DeformGen uses dynamics-based state expansion via localized disturbances and deformation-field warping for trajectory transfer to improve policy learning on deformable manipulation benchmarks.
Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Vision-language-action (VLA) models have shown great potential in building generalist robots, but still face a dilemma-misalignment of 2D image forecasting and 3D action prediction. Besides, such a vision-action entangled training manner limits model learning from large-scale, action-free web video data. To address these issues, we propose DeFI, a novel framework that Decouples visual Forward and Inverse dynamics pretraining to exploit respective data sources, wherein video generation and action prediction are disentangled. We introduce the General Forward Dynamics Model (GFDM), pretrained on diverse human and robot videos for future prediction, and the General Inverse Dynamics Model (GIDM), trained via self-supervised learning to infer latent actions from unlabeled video transitions. These models are then integrated into a unified architecture for end-to-end finetuning on downstream tasks. In this manner, GFDM and GIDM first shine separately and then cooperate for mutual benefit. Extensive experiments on CALVIN ABC-D and SimplerEnv demonstrate state-of-the-art performance, with DeFI achieving an average task length of 4.51 for CALVIN, 51.2% success rate on SimplerEnv-Fractal benchmark and 81.3% success rate in real-world deployment, significantly outperforming prior methods.
years
2026 4verdicts
UNVERDICTED 4representative citing papers
ImageWAM shows image editing models can replace video generation in world action models, delivering better performance with 6x lower FLOPs and 4x lower latency by using edit-derived KV caches as compact context.
MaskWAM unifies mask prompting and prediction in world-action models via Mixture of Transformers to improve robotic policy generalization on language-ambiguous tasks.
A data-centric approach shows that less than 3% of AMASS motion data, filtered by physics feasibility, diversity, and complexity, yields better humanoid tracking policies than the full dataset.
citing papers explorer
-
DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning
DeformGen uses dynamics-based state expansion via localized disturbances and deformation-field warping for trajectory transfer to improve policy learning on deformable manipulation benchmarks.
-
ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?
ImageWAM shows image editing models can replace video generation in world action models, delivering better performance with 6x lower FLOPs and 4x lower latency by using edit-derived KV caches as compact context.
-
MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models
MaskWAM unifies mask prompting and prediction in world-action models via Mixture of Transformers to improve robotic policy generalization on language-ambiguous tasks.
-
LIMMT: Less is More for Motion Tracking
A data-centric approach shows that less than 3% of AMASS motion data, filtered by physics feasibility, diversity, and complexity, yields better humanoid tracking policies than the full dataset.