arXiv subjects

Ethan Tran

Publications and source records attributed to Ethan Tran.

3 recordsLinked to original sources

arXiv2026

Spectra: A Rules-Driven LLM Pipeline for Automated KYC Document Processing

Know Your Client (KYC) onboarding in capital markets requires analysts to manually classify documents, extract structured data from heterogeneous sources, and validate compliance against complex regulatory policies. This process requires significant analyst time per client, with end-to-end onboarding often stretching to multiple weeks due to sequential handoffs. In this work, we analyze an on-boarding process and find that it comprises repeatable components well-suited to AI automation. We therefore propose a restructured workflow to be amenable to automation: we consolidate the traditional four-party process into two parties that share most of the work and can be automated together, eliminating intermediate handoffs that compound delays. To automate the remaining steps, we introduce Spectra, an AI-assisted document processing platform that combines a structured rules engine with LLM-based classification, extraction, and validation agents. The rules engine encodes compliance policy as a queryable database, enabling focused context injection that reduces token usage while improving extraction precision. Rather than a single monolithic prompt, the system decomposes document processing into isolated, auditable stages, each optimized independently and traceable to specific policy clauses. In evaluation on real KYC documents, Spectra achieves 100% classification accuracy and 89.4% extraction accuracy. Human review burden dropped by 96%.

cs.AI↗

arXiv2026

SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports

Deeply understanding sports requires an intricate blend of fine-grained visual perception and rule-based reasoning - a challenge that pushes the limits of current multimodal models. To succeed, models must master three critical capabilities: perceiving nuanced visual details, applying abstract sport rule knowledge, and grounding that knowledge in specific visual evidence. Current sports benchmarks either cover single sports or lack the detailed reasoning chains and precise visual grounding needed to robustly evaluate these core capabilities in a multi-sport context. To address this gap, we introduce SportR, the first multi-sports large-scale benchmark designed to train and evaluate MLLMs on the fundamental reasoning required for sports intelligence. Our benchmark provides a dataset of 4,789 images and 2,052 videos. To enable granular evaluation, we structure our benchmark around a progressive hierarchy of question-answer pairs designed to probe reasoning at increasing depths - from simple infraction identification to complex penalty prediction. For the most advanced tasks requiring multi-step reasoning, such as determining penalties or explaining tactics, we provide 6,841 high-quality, human-authored Chain of Thought annotations. In addition, our benchmark incorporates both image and video modalities and provides manual bounding box annotations to test visual grounding in the image part directly. Extensive experiments demonstrate the profound difficulty of our benchmark. State-of-the-art baseline models perform poorly on our most challenging tasks. While training on our data via Supervised Fine-Tuning and Reinforcement Learning improves these scores, they remain relatively low, highlighting a significant gap in current model capabilities. SportR presents a new challenge for the community, providing a critical resource to drive future research in multimodal sports reasoning.

cs.CV↗

arXiv2024

Floquet Isospectrality of the Zero Potential for Discrete Periodic Schrödinger Operators

Let $Γ=q_1\mathbb{Z}\oplus q_2 \mathbb{Z}\oplus\cdots\oplus q_d\mathbb{Z}$, with $q_j\in (\mathbb{Z}^+)^d$ for each $j\in \{1,\ldots,d\}$, and denote by $Δ$ the discrete Laplacian on $\ell^2\left( \mathbb{Z}^d\right)$. Using Macaulay2, we first numerically find complex-valued $Γ$-periodic potentials $V:\mathbb{Z}^d\to \mathbb{C}$ such that the operators $Δ+V$ and $Δ$ are Floquet isospectral. We then use combinatorial methods to validate these numerical solutions.

math.SP↗