffusion Policy Policy Optimization
- HOIDiNi: Human-Object Interaction through Diffusion Noise Optimization
- Proximal Policy Optimization Algorithms
- CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving