REGEN uses recurrent generative replays from World Action Models to cut catastrophic forgetting by up to 50% in continual imitation learning compared to sequential fine-tuning.
hub Baseline reference
Interndata-a1: Pioneering high-fidelity synthetic data for pre-training generalist policy
Baseline reference. 60% of citing Pith papers use this work as a benchmark or comparison.
25
Pith papers citing it
Baseline
60% of classified citations
hub tools
citation-role summary
dataset 3
background 2
citation-polarity summary
years
2026 25representative citing papers
DeformGen uses dynamics-based state expansion via localized disturbances and deformation-field warping for trajectory transfer to improve policy learning on deformable manipulation benchmarks.
AutoScale is a closed-loop data engine using Graph-RAE for scene representation and Cluster-GA for importance-based retrieval to improve real-synthetic co-training for autonomous driving.
A single RGB image is converted into a layered, simulation-ready robot scene that supports trajectory replay, synthetic data generation, and meaningful sim-real policy evaluation, plus a 564-scene DROID-Sim companion set.
Introduces H-Tac human tactile-action dataset and TTP pre-training that unifies spaces and predicts future tactile signals to improve robotic dexterous manipulation transfer.
Aligning temporal granularity, action subspaces, and train-test conditioning yields SOTA long-horizon mobile and fine-grained manipulation success for a unified world-action model.
An automated real-to-sim pipeline builds digital twins and affordance-preserving cousins from video, yielding sim evaluations that correlate with real robot policy success and zero-shot sim-to-real gains.
Qwen-RobotManip applies unified alignment across representation, motion, and behavior to enable large-scale training on heterogeneous manipulation data, yielding emergent generalization on out-of-distribution robotic benchmarks.
AnnotateAnything converts passive 3D assets into manipulation-ready assets by combining vision-language reasoning for semantics with parallel physics pipelines for executable action annotations such as grasps and articulations.
RepWAM introduces representation visual-action tokenizers to pretrain world action models that jointly model future visual states and latent actions under instructions for improved robot manipulation.
AffordanceVLA proposes a VLA model with affordance-aware modules (Which2Act, Where2Act, How2Act) in a Mixture-of-Transformer trained in three stages to improve robotic manipulation.
OSCAR finetunes Cosmos-Predict2.5-2B on a deduplicated multi-embodiment robotics dataset with kinematic skeleton conditioning, claiming better action following and significant correlation between virtual and real robot policy evaluations.
STABLE generates simulation-ready tabletop scenes by alternating a semantic LLM reasoner for task-aligned coarse layouts with a physics corrector for physical plausibility using progressive scene expansion.
Embody4D generates novel-view videos from monocular robot videos via a 3D-aware synthesis pipeline, confidence-aware expert modulation, and interaction-aware attention for embodied 4D world modeling.
X-WAM unifies robotic action execution and 4D world synthesis by adapting video diffusion priors with a lightweight depth branch and asynchronous noise sampling, achieving 79-91% success on robot benchmarks.
SIM1 converts sparse real demonstrations into high-fidelity synthetic data through physics-aligned simulation, yielding policies that match real-data performance at a 1:15 ratio with 90% zero-shot success on deformable manipulation.
ExpertGen generates high-success expert policies in simulation from imperfect priors by freezing a diffusion behavior model and optimizing its initial noise via RL, then distills them for real-robot deployment.
A video-action foundation model pretrained natively with a causal diffusion transformer and semantic visual-action tokenizer reports improved few-shot robot manipulation and 225 Hz asynchronous closed-loop control.
LabVLA uses RoboGenesis simulation data and a two-stage FAST pretraining plus flow matching recipe on a Qwen3-VL backbone to achieve the highest success rates on LabUtopia under in- and out-of-distribution conditions.
HumanoidMimicGen automatically generates large loco-manipulation datasets from few source demonstrations using whole-body planning, enabling visuomotor policies that outperform real-data-only training by 20% on a new nine-task benchmark.
HyperSim reports 80% and 95% sim-to-real success on two manipulation policies across 400 real executions by combining synthetic environment synthesis, adversarial trajectories, and co-training.
CoEnv introduces a compositional environment that integrates real and simulated spaces for multi-agent robotic collaboration, using real-to-sim reconstruction, VLM action synthesis, and validated sim-to-real transfer to achieve high success rates on multi-arm manipulation tasks.
LingBot-VA combines video world modeling with policy learning via Mixture-of-Transformers, closed-loop rollouts, and asynchronous inference to improve robot manipulation in simulation and real settings.
Authors perform a cross-simulator, cross-policy empirical study of sim-to-real correlation for VLA policies and distill guidance on using simulation for policy improvement.
citing papers explorer
-
World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays
REGEN uses recurrent generative replays from World Action Models to cut catastrophic forgetting by up to 50% in continual imitation learning compared to sequential fine-tuning.
-
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.
-
Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training
AutoScale is a closed-loop data engine using Graph-RAE for scene representation and Cluster-GA for importance-based retrieval to improve real-synthetic co-training for autonomous driving.
-
RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation
A single RGB image is converted into a layered, simulation-ready robot scene that supports trajectory replay, synthetic data generation, and meaningful sim-real policy evaluation, plus a 564-scene DROID-Sim companion set.
-
Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation
Introduces H-Tac human tactile-action dataset and TTP pre-training that unifies spaces and predicts future tactile signals to improve robotic dexterous manipulation transfer.
-
ABot-M0.5: Unified Mobility-and-Manipulation World Action Model
Aligning temporal granularity, action subspaces, and train-test conditioning yields SOTA long-horizon mobile and fine-grained manipulation success for a unified world-action model.
-
SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation
An automated real-to-sim pipeline builds digital twins and affordance-preserving cousins from video, yielding sim evaluations that correlate with real robot policy success and zero-shot sim-to-real gains.
-
Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models
Qwen-RobotManip applies unified alignment across representation, motion, and behavior to enable large-scale training on heterogeneous manipulation data, yielding emergent generalization on out-of-distribution robotic benchmarks.
-
AnnotateAnything: Automatic Annotation of 3D Assets for Robot Manipulation
AnnotateAnything converts passive 3D assets into manipulation-ready assets by combining vision-language reasoning for semantics with parallel physics pipelines for executable action annotations such as grasps and articulations.
-
RepWAM: World Action Modeling with Representation Visual-Action Tokenizers
RepWAM introduces representation visual-action tokenizers to pretrain world action models that jointly model future visual states and latent actions under instructions for improved robot manipulation.
-
AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding
AffordanceVLA proposes a VLA model with affordance-aware modules (Which2Act, Where2Act, How2Act) in a Mixture-of-Transformer trained in three stages to improve robotic manipulation.
-
OSCAR: Omni-Embodiment Action-Conditioned World Model for Robotics
OSCAR finetunes Cosmos-Predict2.5-2B on a deduplicated multi-embodiment robotics dataset with kinematic skeleton conditioning, claiming better action following and significant correlation between virtual and real robot policy evaluations.
-
STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System
STABLE generates simulation-ready tabletop scenes by alternating a semantic LLM reasoner for task-aligned coarse layouts with a physics corrector for physical plausibility using progressive scene expansion.
-
Embody4D: A Generalist Data Engine for Embodied 4D World Modeling
Embody4D generates novel-view videos from monocular robot videos via a 3D-aware synthesis pipeline, confidence-aware expert modulation, and interaction-aware attention for embodied 4D world modeling.
-
Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising
X-WAM unifies robotic action execution and 4D world synthesis by adapting video diffusion priors with a lightweight depth branch and asynchronous noise sampling, achieving 79-91% success on robot benchmarks.
-
SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds
SIM1 converts sparse real demonstrations into high-fidelity synthetic data through physics-aligned simulation, yielding policies that match real-data performance at a 1:15 ratio with 90% zero-shot success on deformable manipulation.
-
ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors
ExpertGen generates high-success expert policies in simulation from imperfect priors by freezing a diffusion behavior model and optimizing its initial noise via RL, then distills them for real-robot deployment.
-
Native Video-Action Pretraining for Generalizable Robot Control
A video-action foundation model pretrained natively with a causal diffusion transformer and semantic visual-action tokenizer reports improved few-shot robot manipulation and 225 Hz asynchronous closed-loop control.
-
LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories
LabVLA uses RoboGenesis simulation data and a two-stage FAST pretraining plus flow matching recipe on a Qwen3-VL backbone to achieve the highest success rates on LabUtopia under in- and out-of-distribution conditions.
-
HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning
HumanoidMimicGen automatically generates large loco-manipulation datasets from few source demonstrations using whole-body planning, enabling visuomotor policies that outperform real-data-only training by 20% on a new nine-task benchmark.
-
HyperSim: A Holistic Sim-To-Real Framework For Robust Robotic Manipulation
HyperSim reports 80% and 95% sim-to-real success on two manipulation policies across 400 real executions by combining synthetic environment synthesis, adversarial trajectories, and co-training.
-
CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment
CoEnv introduces a compositional environment that integrates real and simulated spaces for multi-agent robotic collaboration, using real-to-sim reconstruction, VLM action synthesis, and validated sim-to-real transfer to achieve high success rates on multi-arm manipulation tasks.
-
Causal World Modeling for Robot Control
LingBot-VA combines video world modeling with policy learning via Mixture-of-Transformers, closed-loop rollouts, and asynchronous inference to improve robot manipulation in simulation and real settings.
-
A Practical Recipe Towards Improving Sim-and-Real Correlation for VLA Evaluation
Authors perform a cross-simulator, cross-policy empirical study of sim-to-real correlation for VLA policies and distill guidance on using simulation for policy improvement.
-
JoyAI-RA 0.1: A Foundation Model for Robotic Autonomy
JoyAI-RA is a multi-source pretrained VLA model that claims to bridge human-to-robot embodiment gaps via data unification and outperforms prior methods on generalization-heavy robotic tasks.