DSSP is a history-conditioned diffusion state space policy that uses SSMs to encode full observation streams with an auxiliary dynamics objective and hierarchical fusion, achieving SOTA results with reduced model size in robot manipulation.
ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training, September 2025
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 10roles
background 1polarities
background 1representative citing papers
SCORE constrains sim RL to the support of a real-data policy via flow steering, raising average success on eight dexterous tasks from 37.8% to 89.9%.
ARP enhances quantized skill abstractions in imitation learning by coupling visual grounding via contrastive alignment with execution refinement via IRH, reporting SOTA results on LIBERO, Meta-World, and real-robot tasks.
AEM pretrains compact history representations via masked modeling on interleaved vision-action sequences to boost downstream robot manipulation in simulation and real settings.
GLOVES learns flow models from limited expert demonstrations to selectively correct actions from non-expert policies or operators toward expert distributions using reverse-flow OOD detection as an intervention gate.
SFMDS parametrizes dynamical systems via flow matching with soft penalty or hard architectural constraints to enforce stability while preserving multimodality, extended to Lie groups.
Dynamic scene graphs serve as explicit memory to improve imitation learning policies for spatial-temporal reasoning under partial observability in mobile and tabletop manipulation.
ShapeGen generates shape-diverse 3D robotic manipulation demonstrations without simulators by curating a functional shape library and applying a minimal-annotation pipeline for novel, physically plausible data.
LAFP applies flow matching to preserve multimodal latent action structure in policy learning and uses inference-time interpolation to fix stochastic misalignment, achieving 10-15% higher success rates in imitation tasks.
A transformer 3D encoder plus diffusion decoder architecture, with 3D-specific augmentations, outperforms prior 3D policy methods on manipulation benchmarks by improving training stability.
citing papers explorer
-
Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience
SCORE constrains sim RL to the support of a real-data policy via flow steering, raising average success on eight dexterous tasks from 37.8% to 89.9%.
-
ARP: Enhancing Quantized Skill Abstractions via Visual Alignment and Iterative Refinement for Robotic Manipulation
ARP enhances quantized skill abstractions in imitation learning by coupling visual grounding via contrastive alignment with execution refinement via IRH, reporting SOTA results on LIBERO, Meta-World, and real-robot tasks.
-
Action-Effect Memory Pretraining for Robot Manipulation
AEM pretrains compact history representations via masked modeling on interleaved vision-action sequences to boost downstream robot manipulation in simulation and real settings.
-
Flow-based Policy Adaptation without Policy Updates
GLOVES learns flow models from limited expert demonstrations to selectively correct actions from non-expert policies or operators toward expert distributions using reverse-flow OOD detection as an intervention gate.
-
Let the Dynamics Flow: Stable Flow Matching Dynamical Systems
SFMDS parametrizes dynamical systems via flow matching with soft penalty or hard architectural constraints to enforce stability while preserving multimodality, extended to Lie groups.
-
Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs
Dynamic scene graphs serve as explicit memory to improve imitation learning policies for spatial-temporal reasoning under partial observability in mobile and tabletop manipulation.
-
ShapeGen: Robotic Data Generation for Category-Level Manipulation
ShapeGen generates shape-diverse 3D robotic manipulation demonstrations without simulators by curating a functional shape library and applying a minimal-annotation pipeline for novel, physically plausible data.
-
LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching
LAFP applies flow matching to preserve multimodal latent action structure in policy learning and uses inference-time interpolation to fix stochastic misalignment, achieving 10-15% higher success rates in imitation tasks.
-
R3D: Revisiting 3D Policy Learning
A transformer 3D encoder plus diffusion decoder architecture, with 3D-specific augmentations, outperforms prior 3D policy methods on manipulation benchmarks by improving training stability.