arXiv subjects

Yongchao Huang

Publications and source records attributed to Yongchao Huang.

At least 19 recordsLinked to original sources

arXiv2026

4DGS-JEPA: Temporally Compositional Joint-Embedding Prediction for Dynamic Gaussian Splatting

Dynamic Gaussian Splatting provides an explicit representation of evolving 3D scenes, but existing approaches are primarily optimized for reconstruction, future-state generation, or rendering rather than for learning reusable predictive dynamics. We propose 4DGS-JEPA, a Gaussian-native joint-embedding predictive architecture for causal multi-horizon prediction over dynamic Gaussian scenes. The model uses a hierarchical scene-, motion-group-, and Gaussian-level representation together with a horizon-conditioned transition operator that supports both direct prediction and recursive rollout. Its central principle is temporal composition: different chronological transition paths reaching the same future endpoint should produce compatible predictive states. Endpoint and multi-horizon path supervision anchor these predictions to future target embeddings, while a selective geometry decoder and geometry-level composition ground the learned dynamics in consistent group motion and Gaussian geometry without requiring complete future appearance reconstruction. We further introduce a hybrid correspondence mechanism that combines persistent canonical identity with residual optimal-transport matching under reordering and topology change. We characterize zero-loss path agreement and finite-error rollout accumulation theoretically. Three controlled experiments provide mechanism-level evidence that temporal composition reduces latent path dependence while retaining predictive accuracy, geometry-level composition improves consistency of decoded motion, and hybrid correspondence preserves reliable identity while remaining robust when correspondence becomes ambiguous. Together, 4DGS-JEPA provides a predictive, temporally compositional formulation of dynamic Gaussian worlds.

cs.AI↗

arXiv2026

Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning

A hidden Markov model (HMM) combines three roles: inference of a hidden-state belief from observations, propagation through a Markov transition, and emission back to observation space. We show that full, time-indexed Predictive Information Bottleneck VJEPA (PIB-VJEPA) exposes the same computational structure: a stochastic context encoder plays the role of an amortized filtering distribution, a probabilistic predictor defines latent-state dynamics, and a decoder, inverse target encoder, or induced implicit conditional supplies the emission direction. We distinguish 4 progressively stronger levels of correspondence and give sufficient conditions for exact sequence-level HMM equivalence. To make the connection concrete, we introduce Markov-Chain JEPA (MCJEPA), which replaces the latent predictor by a learned transition matrix; in the finite time-homogeneous case, matrix powers guarantee exact multi-horizon Chapman--Kolmogorov consistency. Conditioned discrete-state transitions, continuous-state Markov kernels, and continuous-time dynamics extend this construction, while deterministic temporal JEPA appears as a degenerate Dirac-kernel special case. We further interpret predictive information-bottleneck learning as seeking a compact predictive state: compression promotes minimality, while residual predictability tests sufficiency. Controlled experiments support transition composition, the filtering interpretation, predictive Markovization in a known synthetic process, and the distinction between JEPA latent prediction and HMM-style sequence learning. Together, these results give temporal JEPA a principled state-space interpretation.

cs.AI↗

arXiv2026

SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors

Joint-embedding predictive architectures learn abstract states by predicting target embeddings from context embeddings, but their transition models are typically opaque neural maps. We introduce SJEPA, a reconstruction-free JEPA framework that learns predictive representations whose induced dynamics admit compact symbolic descriptions. Its hybrid transition combines a symbolic law with a regularised neural correction for dynamics outside the selected grammar. The central principle is to learn the simplest adequate dynamics: representation constraints preserve informative, non-collapsed predictive coordinates, while operator compression favours low-complexity symbolic-neural transitions that remain predictively adequate. We formalise this principle through induced-dynamics complexity, analyse predictive-coordinate non-identifiability, and show that unconstrained operator compression creates a direct shortcut to representation collapse. The framework supports both alternating representation-equation learning and symbolic dynamics fitted to fixed representations. In controlled pendulum experiments, joint learning discovers substantially simpler symbolic dynamics with lower long-horizon rollout error and divergence than post-hoc fitting, while an unconstrained one-step diagnostic realises the predicted collapse shortcut. Under grammar misspecification, correction regularisation preserves the representable symbolic mechanism and directs the neural component towards residual dynamics. The results expose a controllable trade-off among predictive fidelity, representation quality, symbolic parsimony, and symbolic-neural allocation.

cs.LG↗

arXiv2026

Gaussian Mixture Attention: Linear-Time Sequence Mixing via Probabilistic Latent Routing

The dense token-to-token interaction pattern of standard dot-product attention remains a central bottleneck in scaling Transformer architectures to long contexts. We introduce \textbf{Gaussian Mixture Attention (GMA)}, a probabilistic attention-style sequence mixer that replaces explicit pairwise query--key comparison with routing through $K$ learned Gaussian mixture components. Queries and keys are mapped to posterior \textit{responsibility} vectors over a shared latent routing space; their overlap defines an implicit responsibility-space affinity, while values are written into and read from a $K$-slot latent memory. By exploiting the associativity of matrix multiplication, GMA avoids materializing the induced $N\times N$ affinity matrix and instead uses two responsibility matrices whose dominant activation storage scales as $\mathcal{O}(NK)$ rather than $\mathcal{O}(N^2)$ for fixed $K$. We formulate bidirectional and causal variants of GMA, provide an end-to-end differentiable parameterization of the Gaussian mixture components, and analyze its responsibility-modulated gradient structure, constrained non-negative low-rank affinity interpretation, and local routing stability. Empirically, GMA exhibits the intended fixed-$K$ linear memory scaling and is competitive with attention-style baselines on long-context classification, while causal GMA improves over tested linear/random-feature attention variants on WikiText-103 but remains behind optimized causal SDPA and Mamba in the current implementation. Analysis of learned responsibilities further shows broad component usage and moderate alignment with surface-form token categories, supporting GMA as a probabilistic, interpretable, fixed-$K$ linear-time attention-style alternative rather than a universal replacement for optimized softmax attention or state-space models.

cs.LG↗

arXiv2026

Neural Bayesian Sequential Routing

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.

cs.LG↗

arXiv2026

Gaussian Joint Embeddings For Self-Supervised Representation Learning

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.

cs.LG↗

arXiv2026

Knowledge, Rules and Their Embeddings: Two Paths towards Neuro-Symbolic JEPA

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.

cs.LG↗

arXiv2026

BiJEPA: Bi-directional Joint Embedding Predictive Architecture for Symmetric Representation Learning

Self-Supervised Learning (SSL) has shifted from pixel-level reconstruction to latent space prediction, spearheaded by the Joint Embedding Predictive Architecture (JEPA). While effective, standard JEPA models typically rely on a uni-directional prediction mechanism (e.g. Context $\to$ Target), potentially neglecting the informative signal inherent in the inverse relationship, degrading its performance. In this work, we propose \textbf{BiJEPA}, a \textit{Bi-Directional Joint Embedding Predictive Architecture} that enforces cycle-consistent predictability between data segments. We address the inherent instability of symmetric prediction (representation explosion) by introducing a critical norm regularization mechanism on the representation vectors. We evaluate BiJEPA on three distinct modalities: synthetic periodic signals, chaotic Lorenz attractor trajectories, and high-dimensional image data (MNIST). Our results demonstrate that BiJEPA achieves stable convergence without collapse, captures the semantic structure of chaotic systems, and learns robust temporal and spatial representations capable of generation and generalisation, offering a more holistic approach to representation learning.

cs.LG↗

arXiv2026

VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models

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.

cs.LG↗

arXiv2025

Training data membership inference via Gaussian process meta-modeling: a post-hoc analysis approach

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.

cs.LG↗

arXiv2025

Sampling via Gaussian Mixture Approximations

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.

cs.LG↗

arXiv2025

Semantic Fusion with Fuzzy-Membership Features for Controllable Language Modelling

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.

cs.AI↗

arXiv2025

LLM-BI: Towards Fully Automated Bayesian Inference with Large Language Models

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.

cs.AI↗

arXiv2025

LLM-Prior: A Framework for Knowledge-Driven Prior Elicitation and Aggregation

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.

cs.LG↗

arXiv2025

RL as Regressor: A Reinforcement Learning Approach for Function Approximation

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.

cs.LG↗

arXiv2025

Probabilistic and reinforced mining of association rules

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.

cs.LG↗

arXiv2025

Bayesian Inference of Training Dataset Membership

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.

cs.LG↗

arXiv2025

R-ParVI: Particle-based variational inference through lens of rewards

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.

cs.AI↗