DVAC uses denoising variance as an intrinsic signal to adaptively chunk actions in flow-based robot policies, improving success rates and cutting replans on LIBERO, RoboTwin, CALVIN, and real-world tasks.
CALVIN: A benchmark for language-conditioned policy learning for long-horizon robot manipulation tasks.IEEE Robotics and Automation Letters, 7(3):7327–7334
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
SkiP introduces action relabeling and Motion Spectrum Keying to skip redundant steps in robot trajectories, cutting executed steps by 15-40% while maintaining success rates across 72 simulated and 3 real tasks.
GRASP maps natural language to bounding-box goals via VLM for neuro-symbolic planning and reports 73.3% success in 90 real-robot trials without task-specific training.
S2 improves generalization in vision-language-action models by using goal-preserving refined language guidance and explicit visual evidence budgets, raising mean subtask success from 54.2% to 79.0% on eight real-robot tasks compared to pi0.5.
Tabero supplies a data pipeline that turns existing robot trajectories into vision-tactile-language tasks and a VTLA model that keeps task success high while cutting average grip force by over 70 percent under gentle instructions.
LARY benchmark finds general visual foundation models outperform specialized latent action models and latent visual spaces align better to physical actions than pixel spaces.
WLDS applies large models with factual and logical calibration to produce diverse text-and-image deductions of emergency scenarios beyond what traditional fixed simulations can generate.
citing papers explorer
-
Denoising Tells When to Replan: Denoising-Variance Adaptive Chunking for Flow-Based Robot Policies
DVAC uses denoising variance as an intrinsic signal to adaptively chunk actions in flow-based robot policies, improving success rates and cutting replans on LIBERO, RoboTwin, CALVIN, and real-world tasks.
-
SkiP: When to Skip and When to Refine for Efficient Robot Manipulation
SkiP introduces action relabeling and Motion Spectrum Keying to skip redundant steps in robot trajectories, cutting executed steps by 15-40% while maintaining success rates across 72 simulated and 3 real tasks.
-
Bounding Boxes as Goals: Language-Conditioned Grasping via Neuro-Symbolic Planning
GRASP maps natural language to bounding-box goals via VLM for neuro-symbolic planning and reports 73.3% success in 90 real-robot trials without task-specific training.
-
See Less, Specify More: Visual Evidence Budgets for Generalizable VLAs
S2 improves generalization in vision-language-action models by using goal-preserving refined language guidance and explicit visual evidence budgets, raising mean subtask success from 54.2% to 79.0% on eight real-robot tasks compared to pi0.5.
-
Tabero: Learning Gentle Manipulation with Closed-Loop Force Feedback from Vision, Touch, and Language
Tabero supplies a data pipeline that turns existing robot trajectories into vision-tactile-language tasks and a VTLA model that keeps task success high while cutting average grip force by over 70 percent under gentle instructions.
-
LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment
LARY benchmark finds general visual foundation models outperform specialized latent action models and latent visual spaces align better to physical actions than pixel spaces.
-
What Will Happen Next: Large Models-Driven Deduction for Emergency Instances
WLDS applies large models with factual and logical calibration to produce diverse text-and-image deductions of emergency scenarios beyond what traditional fixed simulations can generate.