Digital Twin Calibration with Model-Based Reinforcement Learning

This paper presents a novel methodological framework, called the Actor-Simulator, that incorporates the calibration of digital twins into model-based reinforcement learning for more effective control of stochastic systems with complex nonlinear dynamics. Traditional model-based control often relies on restrictive structural assumptions (such as linear state transitions) and fails to account for parameter uncertainty in the model. These issues become particularly critical in industries such as biopharmaceutical manufacturing, where process dynamics are complex and not fully known, and only a limited amount of data is available. Our approach jointly calibrates the digital twin and searches for an optimal control policy, thus accounting for and reducing model error. We balance exploration and exploitation by using policy performance as a guide for data collection. This dual-component approach provably converges to the optimal policy, and outperforms existing methods in extensive numerical experiments based on the biopharmaceutical manufacturing domain.

Active Learning with Variational Quantum Circuits for Quantum Process Tomography

Quantum process tomography (QPT), used for reconstruction of an unknown quantum process from measurement data, is a fundamental tool for the diagnostic and full characterization of quantum systems. It relies on querying a set of quantum states as input to the quantum process. Previous works commonly use a straightforward strategy to select a set of quantum states randomly, overlooking differences in informativeness among quantum states. Since querying the quantum system requires multiple experiments that can be prohibitively costly, it is always the case that there are not enough quantum states for high-quality reconstruction. In this paper, we propose a general framework for active learning (AL) to adaptively select a set of informative quantum states that improves the reconstruction most efficiently. In particular, we introduce a learning framework that leverages the widely-used variational quantum circuits (VQCs) to perform the QPT task and integrate our AL algorithms into the query step. We design and evaluate three various types of AL algorithms: committee-based, uncertainty-based, and diversity-based, each exhibiting distinct advantages in terms of performance and computational cost. Additionally, we provide a guideline for selecting algorithms suitable for different scenarios. Numerical results demonstrate that our algorithms achieve significantly improved reconstruction compared to the baseline method that selects a set of quantum states randomly. Moreover, these results suggest that active learning based approaches are applicable to other complicated learning tasks in large-scale quantum information processing.

Sensitivity Analysis on Policy-Augmented Graphical Hybrid Models with Shapley Value Estimation

Driven by the critical challenges in biomanufacturing, including high complexity and high uncertainty, we propose a comprehensive and computationally efficient sensitivity analysis framework for general nonlinear policy-augmented knowledge graphical (pKG) hybrid models that characterize the risk- and science-based understandings of underlying stochastic decision process mechanisms. The criticality of each input (i.e., random factors, policy parameters, and model parameters) is measured by applying Shapley value (SV) sensitivity analysis to pKG (called SV-pKG), accounting for process causal interdependences. To quickly assess the SV for heavily instrumented bioprocesses, we approximate their dynamics with linear Gaussian pKG models and improve the SV estimation efficiency by utilizing the linear Gaussian properties. In addition, we propose an effective permutation sampling method with TFWW transformation and variance reduction techniques, namely the quasi-Monte Carlo and antithetic sampling methods, to further improve the sampling efficiency and estimation accuracy of SV for both general nonlinear and linear Gaussian pKG models. Our proposed framework can benefit efficient interpretation and support stable optimal process control in biomanufacturing.

Gradient-Free Supervised Learning using Spike-Timing-Dependent Plasticity for Image Recognition

An approach to supervised learning in spiking neural networks is presented using a gradient-free method combined with spike-timing-dependent plasticity for image recognition. The proposed network architecture is scalable to multiple layers, enabling the development of more complex and deeper SNN models. The effectiveness of this method is demonstrated by its application to the MNIST dataset, showing good learning accuracy. The proposed method provides a robust and efficient alternative to the backpropagation-based method in supervised learning.

Do Large Language Models Truly Grasp Mathematics? An Empirical Exploration

Despite their proficiency in math tasks, the mechanisms underlying LLMs' mathematical reasoning abilities remain a subject of debate. Recent studies suggest that chain-of-thought (CoT) prompts can bolster mathematical reasoning by encouraging LLMs to employ human-like logical reasoning (System 2), enabling them to excel on the Cognitive Reflection Test (CRT). To assess whether LLMs genuinely possess System 2-like logical reasoning, we introduced targeted modifications to CRT problems. Our findings reveal that, despite the use of CoT prompts, mainstream LLMs, including the latest o1-preview model, continue to exhibit a significant error rate. Further analysis indicates that they predominantly rely on System 1-like intuitive reasoning and pattern matching derived from training data, rather than demonstrating mastery of mathematical thinking. This discovery challenges the prevailing notion that LLMs possess genuine logical reasoning abilities and that CoT can enhance them. Consequently, this work may temper overly optimistic projections regarding LLMs' advancement toward artificial general intelligence.

Adjoint Sensitivity Analysis on Multi-Scale Bioprocess Stochastic Reaction Network

Motivated by the pressing challenges in the digital twin development for biomanufacturing process, we introduce an adjoint sensitivity analysis (SA) approach to expedite the learning of mechanistic model parameters. In this paper, we consider enzymatic stochastic reaction networks representing a multi-scale bioprocess mechanistic model that allows us to integrate disparate data from diverse production processes and leverage the information from existing macro-kinetic and genome-scale models. To support forward prediction and backward reasoning, we develop a convergent adjoint SA algorithm studying how the perturbations of model parameters and inputs (e.g., initial state) propagate through enzymatic reaction networks and impact on output trajectory predictions. This SA can provide a sample efficient and interpretable way to assess the sensitivities between inputs and outputs accounting for their causal dependencies. Our empirical study underscores the resilience of these sensitivities and illuminates a deeper comprehension of the regulatory mechanisms behind bioprocess through sensitivities.

Digital Twin Calibration for Biological System-of-Systems: Cell Culture Manufacturing Process

Biomanufacturing innovation relies on an efficient design of experiments (DoE) to optimize processes and product quality. Traditional DoE methods, ignoring the underlying bioprocessing mechanisms, often suffer from a lack of interpretability and sample efficiency. This limitation motivates us to create a new optimal learning approach that can guide a sequential DoEs for digital twin model calibration. In this study, we consider a multi-scale mechanistic model for cell culture process, also known as Biological Systems-of-Systems (Bio-SoS), as our digital twin. This model with modular design, composed of sub-models, allows us to integrate data across various production processes. To calibrate the Bio-SoS digital twin, we evaluate the mean squared error of model prediction and develop a computational approach to quantify the impact of parameter estimation error of individual sub-models on the prediction accuracy of digital twin, which can guide sample-efficient and interpretable DoEs.

Linear Noise Approximation Assisted Bayesian Inference on Mechanistic Model of Partially Observed Stochastic Reaction Network

To support mechanism online learning and facilitate digital twin development for biomanufacturing processes, this paper develops an efficient Bayesian inference approach for partially observed enzymatic stochastic reaction network (SRN), a fundamental building block of multi-scale bioprocess mechanistic model. To tackle the critical challenges brought by the nonlinear stochastic differential equations (SDEs)-based mechanistic model with partially observed state and having measurement error, an interpretable Bayesian updating linear noise approximation (LNA) metamodel, incorporating the structure information of the mechanistic model, is proposed to approximate the likelihood of observations. Then, an efficient posterior sampling approach is developed by utilizing the gradients of the derived likelihood to speed up the convergence of MCMC. The empirical study demonstrates that the proposed approach has a promising performance.

Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology

Large Language Models (LLMs) have gradually become the gateway for people to acquire new knowledge. However, attackers can break the model's security protection ("jail") to access restricted information, which is called "jailbreaking." Previous studies have shown the weakness of current LLMs when confronted with such jailbreaking attacks. Nevertheless, comprehension of the intrinsic decision-making mechanism within the LLMs upon receipt of jailbreak prompts is noticeably lacking. Our research provides a psychological explanation of the jailbreak prompts. Drawing on cognitive consistency theory, we argue that the key to jailbreak is guiding the LLM to achieve cognitive coordination in an erroneous direction. Further, we propose an automatic black-box jailbreaking method based on the Foot-in-the-Door (FITD) technique. This method progressively induces the model to answer harmful questions via multi-step incremental prompts. We instantiated a prototype system to evaluate the jailbreaking effectiveness on 8 advanced LLMs, yielding an average success rate of 83.9%. This study builds a psychological perspective on the explanatory insights into the intrinsic decision-making logic of LLMs.

TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection

Video moment retrieval (MR) and highlight detection (HD) based on natural language queries are two highly related tasks, which aim to obtain relevant moments within videos and highlight scores of each video clip. Recently, several methods have been devoted to building DETR-based networks to solve both MR and HD jointly. These methods simply add two separate task heads after multi-modal feature extraction and feature interaction, achieving good performance. Nevertheless, these approaches underutilize the reciprocal relationship between two tasks. In this paper, we propose a task-reciprocal transformer based on DETR (TR-DETR) that focuses on exploring the inherent reciprocity between MR and HD. Specifically, a local-global multi-modal alignment module is first built to align features from diverse modalities into a shared latent space. Subsequently, a visual feature refinement is designed to eliminate query-irrelevant information from visual features for modal interaction. Finally, a task cooperation module is constructed to refine the retrieval pipeline and the highlight score prediction process by utilizing the reciprocity between MR and HD. Comprehensive experiments on QVHighlights, Charades-STA and TVSum datasets demonstrate that TR-DETR outperforms existing state-of-the-art methods. Codes are available at \url{https://github.com/mingyao1120/TR-DETR}.