ICRA 2026PastRobotics
ICRA 2026 Workshop: From Data to Decisions: VLA Pipelines for Real Robots
ICRA 2026: From Data to Decisions
- Submission deadline
- Apr 22, 2026, 00:00 UTCOpenReview-synced 2026-04-22 00:00 UTC (as of 2026-06-23) — extensions on OpenReview are applied automatically; verify on the website.
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (32)
Fetched from OpenReview (v2) on 2026-06-10.
A Social-interaction World Model Pipeline: Multimodal Data Acquisition for Capturing Bifurcating Social Intents in HRI
AbsVLA: Learning Robust Primitive Manipulation Skills for VLA Models in Object-Centric Abstracted States
AR-VLA: True Autoregressive Action Expert for Vision–Language–Action Models
CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion
Closing The Performance Gap Between Zero-shot And Post-trained Reward Models
CRISP - Compliant ROS2 Controllers for Learning-Based Manipulation Policies and Teleoperation
DexEXO: A Wearability-First Dexterous Exoskeleton for Operator-Agnostic Demonstration and Learning
Energy-Based Action Heads Know When They Don’t Know
EVE: A Generator-Verifier System for Generative Policies
Execution-Aware Task Planning for Language-Conditioned Bimanual Manipulation
From Aerial Twins to VLA Tuples: A Zero-NRE Data Factory with Caption Drift Evaluation
From Demonstrations to Safe Deployment: Path-Consistent Safety Filtering for Diffusion Policies
GAM: Generalized Action Model for Robotic Manipulation
Health-Conditioned Vision-Language-Action Models for Malfunction-Aware Robot Control
How VLAs Fail Differently: Black-Box Action Monitoring Reveals Architecture-Specific Failure Signatures
Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation
Inside the Reasoning Menu: Discrete Failure Bands in Driving VLAs Under Sensor Perturbations
MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation
Per-Group Error, Not Total MSE: Fine-Tuning Vision-Language-Action Models for 11-DoF Mobile Manipulation
ProMix: Learning Optimal Data Mixtures for Robotic Imitation via Proxy-Reference Distillation
Rethinking Exploration Through Context for RL
ReVer: Reasoning-Guided Verification for Embodied Agents
sensVLA: Spatially-Grounded Vision-Language-Action Model for Autonomous Wheel Loader
Toward Hierarchical Vision-Language-Action Models with Continuous Skill Abstraction
Towards Data-Efficient VLA Post-Training: a case study of an industrial task
UniOMA: Unified Optimal-Transport Multi-Modal Structural Alignment for Robot Perception
Verifier-Guided Action Selection For Embodied Agents
VGM: Value-Gated Modulation for Minute-Level Residual Adaptation of VLA Policies
VL-N3RD-Bench: Benchmarking Vision-Language Navigation with 3D Gaussian Splatting Reconstruction for Deployment
vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models
When Absolute State Fails: Evaluating Proprioceptive Encodings for Robust Manipulation
X-Diffusion: Training Diffusion Policies on Cross-Embodiment