paper-with-me

Papers

Neural Bayesian Sequential Routing

2026-05-22 · Yongchao Huang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.26147

Code (0)

등록된 구현이 없습니다.

Tasks

Medical Diagnosis

Similar Papers 제목 키워드 기반

Meta-Attention: Bayesian Per-Token Routing for Efficient Transformer Inference

2026-05-27 · Alan Ferrari arxiv

Standard transformer architectures apply a single attention mechanism uniformly across all tokens and sequence positions, irrespective of local context or computational budget. We propose Meta-Attention, a framework that…

Bayesian Graph Traversal

2025-03-07 · William N. Caballero, Phillip R. Jenkins, David Banks, Matthew Robbins

This research considers Bayesian decision-analytic approaches toward the traversal of an uncertain graph. Namely, a traveler progresses over a graph in which rewards are gained upon a node's first visit and costs are inc…

Decision MakingSequential Decision Making

Sequential Routing Framework: Fully Capsule Network-based Speech Recognition

2020-07-23 · Kyungmin Lee, Hyunwhan Joe, Hyeontaek Lim, Kwangyoun Kim 외

Capsule networks (CapsNets) have recently gotten attention as a novel neural architecture. This paper presents the sequential routing framework which we believe is the first method to adapt a CapsNet-only structure to se…

speech-recognitionSpeech Recognition

Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers

2026-03-10 · Albus Yizhuo Li, Matthew Wicker arxiv

Foundation models are increasingly being deployed in contexts where understanding the uncertainty of their outputs is critical to ensuring responsible deployment. While Bayesian methods offer a principled approach to unc…

Bayesian Inference

Reward Model Routing in Alignment

2025-10-03 · Xinle Wu, Yao Lu arxiv

Reinforcement learning from human or AI feedback (RLHF / RLAIF) has become the standard paradigm for aligning large language models (LLMs). However, most pipelines rely on a single reward model (RM), limiting alignment q…

Reinforcement Learning