Yongchao Huang

Yongchao Huang

Human decision-making is sequential and uncertainty-aware, yet standard neural networks often rely on static, dense forward computation with limited visibility into evidence acquisition, uncertainty evolution, or when computation should stop. We introduce \textbf{Neural Bayesian Sequential Routing (NBSR)}, a framework that models neural inference as active evidence accumulation over a hierarchical Directed Acyclic Graph (DAG). Within a Dirichlet--Categorical conjugate framework, neural experts query a persistent global knowledge oracle to extract positive evidence vectors, which act as pseudo-counts and update a Dirichlet belief state by exact conjugate addition. Coupled with a Gumbel-Softmax Straight-Through estimator, this update enables hard, path-dependent routing while preserving surrogate gradients for end-to-end training. The resulting Dirichlet precision and entropy provide mechanisms for uncertainty quantification, entropy-based early exiting, OOD abstention, and cost-aware evidence acquisition. We prove that, under strictly positive evidence extraction, total Dirichlet precision increases monotonically along any valid trajectory and marginal predictive variance is bounded, formalizing sequential ``hypothesis sharpening''; under idealized capacity and optimization assumptions, the terminal Dirichlet expectation recovers the Bayes-optimal conditional distribution. Empirical evaluations across visual categorization, structured medical diagnosis, language modeling, partially observable control, and cost-aware Bayesian experimental design show that NBSR achieves competitive predictive performance while providing transparent routing traces, path-dependent evidence attribution, uncertainty-aware decision control, and resource-rational inference. Overall, NBSR offers a mathematically grounded framework for interpretable, modular, and resource-rational agentic AI.

Yongchao Huang

In this work, we investigated the application of score-based gradient learning in discriminative and generative classification settings. Score function can be used to characterize data distribution as an alternative to density. It can be efficiently learned via score matching, and used to flexibly generate credible samples to enhance discriminative classification quality, to recover density and to build generative classifiers. We analysed the decision theories involving score-based representations, and performed experiments on simulated and real-world datasets, demonstrating its effectiveness in achieving and improving binary classification performance, and robustness to perturbations, particularly in high dimensions and imbalanced situations.

Yongchao Huang, Hassan Raza

Modern self-supervised predictive architectures excel at capturing complex statistical correlations from high-dimensional data but lack mechanisms to internalize verifiable human logic, leaving them susceptible to spurious correlations and shortcut learning. Conversely, traditional rule-based inference systems offer rigorous, interpretable logic but suffer from discrete boundaries and NP-hard combinatorial explosion. To bridge this divide, we propose a bidirectional neuro-symbolic framework centered around Rule-informed Joint-Embedding Predictive Architectures (RiJEPA). In the first direction, we inject structured inductive biases into JEPA training via Energy-Based Constraints (EBC) and a multi-modal dual-encoder architecture. This fundamentally reshapes the representation manifold, replacing arbitrary statistical correlations with geometrically sound logical basins. In the second direction, we demonstrate that by relaxing rigid, discrete symbolic rules into a continuous, differentiable logic, we can bypass traditional combinatorial search for new rule generation. By leveraging gradient-guided Langevin diffusion within the rule energy landscape, we introduce novel paradigms for continuous rule discovery, which enable unconditional joint generation, conditional forward and abductive inference, and marginal predictive translation. Empirical evaluations on both synthetic topological simulations and a high-stakes clinical use case confirm the efficacy of our approach. Ultimately, this framework establishes a powerful foundation for robust, generative, and interpretable neuro-symbolic representation learning.

Yongchao Huang

A new variational inference method, SPH-ParVI, based on smoothed particle hydrodynamics (SPH), is proposed for sampling partially known densities (e.g. up to a constant) or sampling using gradients. SPH-ParVI simulates the flow of a fluid under external effects driven by the target density; transient or steady state of the fluid approximates the target density. The continuum fluid is modelled as an interacting particle system (IPS) via SPH, where each particle carries smoothed properties, interacts and evolves as per the Navier-Stokes equations. This mesh-free, Lagrangian simulation method offers fast, flexible, scalable and deterministic sampling and inference for a class of probabilistic models such as those encountered in Bayesian inference and generative modelling.

Yongchao Huang

Self-supervised representation learning often relies on deterministic predictive architectures to align context and target views in latent space. While effective in many settings, such methods are limited in genuinely multi-modal inverse problems, where squared-loss prediction collapses towards conditional averages, and they frequently depend on architectural asymmetries to prevent representation collapse. In this work, we propose a probabilistic alternative based on generative joint modeling. We introduce Gaussian Joint Embeddings (GJE) and its multi-modal extension, Gaussian Mixture Joint Embeddings (GMJE), which model the joint density of context and target representations and replace black-box prediction with closed-form conditional inference under an explicit probabilistic model. This yields principled uncertainty estimates and a covariance-aware objective for controlling latent geometry. We further identify a failure mode of naive empirical batch optimization, which we term the Mahalanobis Trace Trap, and develop several remedies spanning parametric, adaptive, and non-parametric settings, including prototype-based GMJE, conditional Mixture Density Networks (GMJE-MDN), topology-adaptive Growing Neural Gas (GMJE-GNG), and a Sequential Monte Carlo (SMC) memory bank. In addition, we show that standard contrastive learning can be interpreted as a degenerate non-parametric limiting case of the GMJE framework. Experiments on synthetic multi-modal alignment tasks and vision benchmarks show that GMJE recovers complex conditional structure, learns competitive discriminative representations, and defines latent densities that are better suited to unconditional sampling than deterministic or unimodal baselines.

Yongchao Huang

A new gradient-based particle sampling method, MPM-ParVI, based on material point method (MPM), is proposed for variational inference. MPM-ParVI simulates the deformation of a deformable body (e.g. a solid or fluid) under external effects driven by the target density; transient or steady configuration of the deformable body approximates the target density. The continuum material is modelled as an interacting particle system (IPS) using MPM, each particle carries full physical properties, interacts and evolves following conservation dynamics. This easy-to-implement ParVI method offers deterministic sampling and inference for a class of probabilistic models such as those encountered in Bayesian inference (e.g. intractable densities) and generative modelling (e.g. score-based).

Yongchao Huang

Joint Embedding Predictive Architectures (JEPA) offer a scalable paradigm for self-supervised learning by predicting latent representations rather than reconstructing high-entropy observations. However, existing formulations rely on \textit{deterministic} regression objectives, which mask probabilistic semantics and limit its applicability in stochastic control. In this work, we introduce \emph{Variational JEPA (VJEPA)}, a \textit{probabilistic} generalization that learns a predictive distribution over future latent states via a variational objective. We show that VJEPA unifies representation learning with Predictive State Representations (PSRs) and Bayesian filtering, establishing that sequential modeling does not require autoregressive observation likelihoods. Theoretically, we prove that VJEPA representations can serve as sufficient information states for optimal control without pixel reconstruction, while providing formal guarantees for collapse avoidance. We further propose \emph{Bayesian JEPA (BJEPA)}, an extension that factorizes the predictive belief into a learned dynamics expert and a modular prior expert, enabling zero-shot task transfer and constraint (e.g. goal, physics) satisfaction via a Product of Experts. Empirically, through a noisy environment experiment, we demonstrate that VJEPA and BJEPA successfully filter out high-variance nuisance distractors that cause representation collapse in generative baselines. By enabling principled uncertainty estimation (e.g. constructing credible intervals via sampling) while remaining likelihood-free regarding observations, VJEPA provides a foundational framework for scalable, robust, uncertainty-aware planning in high-dimensional, noisy environments.

Yongchao Huang

The specification of prior distributions is fundamental in Bayesian inference, yet it remains a significant bottleneck. The prior elicitation process is often a manual, subjective, and unscalable task. We propose a novel framework which leverages Large Language Models (LLMs) to automate and scale this process. We introduce \texttt{LLMPrior}, a principled operator that translates rich, unstructured contexts such as natural language descriptions, data or figures into valid, tractable probability distributions. We formalize this operator by architecturally coupling an LLM with an explicit, tractable generative model, such as a Gaussian Mixture Model (forming a LLM based Mixture Density Network), ensuring the resulting prior satisfies essential mathematical properties. We further extend this framework to multi-agent systems where Logarithmic Opinion Pooling is employed to aggregate prior distributions induced by decentralized knowledge. We present the federated prior aggregation algorithm, \texttt{Fed-LLMPrior}, for aggregating distributed, context-dependent priors in a manner robust to agent heterogeneity. This work provides the foundation for a new class of tools that can potentially lower the barrier to entry for sophisticated Bayesian modeling.

Yongchao Huang, Pengfei Zhang, Shahzad Mumtaz

Membership inference attacks (MIAs) test whether a data point was part of a model's training set, posing serious privacy risks. Existing methods often depend on shadow models or heavy query access, which limits their practicality. We propose GP-MIA, an efficient and interpretable approach based on Gaussian process (GP) meta-modeling. Using post-hoc metrics such as accuracy, entropy, dataset statistics, and optional sensitivity features (e.g. gradients, NTK measures) from a single trained model, GP-MIA trains a GP classifier to distinguish members from non-members while providing calibrated uncertainty estimates. Experiments on synthetic data, real-world fraud detection data, CIFAR-10, and WikiText-2 show that GP-MIA achieves high accuracy and generalizability, offering a practical alternative to existing MIAs.

Yongchao Huang

We present a family of \textit{Gaussian Mixture Approximation} (GMA) samplers for sampling unnormalised target densities, encompassing \textit{weights-only GMA} (W-GMA), \textit{Laplace Mixture Approximation} (LMA), \textit{expectation-maximization GMA} (EM-GMA), and further variants. GMA adopts a simple two-stage paradigm: (i) initialise a finite set of Gaussian components and draw samples from a proposal mixture; (ii) fit the mixture to the target by optimising either only the component weights or also the means and variances, via a sample-based KL divergence objective that requires only evaluations of the unnormalised density, followed by stratified resampling. The method is gradient-free, and computationally efficient: it leverages the ease of sampling from Gaussians, efficient optimisation methods (projected gradient descent, mirror descent, and EM), and the robustness of stratified resampling to produce samples faithful to the target. We show that this optimisation-resampling scheme yields consistent approximations under mild conditions, and we validate this methodology with empirical results demonstrating accuracy and speed across diverse densities.

Yongchao Huang, Hassan Raza

We propose semantic fusion, a lightweight scheme that augments a Transformer language model (LM) with a parallel, fuzzy-membership feature channel that encodes token-level semantics. Each token is represented by a vector of interpretable features (e.g. part-of-speech cues, shallow roles, boundary flags, sentiment polarity and strength) whose values are graded degrees from differentiable membership functions (e.g. power kernels). These per-token vectors form a sentence-level semantic matrix fused via a gated adapter into the LM. Training uses standard next-token prediction, an auxiliary loss that reconstructs the semantic features from hidden states, and a lightweight uniformizer that regularizes adjective-class distributions. On a synthetic two-clause corpus with held-out adjectives for out-of-distribution (OOD) control, semantic fusion improves perplexity and enables precise, user-controllable generation of polarity and punctuation while maintaining model simplicity. This approach adds only small overhead, remains fully compatible with tied input-output embeddings, and provides an interpretable pathway for conditioned natural language generation.

Yongchao Huang

A significant barrier to the widespread adoption of Bayesian inference is the specification of prior distributions and likelihoods, which often requires specialized statistical expertise. This paper investigates the feasibility of using a Large Language Model (LLM) to automate this process. We introduce LLM-BI (Large Language Model-driven Bayesian Inference), a conceptual pipeline for automating Bayesian workflows. As a proof-of-concept, we present two experiments focused on Bayesian linear regression. In Experiment I, we demonstrate that an LLM can successfully elicit prior distributions from natural language. In Experiment II, we show that an LLM can specify the entire model structure, including both priors and the likelihood, from a single high-level problem description. Our results validate the potential of LLMs to automate key steps in Bayesian modeling, enabling the possibility of an automated inference pipeline for probabilistic programming.

Yongchao Huang

Standard regression techniques, while powerful, are often constrained by predefined, differentiable loss functions such as mean squared error. These functions may not fully capture the desired behavior of a system, especially when dealing with asymmetric costs or complex, non-differentiable objectives. In this paper, we explore an alternative paradigm: framing regression as a Reinforcement Learning (RL) problem. We demonstrate this by treating a model's prediction as an action and defining a custom reward signal based on the prediction error, and we can leverage powerful RL algorithms to perform function approximation. Through a progressive case study of learning a noisy sine wave, we illustrate the development of an Actor-Critic agent, iteratively enhancing it with Prioritized Experience Replay, increased network capacity, and positional encoding to enable a capable RL agent for this regression task. Our results show that the RL framework not only successfully solves the regression problem but also offers enhanced flexibility in defining objectives and guiding the learning process.

Yongchao Huang

This work introduces 4 novel probabilistic and reinforcement-driven methods for association rule mining (ARM): Gaussian process-based association rule mining (GPAR), Bayesian ARM (BARM), multi-armed bandit based ARM (MAB-ARM), and reinforcement learning based association rule mining (RLAR). These methods depart fundamentally from traditional frequency-based algorithms such as Apriori, FP-Growth, and Eclat, offering enhanced capabilities for incorporating prior knowledge, modeling uncertainty, item dependencies, probabilistic inference and adaptive search strategies. GPAR employs Gaussian processes to model item co-occurrence via feature representations, enabling principled inference, uncertainty quantification, and efficient generalization to unseen itemsets without retraining. BARM adopts a Bayesian framework with priors and optional correlation structures, yielding robust uncertainty quantification through full posterior distributions over item presence probabilities. MAB-ARM, including its Monte Carlo tree search (MCTS) companion, utilizes an upper confidence bound (UCB) strategy for efficient and adaptive exploration of the itemset space, while RLAR applies a deep Q-network (DQN) to learn a generalizable policy for identifying high-quality rules. Collectively, these approaches improve the flexibility and robustness of ARM, particularly for discovering rare or complex patterns and operating on small datasets. Empirical results on synthetic and real-world datasets demonstrate their effectiveness, while also highlighting trade-offs in computational complexity and interpretability. These innovations mark a significant shift from static, frequency-driven paradigms, offering some prior and dependency-informed, uncertainty-aware or scalable ARM frameworks for diverse application domains such as retail, geography, finance, medical diagnostics, and risk-sensitive scenarios.

Yongchao Huang

Determining whether a dataset was part of a machine learning model's training data pool can reveal privacy vulnerabilities, a challenge often addressed through membership inference attacks (MIAs). Traditional MIAs typically require access to model internals or rely on computationally intensive shadow models. This paper proposes an efficient, interpretable and principled Bayesian inference method for membership inference. By analyzing post-hoc metrics such as prediction error, confidence (entropy), perturbation magnitude, and dataset statistics from a trained ML model, our approach computes posterior probabilities of membership without requiring extensive model training. Experimental results on synthetic datasets demonstrate the method's effectiveness in distinguishing member from non-member datasets. Beyond membership inference, this method can also detect distribution shifts, offering a practical and interpretable alternative to existing approaches.

Yongchao Huang

A reward-guided, gradient-free ParVI method, \textit{R-ParVI}, is proposed for sampling partially known densities (e.g. up to a constant). R-ParVI formulates the sampling problem as particle flow driven by rewards: particles are drawn from a prior distribution, navigate through parameter space with movements determined by a reward mechanism blending assessments from the target density, with the steady state particle configuration approximating the target geometry. Particle-environment interactions are simulated by stochastic perturbations and the reward mechanism, which drive particles towards high density regions while maintaining diversity (e.g. preventing from collapsing into clusters). R-ParVI offers fast, flexible, scalable and stochastic sampling and inference for a class of probabilistic models such as those encountered in Bayesian inference and generative modelling.

Yongchao Huang

A new particle-based sampling and approximate inference method, based on electrostatics and Newton mechanics principles, is introduced with theoretical ground, algorithm design and experimental validation. This method simulates an interacting particle system (IPS) where particles, i.e. the freely-moving negative charges and spatially-fixed positive charges with magnitudes proportional to the target distribution, interact with each other via attraction and repulsion induced by the resulting electric fields described by Poisson's equation. The IPS evolves towards a steady-state where the distribution of negative charges conforms to the target distribution. This physics-inspired method offers deterministic, gradient-free sampling and inference, achieving comparable performance as other particle-based and MCMC methods in benchmark tasks of inferring complex densities, Bayesian logistic regression and dynamical system identification. A discrete-time, discrete-space algorithmic design, readily extendable to continuous time and space, is provided for usage in more general inference problems occurring in probabilistic machine learning scenarios such as Bayesian inference, generative modelling, and beyond.

Yongchao Huang, Yuhang He, Hong Ge

In this work, we introduce a novel framework which combines physics and machine learning methods to analyse acoustic signals. Three methods are developed for this task: a Bayesian inference approach for inferring the spectral acoustics characteristics, a neural-physical model which equips a neural network with forward and backward physical losses, and the non-linear least squares approach which serves as benchmark. The inferred propagation coefficient leads to the room impulse response (RIR) quantity which can be used for relocalisation with uncertainty. The simplicity and efficiency of this framework is empirically validated on simulated data.

Christian Schroeder de Witt, Yongchao Huang, Philip H. S. Torr et al.

Cyber attacks are increasing in volume, frequency, and complexity. In response, the security community is looking toward fully automating cyber defense systems using machine learning. However, so far the resultant effects on the coevolutionary dynamics of attackers and defenders have not been examined. In this whitepaper, we hypothesise that increased automation on both sides will accelerate the coevolutionary cycle, thus begging the question of whether there are any resultant fixed points, and how they are characterised. Working within the threat model of Locked Shields, Europe's largest cyberdefense exercise, we study blackbox adversarial attacks on network classifiers. Given already existing attack capabilities, we question the utility of optimal evasion attack frameworks based on minimal evasion distances. Instead, we suggest a novel reinforcement learning setting that can be used to efficiently generate arbitrary adversarial perturbations. We then argue that attacker-defender fixed points are themselves general-sum games with complex phase transitions, and introduce a temporally extended multi-agent reinforcement learning framework in which the resultant dynamics can be studied. We hypothesise that one plausible fixed point of AI-NIDS may be a scenario where the defense strategy relies heavily on whitelisted feature flow subspaces. Finally, we demonstrate that a continual learning approach is required to study attacker-defender dynamics in temporally extended general-sum games.

Yongchao Huang, Hugh Miles, Pengfei Zhang

The rising availability of large volume data, along with increasing computing power, has enabled a wide application of statistical Machine Learning (ML) algorithms in the domains of Cyber-Physical Systems (CPS), Internet of Things (IoT) and Smart Building Networks (SBN). This paper proposes a learning-based framework for sequentially applying the data-driven statistical methods to predict indoor temperature and yields an algorithm for controlling building heating system accordingly. This framework consists of a two-stage modelling effort: in the first stage, an univariate time series model (AR) was employed to predict ambient conditions; together with other control variables, they served as the input features for a second stage modelling where an multivariate ML model (XGBoost) was deployed. The models were trained with real world data from building sensor network measurements, and used to predict future temperature trajectories. Experimental results demonstrate the effectiveness of the modelling approach and control algorithm, and reveal the promising potential of the mixed data-driven approach in smart building applications. By making wise use of IoT sensory data and ML algorithms, this work contributes to efficient energy management and sustainability in smart buildings.

Pengfei Zhang, Ido Nevat, Gareth W. Peters et al.

We address the two fundamental problems of spatial field reconstruction and sensor selection in heterogeneous sensor networks: (i) how to efficiently perform spatial field reconstruction based on measurements obtained simultaneously from networks with both high and low quality sensors; and (ii) how to perform query based sensor set selection with predictive MSE performance guarantee. For the first problem, we developed a low complexity algorithm based on the spatial best linear unbiased estimator (S-BLUE). Next, building on the S-BLUE, we address the second problem, and develop an efficient algorithm for query based sensor set selection with performance guarantee. Our algorithm is based on the Cross Entropy method which solves the combinatorial optimization problem in an efficient manner.