SynthICL trains flow-matching transformer policies for in-context imitation learning entirely from synthetic RGB data and reports 79% average success on 16 unseen real manipulation tasks with one test-time demonstration.
Instant policy: In-context imitation learning via graph diffusion
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
PEACH uses a novel spatio-temporal point cloud sequence encoder plus auxiliary supervision to enable zero-shot adaptation of graph network simulators to unseen physical properties, outperforming mesh-based baselines in simulation accuracy while being more deployable for real scenes.
GAF creates 4D dynamic scene models by adding motion to 3D Gaussians, enabling better reconstruction and 7.3% higher success in robotic tasks.
citing papers explorer
-
SynthICL: Scalable In-context Imitation Learning with Synthetic Data
SynthICL trains flow-matching transformer policies for in-context imitation learning entirely from synthetic RGB data and reports 79% average success on 16 unseen real manipulation tasks with one test-time demonstration.
-
Point Cloud Sequence Encoding for Material-conditioned Graph Network Simulators
PEACH uses a novel spatio-temporal point cloud sequence encoder plus auxiliary supervision to enable zero-shot adaptation of graph network simulators to unseen physical properties, outperforming mesh-based baselines in simulation accuracy while being more deployable for real scenes.
-
GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation
GAF creates 4D dynamic scene models by adding motion to 3D Gaussians, enabling better reconstruction and 7.3% higher success in robotic tasks.