An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond
cs.CV
Submitted: 2026-09-21
Updated: 2026-09-21
Code: https://github.com/RoboProbe/RoboProbe
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- RT-1: Robotics Transformer for Real-World Control at Scale
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- Language Models are Few-Shot Learners
- Robots Acquire Manipulation Skills in Seconds from a Single Human Video
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
- XPolicyLab: A Unified Standard and Open Ecosystem for Robot Policy Evaluation and Deployment
- PaLM-E: An Embodied Multimodal Language Model
- In-Context Imitation Learning via Next-Token Prediction
- Agent as Policy for Robotic Manipulation
- RoboTTT: Context Scaling for Robot Policies
- Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
- Language Models as Zero-Shot Trajectory Generators
- Code as Policies: Language Model Programs for Embodied Control
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
- Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models
- GPT-4 Technical Report
- RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
- Demonstration-Free Robotic Control via LLM Agents
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models