arXiv subjects

Xiaoxiao Lu

Publications and source records attributed to Xiaoxiao Lu.

3 recordsLinked to original sources

arXiv2026

Making Latent Evolution Explicit: Operator-Structured Transitions for World Action Models

World Action Models (WAMs) augment robot policies by predicting how task-relevant scene states may evolve under interaction. Recent WAMs increasingly perform such prediction in latent representation spaces, avoiding full appearance-level generation while preserving control-relevant information. Yet latent transitions are commonly realized with Transformer-based predictors whose inductive structure is centered on token interaction rather than temporal evolution. We study transition realization as an architectural choice distinct from predictive representation and prediction-policy coupling. We introduce the Latent Evolution Operator Network (LEON), which models latent evolution in a learned observable space through context-modulated operator-based propagation and additive forcing. Grounded in the controlled Koopman generator view of evolution, LEON organizes context-dependent transition variation around a shared evolution-operator structure while retaining a complementary path for additive change. Controlled dynamical systems verify the resulting evolution-specific inductive bias and the complementary roles of operator propagation and forcing. Across two WAM formulations that integrate latent prediction into the policy differently, LEON improves closed-loop performance and robustness while remaining effective under full transition replacement. These results establish transition realization as a consequential architectural choice in latent WAMs.

cs.LG↗

arXiv2026

Stable Long-Horizon PDE Forecasting via Latent Structured Spectral Propagators

Long-horizon forecasting of time-dependent partial differential equations (PDEs) is critical for characterizing the sustained evolution of physical systems. While neural operators have emerged as efficient surrogates, they typically learn implicit finite-time transitions from discrete observations. When deployed autoregressively, such propagators often suffer from rapid error accumulation and dynamic drift. To address this, we propose a neural forecasting framework that reformulates PDE rollout as learning a Structured Spectral Propagator (SSP) in a propagation-oriented latent space. Following an analysis-propagation-synthesis design, our framework: (i) maps physical states into a shared, time-consistent spatial representation; (ii) projects this space into a compact propagation state to isolate recurrent dynamics from fine-grained spatial details, thereby decoupling reconstruction fidelity from rollout regularity; and (iii) evolves retained spectral modes using a frequency-conditioned linear backbone complemented by a nonlinear spectral closure to account for truncated interactions. This explicit structuring endows the propagator with a strong inductive bias for coherent modal evolution. Extensive experiments demonstrate that SSP significantly outperforms state-of-the-art baselines, reducing relative $L_2$ errors by up to 48.9% and exhibiting improved stability in temporal extrapolation beyond the supervised horizon.

cs.LG↗

arXiv2020

NBFTP: A Dedicated Data Transfer System for Remote Astronomical Observation at Dome A

Dome A, Antarctica has been thought to be one of the best astronomical sites on the earth since decades ago. From it was first visited by astronomers in 2008, dozens of facilities for astronomical observation and site testing were deployed. Due to its special geographical location, the data and message exchange between Dome A and the domestic control center could only depend on Iridium. Because the link bandwidth of Iridium is extremely limited, meanwhile the network traffic cost is quite expensive and the network is rather unstable, the commonly used data transfer tools, such as rsync and scp, are not suitable in this case. In this paper, we design and implement a data transfer tool called NBFTP (narrow bandwidth file transfer protocol) for the astronomical observation of Dome A. NBFTP uses a uniform interface to arrange all types of data and matches specific transmission schemes for different data types according to rules. Break-point resuming and extensibility functions are also implemented. Our experimental results show that NBFTP consumes 60% less network traffic than rsync when detecting the data pending to be transferred. And when transferring small files of 1KB, the network traffic consumption of NBFTP is 40% less than rsync. However, as the file size increases, the network traffic consumption of NBFTP tends to approach rsync, but it is still smaller than rsync.

astro-ph.IM↗