Robotics

NavA3: Understanding Any Instruction, Navigating Anywhere, Finding Anything ACL 2026 NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Prediction CVPR 2026 On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning ACL 2026 OpenT2M: No-frill Motion Generation with Open-source, Large-scale, High-quality Data CVPR 2026 PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation CVPR 2026 PEAP: Proactive Embodied Action Sequence Planning with Joint Understanding of Vision and Audio Perception ACL 2026 Perceptual 3D Simulation With Physical World Modeling CVPR 2026 PhysGS: Bayesian-Inferred Gaussian Splatting for Physical Property Estimation CVPR 2026 Physically Ground Commonsense Knowledge for Articulated Object Manipulation with Analytic Concepts CVPR 2026 PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image CVPR 2026 PiLoT: Neural Pixel-to-3D Registration for UAV-based Ego and Target Geo-localization CVPR 2026 Pixel Motion Diffusion is What We Need for Robot Control CVPR 2026 Predict Before You Explore: Predictive Planning with Specialized Memory for Embodied Question Answering CVPR 2026 RC-NF: Robot-Conditioned Normalizing Flow for Real-Time Anomaly Detection in Robotic Manipulation CVPR 2026 Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface CVPR 2026 RealAppiance: Let High-fidelity Appliance Assets Controllable and Workable as Aligned Real Manauls CVPR 2026 RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation CVPR 2026 RegionAligner: Bridging Ego-Exo Views for Object Correspondence via Unified Text-Visual Learning WACV 2026 RoboAgent: Chaining Basic Capabilities for Embodied Task Planning CVPR 2026 RoboWheel: A Data Engine from Real-World Human Demonstrations for Cross-Embodiment Robotic Learning CVPR 2026 rosaOS: Agentic Operating System for Embodied LLMs ACL 2026 S2O: Static to Openable Enhancement for Articulated 3D Objects WACV 2026 SCE-SLAM: Scale-Consistent Monocular SLAM via Scene Coordinate Embeddings CVPR 2026 SDT-6D: Fully Sparse Depth-Transformer for Staged End-to-End 6D Pose Estimation in Industrial Multi-View Bin Picking WACV 2026 SE(3)-Equivariance with Geometric and Topological Guidance for Category-Level Object Pose Estimation CVPR 2026