Exploring the Limits of Combinatorial Generalization in Embodied Manipulation

arXiv:2610.15425 · cs.RO · Submitted 2026-10-11 · Read on arXiv

cs.RO

Submitted: 2026-10-11

Updated: 2026-10-11

Code: https://github.com/AutoLab-SAI-SJTU/RoboCombine

Terminology

• Generalization — 1× in this paper · explained in 13 episodes

Sources

• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
• Motus: A Unified Latent Action World Model
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• Efficient Bimanual Manipulation Using Learned Task Schemas
• Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
• Hierarchical Variational Imitation Learning of Control Programs
• Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning
• CoPa: General Robotic Manipulation through Spatial Constraints of Parts with Foundation Models
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• OpenVLA: An Open-Source Vision-Language-Action Model
• MolmoAct: Action Reasoning Models that can Reason in Space
• OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning
• LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
• HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
• CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks
• FAST: Efficient Action Tokenization for Vision-Language-Action Models
• SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
• Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning

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
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies