What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models Paper • 2610.23987 • Published 23 days ago • 39
Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels Paper • 2607.26121 • Published Jul 28 • 1
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed Paper • 2609.39600 • Published Sep 30 • 33
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Paper • 2609.39601 • Published Sep 30 • 92
An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond Paper • 2609.24170 • Published Sep 21
Efficient Alignment of Unconditioned Action Prior for Language-conditioned Pick and Place in Clutter Paper • 2503.09423 • Published Mar 12, 2025 • 1
XPolicyLab: A Unified Standard and Open Ecosystem for Robot Policy Evaluation and Deployment Paper • 2608.09892 • Published Aug 11
RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination Paper • 2607.14187 • Published Jul 15 • 30
RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies Paper • 2607.04434 • Published Jul 7 • 16
RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design Paper • 2603.01229 • Published Mar 15
IMUG-Bench: Benchmarking Unified Multimodal Models on Interleaved Understanding and Generation Paper • 2606.09169 • Published Jun 8
AutoDriDM: An Explainable Benchmark for Decision-Making of Vision-Language Models in Autonomous Driving Paper • 2601.14702 • Published Jan 21
ManiTwin: Scaling Data-Generation-Ready Digital Object Dataset to 100K Paper • 2603.16866 • Published Mar 17 • 1
ReCamDriving: LiDAR-Free Camera-Controlled Novel Trajectory Video Generation Paper • 2512.03621 • Published Dec 3, 2025 • 9
Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshop Paper • 2506.23351 • Published Jun 29, 2025
RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation Paper • 2506.18088 • Published Jun 22, 2025 • 19
What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models Paper • 2610.23987 • Published 23 days ago • 39
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System Paper • 2604.14125 • Published Apr 15 • 21