Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
hub Canonical reference
Genaug: Retargeting behaviors to unseen situations via generative augmentation.arXiv preprint arXiv:2302.06671
Canonical reference. 89% of citing Pith papers cite this work as background.
19
Pith papers citing it
2
external citations · external index
Background
89% of classified citations
hub tools
citation-role summary
background 9
citation-polarity summary
roles
background 9representative citing papers
π₀.₇ is a steerable generalist robotic model that uses rich multimodal prompts including language, subgoal images, and performance metadata to achieve out-of-the-box generalization across tasks and robot bodies.
DockAnywhere lifts single demonstrations to diverse docking points via structure-preserving augmentation and point-cloud spatial editing to improve viewpoint generalization in visuomotor policies for mobile manipulation.
DreamGen trains robot policies on synthetic trajectories from adapted video world models, enabling a humanoid robot to perform 22 new behaviors in seen and unseen environments from a single pick-and-place teleoperation dataset.
SuSIE uses a finetuned InstructPix2Pix diffusion model to propose subgoal images that guide a low-level goal-conditioned policy, achieving SOTA zero-shot performance on CALVIN and real-world manipulation.
Pose6DAug performs 3D multi-view object swapping via temporally coherent 6D pose trajectories to augment VLA data, reporting 16.5% relative success improvement on novel objects.
SKIP achieves 4.16x faster dense video rollouts for robot world models by synthesizing only multimodal-identified keyframes and interpolating the rest, preserving policy training effectiveness with minimal success rate drops.
Dense scene composition and instance fidelity in synthetic diffusion images drive better segmentation performance; SENSE framework exploits this to improve models on Cityscapes, COCO, and ADE20K.
SID achieves approximately 90% success on six real-world manipulation tasks with only two demonstrations under out-of-distribution initializations, with less than 10% performance drop under distractors and disturbances.
A protocol-driven multi-agent VLA system with visual verification and AugSmolVLA augmentation improves wet-lab robot execution over ACT, X-VLA, and SmolVLA on atomic, composite, and bimanual tasks.
Lucid-XR uses XR-headset physics simulation and physics-guided video generation to create synthetic data that trains robot policies transferring zero-shot to unseen real-world manipulation tasks.
GraspVLA shows that pretraining a grasping model on a billion synthetic action frames enables zero-shot open-vocabulary performance and sim-to-real transfer.
GR00T N1 is a new open VLA foundation model for humanoid robots that outperforms imitation learning baselines in simulation and shows strong performance on real-world bimanual manipulation tasks.
Gen2Act enables generalizable robot manipulation for unseen objects and novel motions by using zero-shot human video generation from web data to condition a policy trained on an order of magnitude less robot interaction data.
Octo is an open-source transformer-based generalist robot policy pretrained on 800k trajectories that serves as an effective initialization for finetuning across diverse robotic platforms.
Augmenting robot datasets via diffusion-based semantic inpainting enables manipulation policies to solve unseen tasks with new objects and improves robustness to novel distractors.
MimicGen creates over 50K robot demonstrations from roughly 200 human ones, allowing imitation learning to achieve strong performance on complex long-horizon tasks like assembly and coffee preparation.
The paper surveys 3D generation techniques for embodied AI and robotics, categorizing them into data generation, simulation environments, and sim-to-real bridging while identifying bottlenecks in physical validity and transfer.
The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.
citing papers explorer
-
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
-
${\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities
π₀.₇ is a steerable generalist robotic model that uses rich multimodal prompts including language, subgoal images, and performance metadata to achieve out-of-the-box generalization across tasks and robot bodies.
-
DockAnywhere: Data-Efficient Visuomotor Policy Learning for Mobile Manipulation via Novel Demonstration Generation
DockAnywhere lifts single demonstrations to diverse docking points via structure-preserving augmentation and point-cloud spatial editing to improve viewpoint generalization in visuomotor policies for mobile manipulation.
-
DreamGen: Unlocking Generalization in Robot Learning through Video World Models
DreamGen trains robot policies on synthetic trajectories from adapted video world models, enabling a humanoid robot to perform 22 new behaviors in seen and unseen environments from a single pick-and-place teleoperation dataset.
-
Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models
SuSIE uses a finetuned InstructPix2Pix diffusion model to propose subgoal images that guide a low-level goal-conditioned policy, achieving SOTA zero-shot performance on CALVIN and real-world manipulation.
-
Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation
Pose6DAug performs 3D multi-view object swapping via temporally coherent 6D pose trajectories to augment VLA data, reporting 16.5% relative success improvement on novel objects.
-
SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models
SKIP achieves 4.16x faster dense video rollouts for robot world models by synthesizing only multimodal-identified keyframes and interpolating the rest, preserving policy training effectiveness with minimal success rate drops.
-
What Makes Synthetic Data Effective in Image Segmentation
Dense scene composition and instance fidelity in synthetic diffusion images drive better segmentation performance; SENSE framework exploits this to improve models on Cityscapes, COCO, and ADE20K.
-
SID: Sliding into Distribution for Robust Few-Demonstration Manipulation
SID achieves approximately 90% success on six real-world manipulation tasks with only two demonstrations under out-of-distribution initializations, with less than 10% performance drop under distractors and disturbances.
-
BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation
A protocol-driven multi-agent VLA system with visual verification and AugSmolVLA augmentation improves wet-lab robot execution over ACT, X-VLA, and SmolVLA on atomic, composite, and bimanual tasks.
-
Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation
Lucid-XR uses XR-headset physics simulation and physics-guided video generation to create synthetic data that trains robot policies transferring zero-shot to unseen real-world manipulation tasks.
-
GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data
GraspVLA shows that pretraining a grasping model on a billion synthetic action frames enables zero-shot open-vocabulary performance and sim-to-real transfer.
-
GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
GR00T N1 is a new open VLA foundation model for humanoid robots that outperforms imitation learning baselines in simulation and shows strong performance on real-world bimanual manipulation tasks.
-
Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation
Gen2Act enables generalizable robot manipulation for unseen objects and novel motions by using zero-shot human video generation from web data to condition a policy trained on an order of magnitude less robot interaction data.
-
Octo: An Open-Source Generalist Robot Policy
Octo is an open-source transformer-based generalist robot policy pretrained on 800k trajectories that serves as an effective initialization for finetuning across diverse robotic platforms.
-
Scaling Robot Learning with Semantically Imagined Experience
Augmenting robot datasets via diffusion-based semantic inpainting enables manipulation policies to solve unseen tasks with new objects and improves robustness to novel distractors.
-
MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations
MimicGen creates over 50K robot demonstrations from roughly 200 human ones, allowing imitation learning to achieve strong performance on complex long-horizon tasks like assembly and coffee preparation.
-
3D Generation for Embodied AI and Robotic Simulation: A Survey
The paper surveys 3D generation techniques for embodied AI and robotics, categorizing them into data generation, simulation environments, and sim-to-real bridging while identifying bottlenecks in physical validity and transfer.
-
Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.