paper-with-me

Papers

Hydra-0: Action Flow for Generalist World Modeling and Control

2026-08-18 · Hongyu Li, Bowen Wen, Xinghao Zhu, Yixuan Wang, Yilun Du, Yunzhu Li, George Konidaris, Stan Birchfield, Soha Pouya, Chenran Li, Yan Chang arxiv

We introduce Hydra-0, a generalist world model conditioned on action flow, which represents robot actions as pixel motion. This shared visual interface enables generalist world modeling and control by learning action consequences across embodiments, tasks, environments, and video-generation backbones. Our best configuration achieves 90.4% lower robot-motion error and 60.2% lower object-motion error than our action-conditioned baseline, while supporting zero-shot composition and data-efficient adaptation. On the RoboLab benchmark, Hydra-0 achieves a Pearson correlation of r=0.96 between replayed and reference success rates. Finally, we uncover an emergent inverse mode of this interface: a world action model that predicts compatible robot motion from desired object flow transferred from a human demonstration. A trained action head maps the resulting latent features to executable actions without requiring task-specific expert robot demonstrations. Together, these results demonstrate the potential of action flow as a shared control interface connecting heterogeneous training data, open-loop policy evaluation, and robot control.

📄 PDF Abstract BibTeX arXiv:2608.18077

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Improving Robotic Generalist Policies via Flow Reversal Steering

2026-06-11 · Andy Tang, William Chen, Andrew Wagenmaker, Chelsea Finn 외 arxiv

Generalist policies can learn a wide range of skills from diverse robot datasets. In order to solve or improve on challenging new tasks, we need a way to infer and invoke the appropriate actions from the policy's rich be…

Reinforcement Learning

Towards Energy Efficient Control for Commercial Heavy-Duty Mobile Cranes: Modeling Hydraulic Pressures using Machine Learning

2023-07-31 · Abdolreza Taheri, Robert Pettersson, Pelle Gustafsson, Joni Pajarinen 외

A sizable part of the fleet of heavy-duty machinery in the construction equipment industry uses the conventional valve-controlled load-sensing hydraulics. Rigorous climate actions towards reducing CO$_{2}$ emissions has …

HydraCIL: Decoupled Class-Incremental Learning through Prototype-Guided Multi-Head Classifiers

2026-06-08 · Daniel Vila-Cruz, Laura Morán-Fernández, Verónica Bolón-Canedo arxiv

We present HydraCIL, a decoupled continual learning model based on prototype-guided multi-head classifiers, targeting sustainable deployment in embedded and resource-constrained environments. While most Class-Incremental…

class-incremental learningContinual Learning

HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL

2026-08-17 · Langzhe Gu, Chengkai Hou, Meng Li, Xinhua Wang 외 arxiv

Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulati…

Dimensionality ReductionReinforcement Learning

Physics-Informed Learning of Flow Distribution and Receiver Heat Losses in Parabolic Trough Solar Fields

2025-12-11 · Stefan Matthes, Markus Schramm arxiv

Parabolic trough Concentrating Solar Power (CSP) plants operate large hydraulic networks of collector loops that must deliver a uniform outlet temperature despite spatially heterogeneous optical performance, heat losses,…