π₀.₇ is a steerable generalist robotic model that uses rich multimodal prompts including language, subgoal images, and performance metadata to achieve out-of-the-box generalization across tasks and robot bodies.
Robot data curation with mutual information estimators
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 8verdicts
UNVERDICTED 8roles
background 3polarities
background 3representative citing papers
AutoSpeed optimizes visuomotor policies over candidate trajectories at varying speeds using a composite cost of prediction error versus horizon length, with DCT-based modulation, yielding shorter execution times and higher success rates while producing speeds that align with task stages.
FrameSkip improves VLA policy training success from 66.50% to 76.15% by selecting high-importance frames and retaining only 20% of unique frames across three benchmarks.
Power spectral density of trajectories ranks demonstration quality for imitation learning, enabling rollout-free curation that improves fine-tuned policy success.
GiB uses self-supervised latent features and Mahalanobis distance to filter erroneous subtasks from mixed-quality human demonstrations, improving robot policy learning in simulation and real-world tasks.
RINSE scores robot demonstration trajectories for smoothness via SAL and TED metrics to curate higher-quality data for behavioral cloning, improving success rates with less data on benchmarks and real robots.
GeoSem-WAM adds geometric and semantic auxiliary prediction tasks to World Action Models during training to improve latent representations and action prediction accuracy while keeping inference efficient by avoiding explicit future rollouts.
AttenA+ reweights action training objectives in VLA and WAM models via inverse velocity attention to prioritize kinematically critical segments, yielding small benchmark gains.
citing papers explorer
-
${\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities
π₀.₇ is a steerable generalist robotic model that uses rich multimodal prompts including language, subgoal images, and performance metadata to achieve out-of-the-box generalization across tasks and robot bodies.
-
AutoSpeed: Annotation-Free Stage-Adaptive Motion Speed Learning for Robot Manipulation
AutoSpeed optimizes visuomotor policies over candidate trajectories at varying speeds using a composite cost of prediction error versus horizon length, with DCT-based modulation, yielding shorter execution times and higher success rates while producing speeds that align with task stages.
-
FrameSkip: Learning from Fewer but More Informative Frames in VLA Training
FrameSkip improves VLA policy training success from 66.50% to 76.15% by selecting high-importance frames and retaining only 20% of unique frames across three benchmarks.
-
An Efficient Metric for Data Quality Measurement in Imitation Learning
Power spectral density of trajectories ranks demonstration quality for imitation learning, enabling rollout-free curation that improves fine-tuned policy success.
-
Good in Bad (GiB): Sifting Through End-user Demonstrations for Learning a Better Policy
GiB uses self-supervised latent features and Mahalanobis distance to filter erroneous subtasks from mixed-quality human demonstrations, improving robot policy learning in simulation and real-world tasks.
-
Learning from the Best: Smoothness-Driven Metrics for Data Quality in Imitation Learning
RINSE scores robot demonstration trajectories for smoothness via SAL and TED metrics to curate higher-quality data for behavioral cloning, improving success rates with less data on benchmarks and real robots.
-
GeoSem-WAM: Geometry- and Semantic-Aware World Action Models
GeoSem-WAM adds geometric and semantic auxiliary prediction tasks to World Action Models during training to improve latent representations and action prediction accuracy while keeping inference efficient by avoiding explicit future rollouts.
-
AttenA+: Rectifying Action Inequality in Robotic Foundation Models
AttenA+ reweights action training objectives in VLA and WAM models via inverse velocity attention to prioritize kinematically critical segments, yielding small benchmark gains.