#GitHub

Oct 20Tue

Oct 20Tuesday

08:00
HuggingFace Daily Papers· 08:00AI score6060
RoboCasa-Shift: A Stage-Aware Robustness Benchmark for VLA Policies in Long-Horizon Household Manipulation
The paper introduces RoboCasa-Shift, a diagnostic robustness benchmark built on RoboCasa365 for evaluating how vision-language-action (VLA) policies handle distribution shifts in long-horizon household manipulation tasks.
Research #Research #Evaluations and benchmarks #Robot models and learning

Oct 12Mon

Oct 12Monday

07:00
3D视觉工坊 · 微信公众号· 07:00AI score5656
Pumpire: A Unified Benchmark for Evaluating Point-to-Point Metric Distance Estimation in 3D Foundation Models
Zhejiang University and other institutions propose Pumpire, a unified benchmark that directly evaluates the ability of image-level and video-level 3D foundation models to estimate point-to-point metric distances in reconstructed geometry, noting that previous approaches of separately evaluating depth and camera intrinsics cannot reflect this ability.
Research #Research #Evaluations and benchmarks #Perception and localization