WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models
A robotics research paper on WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models.
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.
SkillWeave: Weaving Heterogeneous Demonstrations into Long-Horizon Manipulation Skills
A robotics research paper on SkillWeave: Weaving Heterogeneous Demonstrations into Long-Horizon Manipulation Skills.
Engineering 5.0 · Research 7.0 · Business 4.0
Immiscible Diffusion Policy: Preserving Multimodal Robot Actions through Label-Free Noise Assignment
A robotics research paper on Immiscible Diffusion Policy: Preserving Multimodal Robot Actions through Label-Free Noise Assignment.
Engineering 5.0 · Research 7.0 · Business 4.0
ESP: Energy-Score Policy for One-Step Multimodal Action Generation
A robotics research paper on ESP: Energy-Score Policy for One-Step Multimodal Action Generation.
Engineering 5.0 · Research 7.0 · Business 4.0
DepthWorld: 3D World Model for Robot Manipulation
A robotics research paper on DepthWorld: 3D World Model for Robot Manipulation.
Engineering 5.0 · Research 7.0 · Business 4.0
PEARS: Physical-Prior-Guided Efficient Adaptation via Failure Reasoning and Diffusion Steering for Tactile Manipulation
A robotics research paper on PEARS: Physical-Prior-Guided Efficient Adaptation via Failure Reasoning and Diffusion Steering for Tactile Manipulation.
Engineering 5.0 · Research 7.0 · Business 4.0
Reachability-Aware Diffusion Policy Optimization
A robotics research paper on Reachability-Aware Diffusion Policy Optimization.
Engineering 5.0 · Research 7.0 · Business 4.0
Benchmarking Generative Trajectory Models for Active-Inference Control
A robotics research paper on Benchmarking Generative Trajectory Models for Active-Inference Control.
Engineering 5.0 · Research 7.0 · Business 4.0
Demonstration-Calibrated Port-Hamiltonian Retuning for Manipulation Policies
A robotics research paper on Demonstration-Calibrated Port-Hamiltonian Retuning for Manipulation Policies.
Engineering 5.0 · Research 7.0 · Business 4.0
Robotizing Human Videos with Physically Consistent Interactions
A robotics research paper on Robotizing Human Videos with Physically Consistent Interactions.
Engineering 5.0 · Research 7.0 · Business 4.0
AdaTempo: Learning Shared Relative Tempo from Demonstrations for Faster Robot Manipulation
A robotics research paper on AdaTempo: Learning Shared Relative Tempo from Demonstrations for Faster Robot Manipulation.
Engineering 5.0 · Research 7.0 · Business 4.0
Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation
A robotics research paper on Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation.
Engineering 5.0 · Research 7.0 · Business 4.0
Text-to-3D Policy: Fine-Grained Language-Behavior Alignment for Unseen Specification Generalization
A robotics research paper on Text-to-3D Policy: Fine-Grained Language-Behavior Alignment for Unseen Specification Generalization.
Engineering 5.0 · Research 7.0 · Business 4.0
Diffusion Policy Improvement with Proposal-Conditioned Refinement Flows
A robotics research paper on Diffusion Policy Improvement with Proposal-Conditioned Refinement Flows.
Engineering 5.0 · Research 7.0 · Business 4.0
EquivDP3: A SIM(3)-Invariant Point-Cloud Encoder for Data-Efficient Humanoid Loco-Manipulation
A robotics research paper on EquivDP3: A SIM(3)-Invariant Point-Cloud Encoder for Data-Efficient Humanoid Loco-Manipulation.
Engineering 5.0 · Research 7.0 · Business 4.0
DROM: A Language-Guided Diffusion Framework for Multi-Skill Robotic Manipulation
A robotics research paper on DROM: A Language-Guided Diffusion Framework for Multi-Skill Robotic Manipulation.
Engineering 5.0 · Research 7.0 · Business 4.0
Safe Score Matching: Diffusion Policies with Hamilton-Jacobi Reachability for Online Safe Reinforcement Learning
A robotics research paper on Safe Score Matching: Diffusion Policies with Hamilton-Jacobi Reachability for Online Safe Reinforcement Learning.
Engineering 5.0 · Research 7.0 · Business 4.0
Principal Steering Subspaces for Online Adaptation of Frozen Generative Robot Policies
A robotics research paper on Principal Steering Subspaces for Online Adaptation of Frozen Generative Robot Policies.
Engineering 5.0 · Research 7.0 · Business 4.0
RoboFFT: Finetuning generative robot policy via online reinforcement learning with forward process
A robotics research paper on RoboFFT: Finetuning generative robot policy via online reinforcement learning with forward process.
Engineering 5.0 · Research 7.0 · Business 4.0
Constrained Flow Policy Updates: A Generalized Schrödinger Bridge View
A robotics research paper on Constrained Flow Policy Updates: A Generalized Schrödinger Bridge View.
Engineering 5.0 · Research 7.0 · Business 4.0