SkyJEPA learns long-horizon latent dynamics for quadrotors via JEPA plus a physics prober, enabling zero-shot sim-to-real control with sampling-based MPC and automated sim data generation.
hub
World models can leverage human videos for dexterous manipulation
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
years
2026 22roles
background 3representative citing papers
DexFuture reaches 90% of oracle performance on bimanual tool-use tasks at 60 Hz by using a horizon-conditioned transformer to predict future visuomotor targets and a per-link policy to track them.
DreamDojo is a foundation world model pretrained on the largest human video dataset to date that uses continuous latent actions to transfer interaction knowledge and achieves controllable physics simulation after robot post-training.
World Action Model co-training with DINO or 3D-flow targets scales human-to-robot transfer on bimanual tasks far better than behavior cloning, while pixel prediction transfers weakly.
A real-time robot-centric video world model driven by depth-aware hand skeletons generates imitation-learning trajectories that support zero-shot real-robot transfer and improve policies when mixed with real data.
Wh0 generates scalable egocentric human manipulation videos with world models and converts them to boost pretrained VLA models' zero-shot dexterous task success from 8.3% to 38.9% on 18 real-world tasks.
DO AS I DO reconstructs and retargets hand-object interactions from in-the-wild monocular RGB videos to produce dexterous robot manipulation trajectories, outperforming prior methods on ground-truth and online video datasets.
Introduces a new task of goal-conditioned 3D point motion forecasting along with a 1.16M-video dataset, a 111-category benchmark, and a model that outperforms baselines while transferring to robotics and video generation.
KPGrasp is a scalable Transformer flow-matching model using 3D hand keypoints that achieves 76.3% success on Dexonomy (47.4% improvement) and best average on DexGrasp Anything without contact losses or test-time refinement.
DexSIM is a bi-directional video diffusion model with hand trajectory embedding and spatial memory cache for real-time dexterous hand-object simulation at 15 FPS.
EgoKit is a new toolkit and accessory set that unifies egocentric video collection with wrist views across heterogeneous consumer devices using a consistent interface and log format.
LACE aligns human-robot visual features via semantic distribution matching on corresponding body parts plus Gram loss, yielding 65% better zero-shot policy transfer than baseline DINO.
Method converts exocentric videos to egocentric format via body-pose extraction and kinematics to improve egocentric world-model prediction and planning.
SCAR proposes a joint inverse-forward dynamics framework to learn transferable continuous action representations across embodiments from visual data using regularization and adversarial invariance.
Planning with a frozen egocentric world model is lifted from 48-dim joint actions to a few 2D goal waypoints via a trained policy, reducing CEM error reduction by 3.8x.
A vision-language-aligned world model turns visuomotor MPC into a language-following planner that reaches 87% success on 288 unseen semantic tasks where standard VLAs drop to 22%.
AdaJEPA performs closed-loop test-time adaptation of latent world models during MPC by executing an action chunk, observing the transition, and taking one gradient step on the model before replanning, yielding higher goal-reaching success.
LUCID learns embodiment-agnostic intent models from unstructured human videos to train dexterous robot policies in simulation, enabling zero-shot transfer on real-world tasks like stirring and wiping.
WorldDP combines a high-level object-centric world model for subgoal planning with a low-level diffusion policy for execution, claiming better performance than baselines on multi-stage robotic manipulation benchmarks.
The paper presents stable-worldmodel (swm), a platform with high-performance data layer, modern world model baselines, planning solvers, and extended environments for reproducible research and generalization evaluation.
Donk is a unified video-action denoising model that generates dexterous hand trajectories and videos under language, image, and state conditioning while also serving as a text-conditioned data engine.
A survey that clarifies boundaries and organizes World Action Models by generation requirements and predictive substrates, identifying a trend toward generating less of the future.
citing papers explorer
-
SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors
SkyJEPA learns long-horizon latent dynamics for quadrotors via JEPA plus a physics prober, enabling zero-shot sim-to-real control with sampling-based MPC and automated sim data generation.
-
DexFuture: Hierarchical Future-State Visuomotor Targeting for Bimanual Dexterous Tool Use
DexFuture reaches 90% of oracle performance on bimanual tool-use tasks at 60 Hz by using a horizon-conditioned transformer to predict future visuomotor targets and a per-link policy to track them.
-
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
DreamDojo is a foundation world model pretrained on the largest human video dataset to date that uses continuous latent actions to transfer interaction knowledge and achieves controllable physics simulation after robot post-training.
-
EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data
World Action Model co-training with DINO or 3D-flow targets scales human-to-robot transfer on bimanual tasks far better than behavior cloning, while pixel prediction transfers weakly.
-
RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation
A real-time robot-centric video world model driven by depth-aware hand skeletons generates imitation-learning trajectories that support zero-shot real-robot transfer and improve policies when mixed with real data.
-
Wh0: Generative World Models as Scalable Sources of Egocentric Human Hand Manipulation Data
Wh0 generates scalable egocentric human manipulation videos with world models and converts them to boost pretrained VLA models' zero-shot dexterous task success from 8.3% to 38.9% on 18 real-world tasks.
-
Do as I Do: Dexterous Manipulation Data from Everyday Human Videos
DO AS I DO reconstructs and retargets hand-object interactions from in-the-wild monocular RGB videos to produce dexterous robot manipulation trajectories, outperforming prior methods on ground-truth and online video datasets.
-
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction
Introduces a new task of goal-conditioned 3D point motion forecasting along with a 1.16M-video dataset, a 111-category benchmark, and a model that outperforms baselines while transferring to robotics and video generation.
-
KPGrasp: Scalable Keypoint Flow Matching for Dexterous Grasp Generation
KPGrasp is a scalable Transformer flow-matching model using 3D hand keypoints that achieves 76.3% success on Dexonomy (47.4% improvement) and best average on DexGrasp Anything without contact losses or test-time refinement.
-
DexSIM: Real-time Dexterous Simulation with Unified Causal Video Diffusion
DexSIM is a bi-directional video diffusion model with hand trajectory embedding and spatial memory cache for real-time dexterous hand-object simulation at 15 FPS.
-
EgoKit: Towards Unified Low-Cost Egocentric Data Collection with Heterogeneous Devices
EgoKit is a new toolkit and accessory set that unifies egocentric video collection with wrist views across heterogeneous consumer devices using a consistent interface and log format.
-
LACE: Latent Visual Representation for Cross-Embodiment Learning
LACE aligns human-robot visual features via semantic distribution matching on corresponding body parts plus Gram loss, yielding 65% better zero-shot policy transfer than baseline DINO.
-
EgoExo-WM: Unlocking Exo Video for Ego World Models
Method converts exocentric videos to egocentric format via body-pose extraction and kinematics to improve egocentric world-model prediction and planning.
-
SCAR: Self-Supervised Continuous Action Representation Learning
SCAR proposes a joint inverse-forward dynamics framework to learn transferable continuous action representations across embodiments from visual data using regularization and adversarial invariance.
-
Lifting Embodied World Models for Planning and Control
Planning with a frozen egocentric world model is lifted from 48-dim joint actions to a few 2D goal waypoints via a trained policy, reducing CEM error reduction by 3.8x.
-
Grounded World Model for Semantically Generalizable Planning
A vision-language-aligned world model turns visuomotor MPC into a language-following planner that reaches 87% success on 288 unseen semantic tasks where standard VLAs drop to 22%.
-
AdaJEPA: An Adaptive Latent World Model
AdaJEPA performs closed-loop test-time adaptation of latent world models during MPC by executing an action chunk, observing the transition, and taking one gradient step on the model before replanning, yielding higher goal-reaching success.
-
LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition
LUCID learns embodiment-agnostic intent models from unstructured human videos to train dexterous robot policies in simulation, enabling zero-shot transfer on real-world tasks like stirring and wiping.
-
Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks
WorldDP combines a high-level object-centric world model for subgoal planning with a low-level diffusion policy for execution, claiming better performance than baselines on multi-stage robotic manipulation benchmarks.
-
stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
The paper presents stable-worldmodel (swm), a platform with high-performance data layer, modern world model baselines, planning solvers, and extended environments for reproducible research and generalization evaluation.
-
Unified Video-Action Joint Denoising for Dexterous Action and Data Generation
Donk is a unified video-action denoising model that generates dexterous hand trajectories and videos under language, image, and state conditioning while also serving as a text-conditioned data engine.
-
World Action Models: A Survey
A survey that clarifies boundaries and organizes World Action Models by generation requirements and predictive substrates, identifying a trend toward generating less of the future.