GeoProp: Grounding Robot State in Vision for Generalist Manipulation
A robotics research paper on GeoProp: Grounding Robot State in Vision for Generalist Manipulation.
Engineering 5.0 · Research 7.0 · Business 4.0
Diffusion Policy Papers, Code and Reading Roadmap
Diffusion Policy methods generate robot action sequences using diffusion models, especially for robot manipulation tasks.
Technical roadmap
Start from Diffusion Policy, then read follow-up work on visuomotor policies, language-conditioned manipulation, real-robot deployment and imitation learning.
Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF
A robotics research paper on Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF.
Engineering 5.0 · Research 7.0 · Business 4.0
RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation
A robotics research paper on RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation.
Engineering 5.0 · Research 7.0 · Business 4.0
KAM-WM: Kinematic Affordance Maps from Latent World Models for Robot Manipulation
A robotics research paper on KAM-WM: Kinematic Affordance Maps from Latent World Models for Robot Manipulation.
Engineering 5.0 · Research 7.0 · Business 4.0
Mask2Real-WM: Segmentation Masks as a Sim-to-Real Bridge for Controllable Dexterous World Models
A robotics research paper on Mask2Real-WM: Segmentation Masks as a Sim-to-Real Bridge for Controllable Dexterous World Models.
Engineering 5.0 · Research 7.0 · Business 4.0
High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matching
A robotics research paper on High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matching.
Engineering 5.0 · Research 7.0 · Business 4.0
FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement
A robotics research paper on FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement.
Engineering 5.0 · Research 7.0 · Business 4.0
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
A robotics research paper on Diffusion-GR2: Diffusion Generative Reasoning Re-ranker.
Engineering 5.0 · Research 7.0 · Business 4.0
Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors
A robotics research paper on Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors.
Engineering 5.0 · Research 7.0 · Business 4.0
ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies
A robotics research paper on ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies.
Engineering 5.0 · Research 7.0 · Business 4.0
ChronoFlow-Policy: Unifying Past-Current-Future Interaction Flow in Visuomotor Policy Learning
A robotics research paper on ChronoFlow-Policy: Unifying Past-Current-Future Interaction Flow in Visuomotor Policy Learning.
Engineering 5.0 · Research 7.0 · Business 4.0
From Grasps to Dexterity: Large-Scale Grasp Pretraining for Dexterous Manipulation
A robotics research paper on From Grasps to Dexterity: Large-Scale Grasp Pretraining for Dexterous Manipulation.
Engineering 5.0 · Research 7.0 · Business 4.0
Learning Transferable Dynamics Priors from Action to World Modeling
A robotics research paper on Learning Transferable Dynamics Priors from Action to World Modeling.
Engineering 5.0 · Research 7.0 · Business 4.0
Keypose Exploration: Efficient Automatic Trajectory Labelling and Cross-Embodiment Policy Transfer
A robotics research paper on Keypose Exploration: Efficient Automatic Trajectory Labelling and Cross-Embodiment Policy Transfer.
Engineering 5.0 · Research 7.0 · Business 4.0
RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance
A robotics research paper on RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance.
Engineering 5.0 · Research 7.0 · Business 4.0
Bridging Handheld and Teleoperated Supervision for Contact-Rich Manipulation via State-Gated Experts
A robotics research paper on Bridging Handheld and Teleoperated Supervision for Contact-Rich Manipulation via State-Gated Experts.
Engineering 5.0 · Research 7.0 · Business 4.0
Humanoid-DART: Humanoid Loco-Manipulation using Diffusion-guided Augmentation through Relabeling and Tracking
A robotics research paper on Humanoid-DART: Humanoid Loco-Manipulation using Diffusion-guided Augmentation through Relabeling and Tracking.
Engineering 5.0 · Research 7.0 · Business 4.0
DynaMOMA: Instantaneous Prediction of Grasp Poses for Mobile Manipulation of Dynamic Objects
A robotics research paper on DynaMOMA: Instantaneous Prediction of Grasp Poses for Mobile Manipulation of Dynamic Objects.
Engineering 5.0 · Research 7.0 · Business 4.0
Action ControlNet: A Lightweight Delay-Aware Adapter for Smooth Asynchronous Control in Vision-Language-Action Models
A robotics research paper on Action ControlNet: A Lightweight Delay-Aware Adapter for Smooth Asynchronous Control in Vision-Language-Action Models.
Engineering 5.0 · Research 7.0 · Business 4.0
dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models
A robotics research paper on dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models.
Engineering 5.0 · Research 7.0 · Business 4.0