Tax Law

arXiv:2603.06503v1 Announce Type: new Abstract: Recent advances in multimodal Retrieval-Augmented Generation (RAG) enable Large Language Models (LLMs) to analyze enterprise spreadsheet workbooks containing millions of cells, cross-sheet dependencies, and embedded visual artifacts. However, state-of-the-art approaches exclude critical context through single-pass...

arXiv:2603.05761v1 Announce Type: new Abstract: Rectified Flow (RF) models achieve state-of-the-art generation quality, yet controlling them for precise tasks -- such as semantic editing or blind image recovery -- remains a challenge. Current approaches bifurcate into inversion-based guidance, which suffers...

arXiv:2603.05764v1 Announce Type: new Abstract: Autonomous coding agents can produce strong tabular baselines quickly on Kaggle-style tasks. Practical value depends on end-to-end correctness and reliability under time limits. This paper introduces TML-Bench, a tabular benchmark for data science agents on...

arXiv:2603.05805v1 Announce Type: new Abstract: Mixture of Experts (MoE) achieve parameter-efficient scaling through sparse expert routing, yet their internal representations remain poorly understood compared to dense models. We present a systematic comparison of MoE and dense model internals using crosscoders,...

arXiv:2603.05806v1 Announce Type: new Abstract: Mixture of Experts (MoE) models enable parameter-efficient scaling through sparse expert activations, yet optimizing their inference and memory costs remains challenging due to limited understanding of their specialization behavior. We present a systematic analysis of...

arXiv:2603.05822v1 Announce Type: new Abstract: Adapting foundation models to new clinical sites remains challenging in practice. Domain shift and scarce annotations must be handled by experts, yet many clinical groups do not have ready access to skilled AI engineers to...

arXiv:2603.06120v1 Announce Type: new Abstract: Stochastic Gradient Descent (SGD) and its momentum variants form the backbone of deep learning optimization, yet the underlying dynamics of their gradient behavior remain insufficiently understood. In this work, we reinterpret gradient updates through the...

arXiv:2603.06248v1 Announce Type: new Abstract: Understanding the intricate non-convex training dynamics of softmax-based models is crucial for explaining the empirical success of transformers. In this article, we analyze the gradient flow dynamics of the value-softmax model, defined as ${L}(\mathbf{V} \sigma(\mathbf{a}))$,...

The article is devoted to the international regulation on artificial intelligence influence on the Information Law of Ukraine. It was noted that the principles of regulation of artificial intelligence should be reflected in the Information Law of Ukraine. Based on...

2025-26 Academic Calendar Please note: All times in U.S. Central. EventDate / Time First Registration Appointment Window (all 3Ls)June 16 (YES opens at 12:35 PM) thru June 22 (YES closes at 11:59 PM) Second Registration Appointment Window (all 2Ls/3Ls)June 23...

Boundary-conforming coordinate transformations are used widely to map a flow region onto a computational space in which a finite-difference solution to the differential flow conservation laws is carried out. This method entails difficulties with maintenance of global conservation and with...

News from the Vanderbilt Law School

Residential colleges are a type of on-campus student residence in which the academic experience is integrated into residential life, creating communities and opportunities for learning outside the classroom among a diverse student body.

Abstract As artificial intelligence (AI) transforms a wide range of sectors and drives innovation, it also introduces different types of risks that should be identified, assessed, and mitigated. Various AI governance frameworks have been released recently by governments, organizations, and...

[Context] Semantic legal metadata provides information that helps with understanding and interpreting the meaning of legal provisions. Such metadata is important for the systematic analysis of legal requirements. [Objectives] Our work is motivated by two observations: (1) The existing requirements...

As methods in legal information retrieval (IR) evolve to meet the demands of rapidly increasing stores of electronic information, there is the intuitive appeal of capturing detail in legal queries with natural language processing (NLP). One difficulty with this approach...

In Loper Bright v. Raimondo, the Supreme Court adopted and deployed a particular narrative about agency action in support of overruling Chevron: Agencies reverse their own statutory interpretations “as much as [they] like[],” creating pervasive instability in the law, thereby...

This article analyzes the challenges of regulating Artificial Intelligence (AI) in the Brazilian judicial system, considering the constitutional, ethical, and normative principles that guide the use of technologies within the Judiciary. The research examines the normative evolution promoted by the...

The so-called fourth industrial revolution and its economic and societal implications are no longer solely an academic concern, but a matter for political as well as public debate. Characterized as the convergence of robotics, AI, autonomous systems and information technology...

Although computers and digital technologies have existed for many decades, their capabilities today have changed dramatically. Current buzzwords like Big Data, artificial intelligence, robotics, and blockchain are shorthand for further leaps in development. The digitalisation of communication, which is a...

The present society is in a period of rapid development of artificial intelligence, and the process of its swift advancement is filled with both opportunities and challenges. As a branch of artificial intelligence, deep synthesis technology gradually enters people's vision....

The rapid evolution of financial technology, especially the integration of Artificial Intelligence (AI), is reshaping the financial sector in Africa. This paper comprehensively reviews the rise, implications, and future prospects of AI-driven financial services in Africa. This study aimed to...

Introduction At the core of intellectual property (IP) law lies a fundamental question of political philosophy: Can any argument justify the state’s grant of private property rights in intangibles?[1] To this question, scholars have responded that IP rights can be...

Introduction Modern society faces a paradox: While corporations can be useful engines of innovation and value creation, they increasingly operate as vectors for profound public harm beyond the reach of public regulation. The “economic and human tolls,” experts note, “almost...

Researchers and practitioners from different disciplines have highlighted the ethical and legal challenges posed by the use of machine learned models and data-driven systems, and the potential for such systems to discriminate against certain population groups, due to biases in...

Abstract This article examines the challenges of regulating artificial intelligence (AI) systems and proposes an adapted model of regulation suitable for AI's novel features. Unlike past technologies, AI systems built using techniques like deep learning cannot be directly analyzed, specified,...