ForkCast: Predictive Recovery for Vision-Language-Action Policies via Counterfactual Futures

cs.RO

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: 9 pages, 5 figures, 3 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution
• Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
• LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
• SaPaVe: Towards Active Perception and Manipulation in Vision-Language-Action Models for Robotics
• Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies
• Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents
• PATCH: Action-Chunk-Conditioned Latent Patch Innovation Monitoring for Robot Manipulation
• Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress
• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
• DREAMSTEER: Latent World Models Can Steer VLA Policies During Deployment Without Any Finetuning
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models
• LIBERO-Occ: Evaluating and Improving Vision-Language-Action Models under Scene-Induced Occlusion via Viewpoint Imagination
• Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance
• RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models
• Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models
• From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

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