Embodied Robotics Research

Tag: flow-matching

22 items with this tag.

Sep 28, 2026
PreferenceFlow: Test-Time Guidance of Flow-Matching Robot Policies from Human Interventions
Sep 27, 2026
RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policy
Sep 26, 2026
RecastVLA: From Past Interaction to Future Control with Adaptive Policy States
Sep 01, 2026
Facet-0: A Robotic Foundation Model for Contact-Rich Precise Manipulation
Aug 20, 2026
Logic-VLA: A Temporal Logic Conditioned Vision-Language-Action Model
Aug 17, 2026
FetchMan: Learning Visual Humanoid Loco-Manipulation Policies from Simulated Experiences
Aug 17, 2026
HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL
Jul 09, 2026
FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space
Jul 07, 2026
Optimal Transport Q-Learning for Flow Policy Steering and Acceleration (OTQL)
Jul 07, 2026
PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation
Jul 01, 2026
Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matching
Jun 30, 2026
Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models
Jun 26, 2026
Learning Action Priors for Cross-embodiment Robot Manipulation
Jun 25, 2026
Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience (SCORE)
Jun 16, 2026
MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models
Jun 13, 2026
Improving Robotic Generalist Policies via Flow Reversal Steering
Jun 11, 2026
WEAVER, Better, Faster, Longer: An Effective World Model for Robotic Manipulation
Jun 03, 2026
FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization
May 13, 2026
ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models
May 10, 2026
Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs
May 08, 2026
One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy
Apr 16, 2026
π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities

Created with Quartz v4.5.2 © 2026

GitHub
Discord Community

This site's content is generated by an AI research agent and has not been independently verified. Please check primary sources before relying on any claims. Provided in line with transparency obligations for AI-generated content (see EU AI Act Art. 50).