Selected work

Representative Papers

CUBICS: Situation-aware performance estimation for safety-relevant ML components

Aug 17, 2026

This study addresses the challenge that safety-critical ML component performance is highly scenario-dependent yet lacks modular field assessment capabilities. We propose CUBICS, a framework that partitions the operational domain into specific contexts and employs subjective logic with Bayesian inference to dynamically update component-level probabilistic assurances, deriving overall risk through context frequency analysis. The core contribution lies in enabling context-aware modular evaluation without requiring a monolithic system model, thereby overcoming the limitations of traditional global failure probabilities. Consequently, this work provides effective building blocks for safety assurance of safety-critical ML systems based on field data, facilitating more granular and adaptive risk quantification in dynamic environments.

0 citationsRead paper

Lindblad-Inspired Multi-Timescale Reservoir Computing with Separable Rotation and Dissipation

Jul 27, 2026

This work addresses the limitations of conventional reservoir computing, which struggles to independently control signal mixing and memory forgetting while lacking global stability guarantees. Inspired by the Lindblad equation, the authors introduce dissipative dynamics from open quantum systems into classical reservoirs, proposing a multi-timescale damped rotating reservoir. By employing orthogonal modes, the approach explicitly decouples rotation (for mixing) and dissipation (for forgetting). Stability of the echo state network is directly ensured through a tunable decay spectrum, eliminating the need for post-hoc spectral scaling. The method achieves state-of-the-art performance on the NARMA-20 and Lorenz-63 prediction tasks as well as linear memory benchmarks, demonstrating consistently competitive results across multiple standard datasets.

0 citationsRead paper

Self-Healing Coordination in Cognitive Swarm Agents with Bloch-Type Perceptual Memory

Jul 12, 2026

This work addresses the challenge that conventional reactive swarms, lacking internal perceptual states, struggle to regain coordination following disturbances. To overcome this limitation, the authors propose a perceptual memory mechanism grounded in Bloch-type slow–fast dynamics, which couples slow regulatory variables with perceptual registers to operationally encode history-dependent cues. This endows the swarm with non-Markovian self-healing coordination capabilities. Evaluated in a drone migration task within aperiodic obstacle environments, the proposed architecture markedly accelerates the restoration of spatial connectivity after fragmentation. It consistently outperforms memoryless and partial-feedback baselines across multiple metrics, including recovery time, swarm reassembly completeness, polar order consistency, and path efficiency.

0 citationsRead paper

jNO: A JAX Library for Neural Operator and Foundation Model Training

May 11, 2026

This work addresses the lack of an efficient and flexible JAX-native framework for neural operators and physics-informed foundation models. We propose a unified JAX-based training library that constructs an end-to-end differentiable programming model through symbolic tracing, encompassing domain specification, model invocation, residual computation, supervised loss, and diagnostics. The framework tightly integrates automatic differentiation, compilation optimizations, and physics-constrained modeling, enabling seamless composition of multiple models, fine-grained parameter-level control, and hyperparameter tuning. Crucially, it allows effortless switching among operator regression, mesh-aware residual evaluation, and PDE-constrained training paradigms without code refactoring, substantially enhancing development efficiency and training flexibility. A complete implementation is publicly released.

0 citationsRead paper

Physics-informed fine-tuning of foundation models for partial differential equations

Mar 16, 2026

This work addresses the challenge of efficiently adapting pre-trained foundation models for partial differential equations (PDEs) under data scarcity and distribution shift. We propose a physics-informed fine-tuning framework that incorporates physical constraints—such as PDE residuals and boundary conditions—directly into the fine-tuning objective, enabling data-efficient adaptation without requiring ground-truth solutions. To our knowledge, this is the first systematic demonstration of the effectiveness of physics-informed fine-tuning for transferring PDE foundation models. By integrating a hybrid fine-tuning strategy, our approach significantly enhances out-of-distribution generalization. Experiments show that, even in the absence of ground-truth solutions, our method achieves accuracy comparable to purely data-driven approaches on unseen PDE tasks and consistently outperforms them when only limited data are available.

0 citationsRead paper

Recent publications

Latest Papers

CUBICS: Situation-aware performance estimation for safety-relevant ML components

Aug 17, 2026

This study addresses the challenge that safety-critical ML component performance is highly scenario-dependent yet lacks modular field assessment capabilities. We propose CUBICS, a framework that partitions the operational domain into specific contexts and employs subjective logic with Bayesian inference to dynamically update component-level probabilistic assurances, deriving overall risk through context frequency analysis. The core contribution lies in enabling context-aware modular evaluation without requiring a monolithic system model, thereby overcoming the limitations of traditional global failure probabilities. Consequently, this work provides effective building blocks for safety assurance of safety-critical ML systems based on field data, facilitating more granular and adaptive risk quantification in dynamic environments.

0 citationsRead paper

Lindblad-Inspired Multi-Timescale Reservoir Computing with Separable Rotation and Dissipation

Jul 27, 2026

This work addresses the limitations of conventional reservoir computing, which struggles to independently control signal mixing and memory forgetting while lacking global stability guarantees. Inspired by the Lindblad equation, the authors introduce dissipative dynamics from open quantum systems into classical reservoirs, proposing a multi-timescale damped rotating reservoir. By employing orthogonal modes, the approach explicitly decouples rotation (for mixing) and dissipation (for forgetting). Stability of the echo state network is directly ensured through a tunable decay spectrum, eliminating the need for post-hoc spectral scaling. The method achieves state-of-the-art performance on the NARMA-20 and Lorenz-63 prediction tasks as well as linear memory benchmarks, demonstrating consistently competitive results across multiple standard datasets.

0 citationsRead paper

Self-Healing Coordination in Cognitive Swarm Agents with Bloch-Type Perceptual Memory

Jul 12, 2026

This work addresses the challenge that conventional reactive swarms, lacking internal perceptual states, struggle to regain coordination following disturbances. To overcome this limitation, the authors propose a perceptual memory mechanism grounded in Bloch-type slow–fast dynamics, which couples slow regulatory variables with perceptual registers to operationally encode history-dependent cues. This endows the swarm with non-Markovian self-healing coordination capabilities. Evaluated in a drone migration task within aperiodic obstacle environments, the proposed architecture markedly accelerates the restoration of spatial connectivity after fragmentation. It consistently outperforms memoryless and partial-feedback baselines across multiple metrics, including recovery time, swarm reassembly completeness, polar order consistency, and path efficiency.

0 citationsRead paper

jNO: A JAX Library for Neural Operator and Foundation Model Training

May 11, 2026

This work addresses the lack of an efficient and flexible JAX-native framework for neural operators and physics-informed foundation models. We propose a unified JAX-based training library that constructs an end-to-end differentiable programming model through symbolic tracing, encompassing domain specification, model invocation, residual computation, supervised loss, and diagnostics. The framework tightly integrates automatic differentiation, compilation optimizations, and physics-constrained modeling, enabling seamless composition of multiple models, fine-grained parameter-level control, and hyperparameter tuning. Crucially, it allows effortless switching among operator regression, mesh-aware residual evaluation, and PDE-constrained training paradigms without code refactoring, substantially enhancing development efficiency and training flexibility. A complete implementation is publicly released.

0 citationsRead paper

Physics-informed fine-tuning of foundation models for partial differential equations

Mar 16, 2026

This work addresses the challenge of efficiently adapting pre-trained foundation models for partial differential equations (PDEs) under data scarcity and distribution shift. We propose a physics-informed fine-tuning framework that incorporates physical constraints—such as PDE residuals and boundary conditions—directly into the fine-tuning objective, enabling data-efficient adaptation without requiring ground-truth solutions. To our knowledge, this is the first systematic demonstration of the effectiveness of physics-informed fine-tuning for transferring PDE foundation models. By integrating a hybrid fine-tuning strategy, our approach significantly enhances out-of-distribution generalization. Experiments show that, even in the absence of ground-truth solutions, our method achieves accuracy comparable to purely data-driven approaches on unseen PDE tasks and consistently outperforms them when only limited data are available.

0 citationsRead paper