Think Fast, Plan Selectively: Adaptive Deliberation for Efficient Data-Driven MPC
cs.RO, cs.LG
Submitted: 2026-09-26
Updated: 2026-09-30
Terminology
Sources
- TurboMPC: Fast, Scalable, and Differentiable Model Predictive Control on the GPU
- MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control
- Accelerating Large Language Model Decoding with Speculative Sampling
- AEGIS: A Backup Reflex for Physical AI
- EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control
- Fast LeWorldModel
- Adaptive Computation Time for Recurrent Neural Networks
- Hallucination in World Models is Predictable and Preventable
- TD-MPC-Opt: Distilling Model-Based Multi-Task Reinforcement Learning Agents
- Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
- ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies
- VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
- TD-M(PC)$^2$: Improving Temporal Difference MPC Through Policy Constraint
- Accelerating Multi-modal LLM Gaming Performance via Input Prediction and Mishit Correction
- Adaptive Reinforcement and Model Predictive Control Switching for Safe Human-Robot Cooperative Navigation
- LIDAR-AD: A Decoder-Free Latent-Interaction Dreamer with Action-Residual Chains for Autonomous Driving
- OOD-RL-Bench: A Benchmark Framework for Out-of-Distribution Detection in Reinforcement Learning
- Finding the Time to Think: Learning Planning Budgets in Real-Time RL
- Latent Geometry Beyond Search: Amortizing Planning in World Models
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