FlowForge: A Staged Local Rollout Engine for Flow-Field Prediction

2026-04-21 · Xiaowen Zhang, Ziming Zhou, Fengnian Zhao, David L. S. Hung arxiv

Deep learning surrogates for CFD flow-field prediction often rely on large, complex models, which can be slow and fragile when data are noisy or incomplete. We introduce FlowForge, a staged local rollout engine that predicts future flow fields by compiling a locality-preserving update schedule and executing it with a shared lightweight local predictor. Rather than producing the next frame in a single global pass, FlowForge rewrites spatial sites stage by stage so that each update conditions only on bounded local context exposed by earlier stages. This compile-execute design aligns inference with short-range physical dependence, keeps latency predictable, and limits error amplification from global mixing. Across PDEBench, CFDBench, and BubbleML, FlowForge matches or improves upon strong baselines in pointwise accuracy, delivers consistently better robustness to noise and missing observations, and maintains stable multi-step rollout behavior while reducing per-step latency.

📄 PDF Abstract BibTeX arXiv:2604.18953

Code (0)

등록된 구현이 없습니다.

Automating Staged Rollout with Reinforcement Learning

2022-04-01 · Shadow Pritchard, Vidhyashree Nagaraju, Lance Fiondella

Staged rollout is a strategy of incrementally releasing software updates to portions of the user population in order to accelerate defect discovery without incurring catastrophic outcomes such as system wide outages. Som…

Multi-Objective Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Specification-Driven Generation and Evaluation of Discrete-Event World Models via the DEVS Formalism

2026-03-04 · Zheyu Chen, Huiteng Zhuang, Zhuohuan Li, Chuanhao Li arxiv

World models are central to LLM agents that must evaluate actions over long horizons. Yet much existing work focuses on environments governed by physical dynamics or spatial structure, whereas many high-impact domains, i…

The Alignment Flywheel: A Governance-Centric Hybrid MAS for Architecture-Agnostic Safety

2026-02-28 · Elias Malomgré, Pieter Simoens arxiv

Multi-agent systems provide mature methodologies for role decomposition, coordination, and normative governance, capabilities that remain essential as increasingly powerful autonomous decision components are embedded wit…

Rollout-Training Co-Design for Efficient LLM-Based Multi-Agent Reinforcement Learning

2026-02-10 · Zhida Jiang, Zhaolong Xing, Jiawei Lu, Yipei Niu 외 arxiv

Despite algorithm-level innovations for multi-agent reinforcement learning (MARL), the underlying networked infrastructure for large-scale MARL training remains underexplored. Existing training frameworks primarily optim…

Multi-agent Reinforcement Learning

Contour Flow: Middle-Level Motion Estimation by Combining Motion Segmentation and Contour Alignment

2015-12-01 · ICCV 2015 12 · Huijun Di, Qingxuan Shi, Feng Lv, Ming Qin 외

Our goal is to estimate contour flow (the contour pairs with consistent point correspondence) from inconsistent contours extracted independently in two video frames. We formulate the contour flow estimation locally as a …

Motion Estimation Motion Segmentation Optical Flow Estimation