Copertina

Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cao, Jiahang, Huang, Yize, Guo, Hanzhong, Zhang, Rui, Nan, Mu, Mai, Weijian, Wang, Jiaxu, Cheng, Hao, Sun, Jingkai, Han, Gang, Zhao, Wen, Zhang, Qiang, Guo, Yijie, Zheng, Qihao, Song, Chunfeng, Li, Xiao, Luo, Ping, Luo, Andrew F.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Robotics Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition
di: Cao, Jiahang, et al.
Pubblicazione: (2025)

Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotion
di: Zhang, Qiang, et al.
Pubblicazione: (2025)

NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity
di: Mai, Weijian, et al.
Pubblicazione: (2026)

LiPS: Large-Scale Humanoid Robot Reinforcement Learning with Parallel-Series Structures
di: Zhang, Qiang, et al.
Pubblicazione: (2025)

DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction
di: Sun, Jingkai, et al.
Pubblicazione: (2025)

Trinity: A Modular Humanoid Robot AI System
di: Sun, Jingkai, et al.
Pubblicazione: (2025)

Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models
di: Cao, Jiahang, et al.
Pubblicazione: (2024)

ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network
di: Zhang, Qiang, et al.
Pubblicazione: (2025)

Reinforcement Learning with Generalizable Gaussian Splatting
di: Wang, Jiaxu, et al.
Pubblicazione: (2024)

Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras
di: Sun, Jingkai, et al.
Pubblicazione: (2025)

Occupancy World Model for Robots
di: Zhang, Zhang, et al.
Pubblicazione: (2025)

E2H: A Two-Stage Non-Invasive Neural Signal Driven Humanoid Robotic Whole-Body Control Framework
di: Duan, Yiqun, et al.
Pubblicazione: (2024)

Mamba as Decision Maker: Exploring Multi-scale Sequence Modeling in Offline Reinforcement Learning
di: Cao, Jiahang, et al.
Pubblicazione: (2024)

Expert Composer Policy: Scalable Skill Repertoire for Quadruped Robots
di: Christmann, Guilherme, et al.
Pubblicazione: (2024)

HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots
di: Zhang, Qiang, et al.
Pubblicazione: (2025)

Neuro-3D: Towards 3D Visual Decoding from EEG Signals
di: Guo, Zhanqiang, et al.
Pubblicazione: (2024)

DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream
di: He, Junhao, et al.
Pubblicazione: (2025)

Provincial Industrial Policy and Corporate Emissions: Evidence From China
di: Nan Lin, et al.
Pubblicazione: (2025)

Fast Visuomotor Policy for Robotic Manipulation
di: Jia, Jingkai, et al.
Pubblicazione: (2025)

Fully Spiking Neural Network for Legged Robots
di: Jiang, Xiaoyang, et al.
Pubblicazione: (2023)

Entropy-based Training Methods for Scalable Neural Implicit Sampler
di: Luo, Weijian, et al.
Pubblicazione: (2023)

AttenA+: Rectifying Action Inequality in Robotic Foundation Models
di: Peng, Daojie, et al.
Pubblicazione: (2026)

Vision-based Vehicle Re-identification in Bridge Scenario using Flock Similarity
di: Zhang, Chunfeng, et al.
Pubblicazione: (2024)

Whole-body Humanoid Robot Locomotion with Human Reference
di: Zhang, Qiang, et al.
Pubblicazione: (2024)

RISE: Self-Improving Robot Policy with Compositional World Model
di: Yang, Jiazhi, et al.
Pubblicazione: (2026)

Spiking Diffusion Models
di: Cao, Jiahang, et al.
Pubblicazione: (2024)

Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation
di: Yang, Yijie, et al.
Pubblicazione: (2024)

FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulation
di: Zhang, Qinglun, et al.
Pubblicazione: (2024)

MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy
di: Wang, Jiaxu, et al.
Pubblicazione: (2026)

SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning
di: Mai, Weijian, et al.
Pubblicazione: (2025)

Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation
di: Jiang, Yicheng, et al.
Pubblicazione: (2026)

Flow Generator Matching
di: Huang, Zemin, et al.
Pubblicazione: (2024)

SPARR: Simulation-based Policies with Asymmetric Real-world Residuals for Assembly
di: Guo, Yijie, et al.
Pubblicazione: (2026)

LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots
di: Wu, Peilin, et al.
Pubblicazione: (2024)

PDRIMA: A Policy-Driven Runtime Integrity Measurement and Attestation Approach for ARM TrustZone-based TEE
di: Mao, Jingkai, et al.
Pubblicazione: (2025)

MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation
di: Wang, Jiaxu, et al.
Pubblicazione: (2026)

Query-based Semantic Gaussian Field for Scene Representation in Reinforcement Learning
di: Wang, Jiaxu, et al.
Pubblicazione: (2024)

Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots
di: Cui, Wei, et al.
Pubblicazione: (2025)

Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy
di: Ni, Minheng, et al.
Pubblicazione: (2024)

Learning Stable Robot Grasping with Transformer-based Tactile Control Policies
di: Puang, En Yen, et al.
Pubblicazione: (2024)