Flow Reversal Steering steers flow matching generalist policies by reversing suboptimal actions to nearby better modes, enabling improved zero-shot control, quick distillation, and RL bootstrapping in robotic manipulation.
arXiv preprint arXiv:2412.09858 (2024) 9
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative 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.
GLOVES learns flow models from limited expert demonstrations to selectively correct actions from non-expert policies or operators toward expert distributions using reverse-flow OOD detection as an intervention gate.
LWD is a fleet-scale offline-to-online RL framework that continually improves pretrained VLA policies using autonomous rollouts and human interventions, reaching 95% average success on real-world manipulation tasks.
RECAP enables a generalist VLA to self-improve via advantage-conditioned RL on mixed real-world data, more than doubling throughput and halving failure rates on hard manipulation tasks.
VLA-RL applies online RL to pretrained VLAs, yielding a 4.5% gain over strong baselines on 40 LIBERO manipulation tasks and matching commercial models like π₀-FAST.
InSight enables autonomous acquisition of manipulation primitives in VLAs via automated segmentation for steerability and a VLM-guided data flywheel that generates and integrates new demonstrations for tasks like pouring and sweeping.
An RL data generation pipeline with generalizable rewards and language annotations produces diverse synthetic datasets that improve multi-task policy generalization on three bimanual manipulation tasks.
AllDayNav encodes scene dynamics into a large model's parameters via RL and a multimodal memory, achieving near-100% success rates in lifelong navigation and outperforming map-based and VLM baselines.
DexPIE improves dexterous manipulation success rates by 37% over demo policies via real-world experience collection with adapted intervention, multi-stage DAgger, asynchronous relative-action inference, and optimality conditioning.
A semi-supervised MOL framework for diffusion models with generalization bounds depending only on specialist model complexity, extended to diffusion policies for sequential decisions.
JoyAI-Sim provides bidirectional Robot-Simulation-Human pathways for aligned model evaluation and data generation in robotics using the JoySim simulator as an evaluation layer and physical consistency filter.
citing papers explorer
-
Improving Robotic Generalist Policies via Flow Reversal Steering
Flow Reversal Steering steers flow matching generalist policies by reversing suboptimal actions to nearby better modes, enabling improved zero-shot control, quick distillation, and RL bootstrapping in robotic manipulation.
-
${\pi}_{0.7}$: 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.
-
Flow-based Policy Adaptation without Policy Updates
GLOVES learns flow models from limited expert demonstrations to selectively correct actions from non-expert policies or operators toward expert distributions using reverse-flow OOD detection as an intervention gate.
-
Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies
LWD is a fleet-scale offline-to-online RL framework that continually improves pretrained VLA policies using autonomous rollouts and human interventions, reaching 95% average success on real-world manipulation tasks.
-
$\pi^{*}_{0.6}$: a VLA That Learns From Experience
RECAP enables a generalist VLA to self-improve via advantage-conditioned RL on mixed real-world data, more than doubling throughput and halving failure rates on hard manipulation tasks.
-
VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
VLA-RL applies online RL to pretrained VLAs, yielding a 4.5% gain over strong baselines on 40 LIBERO manipulation tasks and matching commercial models like π₀-FAST.
-
InSight: Self-Guided Skill Acquisition via Steerable VLAs
InSight enables autonomous acquisition of manipulation primitives in VLAs via automated segmentation for steerability and a VLM-guided data flywheel that generates and integrates new demonstrations for tasks like pouring and sweeping.
-
Scalable Multi-Task Data Generation via Reinforcement Learning for Language-Conditioned Bimanual Dexterous Manipulation
An RL data generation pipeline with generalizable rewards and language annotations produces diverse synthetic datasets that improve multi-task policy generalization on three bimanual manipulation tasks.
-
AllDayNav: Lifelong Navigation via Real-World Reinforcement Learning
AllDayNav encodes scene dynamics into a large model's parameters via RL and a multimodal memory, achieving near-100% success rates in lifelong navigation and outperforming map-based and VLM baselines.
-
DexPIE: Stable Dexterous Policy Improvement from Real-World Experience
DexPIE improves dexterous manipulation success rates by 37% over demo policies via real-world experience collection with adapted intervention, multi-stage DAgger, asynchronous relative-action inference, and optimality conditioning.
-
Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning
A semi-supervised MOL framework for diffusion models with generalization bounds depending only on specialist model complexity, extended to diffusion policies for sequential decisions.
-
JoyAI-Sim: A Simulation-Enabled Interconversion Toolchain for the Embodied Data Pyramid
JoyAI-Sim provides bidirectional Robot-Simulation-Human pathways for aligned model evaluation and data generation in robotics using the JoySim simulator as an evaluation layer and physical consistency filter.