InfCoiL: Coordinated Planner-Controller Learning for Closed-Loop Physics-Based Human-Object Interaction
cs.CV, cs.LG
Submitted: 2026-11-08
Updated: 2026-11-08
Project page: https://infcoil.github.io
Terminology
Sources
- Unleashing Guidance Without Classifiers for Human-Object Interaction Animation
- InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactions
- SimGenHOI: Physically Realistic Whole-Body Humanoid-Object Interaction via Generative Modeling and Reinforcement Learning
- CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control
- Flow Matching for Generative Modeling
- Back to Basics: Let Denoising Generative Models Denoise
- Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learning
- ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning
- Flow-GRPO: Training Flow Matching Models via Online RL
- Flow Matching Policy Gradients
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Flow Policy Gradients for Robot Control
- GenHOI: Generalizing Text-driven 4D Human-Object Interaction Synthesis for Unseen Objects
- HOI-Dyn: Learning Interaction Dynamics for Human-Object Motion Diffusion
- MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model
- InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinement
- PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction
- GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation
- Universal Humanoid Motion Representations for Physics-Based Control
- Hierarchical World Models as Visual Whole-Body Humanoid Controllers
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs