RotVLA models latent actions as continuous SO(n) rotations with triplet-frame supervision and flow-matching to reach 98.2% success on LIBERO and 89.6%/88.5% on RoboTwin2.0 using a 1.7B-parameter model.
//arxiv.org/abs/2308.10901
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
World models succeed when their latent states are built to meet task-specific sufficiency constraints rather than preserving the maximum amount of information.
GraspDreamer synthesizes human functional grasping demonstrations with visual generative models to enable zero-shot robot grasping with improved data efficiency and generalization.
A new occlusion-aware control module generates high-fidelity egocentric videos from sparse 3D hand joints, supported by a million-clip dataset and cross-embodiment benchmark.
A GPT-style model pre-trained on large video datasets achieves 94.9% success on CALVIN multi-task manipulation and 85.4% zero-shot generalization, outperforming prior baselines.
A survey introduces an interface-centric taxonomy for video-to-control methods in robotic manipulation and identifies the robotics integration layer as the central open challenge.
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
citing papers explorer
-
RotVLA: Rotational Latent Action for Vision-Language-Action Model
RotVLA models latent actions as continuous SO(n) rotations with triplet-frame supervision and flow-matching to reach 98.2% success on LIBERO and 89.6%/88.5% on RoboTwin2.0 using a 1.7B-parameter model.
-
Latent State Design for World Models under Sufficiency Constraints
World models succeed when their latent states are built to meet task-specific sufficiency constraints rather than preserving the maximum amount of information.
-
Grasp as You Dream: Imitating Functional Grasping from Generated Human Demonstrations
GraspDreamer synthesizes human functional grasping demonstrations with visual generative models to enable zero-shot robot grasping with improved data efficiency and generalization.
-
Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints
A new occlusion-aware control module generates high-fidelity egocentric videos from sparse 3D hand joints, supported by a million-clip dataset and cross-embodiment benchmark.
-
Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation
A GPT-style model pre-trained on large video datasets achieves 94.9% success on CALVIN multi-task manipulation and 85.4% zero-shot generalization, outperforming prior baselines.
-
From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data
A survey introduces an interface-centric taxonomy for video-to-control methods in robotic manipulation and identifies the robotics integration layer as the central open challenge.
-
World Action Models: The Next Frontier in Embodied AI
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.