CAPEX: Efficiently Distilling Foundation Model Behavior into Deployable Robot Policies through Experience-Adaptive Reasoning
cs.RO, cs.AI, cs.LG
Submitted: 2026-09-26
Updated: 2026-09-26
Project page: https://capex-paper.github.io
Terminology
Sources
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents
- Real-Time Execution of Action Chunking Flow Policies
- RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation
- In-Context Robot Learning with VLM Agents
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
- Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots
- X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real
- Manipulate-Anything: Automating Real-World Robots using Vision-Language Models
- Denoising Tells When to Replan: Denoising-Variance Adaptive Chunking for Flow-Based Robot Policies
- Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition
- Inner Monologue: Embodied Reasoning through Planning with Language Models
- VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
- Agent as Policy for Robotic Manipulation
- DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning
- EgoMimic: Scaling Imitation Learning via Egocentric Video
- OpenVLA: An Open-Source Vision-Language-Action Model
- MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation
- Code as Policies: Language Model Programs for Embodied 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