IntSeqBERT: Learning Arithmetic Structure in OEIS via Modulo-Spectrum Embeddings
arXiv:2603.05556v1 Announce Type: new Abstract: Integer sequences in the OEIS span values from single-digit constants to astronomical factorials and exponentials, making prediction challenging for standard tokenised models that cannot handle out-of-vocabulary values or exploit periodic arithmetic structure. We present IntSeqBERT,...
A Novel Hybrid Heuristic-Reinforcement Learning Optimization Approach for a Class of Railcar Shunting Problems
arXiv:2603.05579v1 Announce Type: new Abstract: Railcar shunting is a core planning task in freight railyards, where yard planners need to disassemble and reassemble groups of railcars to form outbound trains. Classification tracks with access from one side only can be...
Unsupervised domain adaptation for radioisotope identification in gamma spectroscopy
arXiv:2603.05719v1 Announce Type: new Abstract: Training machine learning models for radioisotope identification using gamma spectroscopy remains an elusive challenge for many practical applications, largely stemming from the difficulty of acquiring and labeling large, diverse experimental datasets. Simulations can mitigate this...
Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment
arXiv:2603.05739v1 Announce Type: new Abstract: Best-of-N (BoN) sampling is a widely used inference-time alignment method for language models, whereby N candidate responses are sampled from a reference model and the one with the highest predicted reward according to a learned...
TML-Bench: Benchmark for Data Science Agents on Tabular ML Tasks
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...
Bridging Domains through Subspace-Aware Model Merging
arXiv:2603.05768v1 Announce Type: new Abstract: Model merging integrates multiple task-specific models into a single consolidated one. Recent research has made progress in improving merging performance for in-distribution or multi-task scenarios, but domain generalization in model merging remains underexplored. We investigate...
Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning
arXiv:2603.05900v1 Announce Type: new Abstract: Large language models (LLMs) benefit substantially from supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) in reasoning tasks. However, these recipes perform poorly in instruction-based molecular optimization, where each data point typically provides...
Stock Market Prediction Using Node Transformer Architecture Integrated with BERT Sentiment Analysis
arXiv:2603.05917v1 Announce Type: new Abstract: Stock market prediction presents considerable challenges for investors, financial institutions, and policymakers operating in complex market environments characterized by noise, non-stationarity, and behavioral dynamics. Traditional forecasting methods often fail to capture the intricate patterns and...
Design Experiments to Compare Multi-armed Bandit Algorithms
arXiv:2603.05919v1 Announce Type: new Abstract: Online platforms routinely compare multi-armed bandit algorithms, such as UCB and Thompson Sampling, to select the best-performing policy. Unlike standard A/B tests for static treatments, each run of a bandit algorithm over $T$ users produces...
Weak-SIGReg: Covariance Regularization for Stable Deep Learning
arXiv:2603.05924v1 Announce Type: new Abstract: Modern neural network optimization relies heavily on architectural priorssuch as Batch Normalization and Residual connectionsto stabilize training dynamics. Without these, or in low-data regimes with aggressive augmentation, low-bias architectures like Vision Transformers (ViTs) often suffer...
Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments
arXiv:2603.06009v1 Announce Type: new Abstract: Plateaus, where an agent's performance stagnates at a suboptimal level, are a common problem in deep on-policy RL. Focusing on PPO due to its widespread adoption, we show that plateaus in certain regimes arise not...
Agnostic learning in (almost) optimal time via Gaussian surface area
arXiv:2603.06027v1 Announce Type: new Abstract: The complexity of learning a concept class under Gaussian marginals in the difficult agnostic model is closely related to its $L_1$-approximability by low-degree polynomials. For any concept class with Gaussian surface area at most $\Gamma$,...
Dynamic Momentum Recalibration in Online Gradient Learning
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...
Partial Policy Gradients for RL in LLMs
arXiv:2603.06138v1 Announce Type: new Abstract: Reinforcement learning is a framework for learning to act sequentially in an unknown environment. We propose a natural approach for modeling policy structure in policy gradients. The key idea is to optimize for a subset...
Ensemble Graph Neural Networks for Probabilistic Sea Surface Temperature Forecasting via Input Perturbations
arXiv:2603.06153v1 Announce Type: new Abstract: Accurate regional ocean forecasting requires models that are both computationally efficient and capable of representing predictive uncertainty. This work investigates ensemble learning strategies for sea surface temperature (SST) forecasting using Graph Neural Networks (GNNs), with...
OpenAI robotics lead Caitlin Kalinowski quits in response to Pentagon deal
Hardware executive Caitlin Kalinowski announced today that in response to OpenAI's controversial agreement with the Department of Defense, she’s resigned from her role leading the company's robotics team.
OpenAI delays ChatGPT’s ‘adult mode’ again
The feature, which will give verified adult users access to erotica and other adult content, had already been delayed from December.
Securitising AI: routine exceptionality and digital governance in the Gulf
Abstract This article examines how Gulf Cooperation Council (GCC) states securitise artificial intelligence (AI) through discourses and infrastructures that fuse modernisation with regime resilience. Drawing on securitisation theory (Buzan et al., 1998; Balzacq, 2011) and critical security studies, it analyses...
Construction and Management of the South Florida Detention Facility
The second Trump Administration is executing an extensive immigration crackdown — pulling more people into detention, expanding Immigration and Customs Enforcement (ICE), and funneling money from...The postConstruction and Management of the South Florida Detention Facilityappeared first onHarvard Law Review.
Pressing Charges: Criminal Fees and the Excessive Fines Clause lawreview - Minnesota Law Review
By ANNEMARIE FOY. Full Text. Millions of people owe money to the government as a consequence of a criminal charge. But while some of that debt is tied to fines or restitution, much of it is levied as fees, or...
An Adaptive Conceptualisation of Artificial Intelligence and the Law, Regulation and Ethics
The description of a combination of technologies as ‘artificial intelligence’ (AI) is misleading. To ascribe intelligence to a statistical model without human attribution points towards an attempt at shifting legal, social, and ethical responsibilities to machines. This paper exposes the...
A Tribute to Sarah Lee Best
Sarah Best introduced herself to me in July 2019. She had worked that summer in the General Counsel’s Office at the U.S. Department of Education, and in the course of researching the application of the Indian-law canons of construction to...
Seeing the Dead: Marks, Meaning and the Haunting of American Trademark Law
[Introduction] The retirement of trademarks such as “Uncle Ben” and “Aunt Jemima” during the fulcrum of the Black Lives Matter movement prompted scholars to reconsider how trademark law protected various marks that perpetuated images built on a terrifying scaffold of...
Protecting Intellectual Property of Deep Neural Networks with Watermarking
Deep learning technologies, which are the key components of state-of-the-art Artificial Intelligence (AI) services, have shown great success in providing human-level capabilities for a variety of tasks, such as visual analysis, speech recognition, and natural language processing and etc. Building...
Beyond the Paycheck: Why Compensating NCAA Student-Athletes Does Not Mean Employing Them
Sometimes the best lessons you learn are when you do have failings. You can always learn more when you don’t do something exactly right.[1] —Nick Saban, Alabama Head Football Coach 2007–2024.[2] Introduction If the best lessons emerge from failure, the...
Profs. Joseph Blocher & Brandon Garrett Discuss “Fact Stripping” with Judge Paul Grimm
November 9, 2023 Last month, Professors Joseph Blocher and Brandon Garrett discussed their recent Article, “Fact Stripping,” with Judge Paul Grimm, the director of the Bolch Judicial Institute. Listen to their conversation below, and read their Article here.The postProfs. Joseph...
Refining the Dangerousness Standard in Felon Disarmament lawreview - Minnesota Law Review
By Jamie G. McWilliam. Full Text. To some, 18 U.S.C. 922(g) is a necessary safeguard that keeps guns out of the hands of dangerous persons. To others, it strips classes of non-violent people of their natural and constitutional rights. This...
Computation of minimum-time feedback control laws for discrete-time systems with state-control constraints
The problem of finding a feedback law that drives the state of a linear discrete-time system to the origin in minimum-time subject to state-control constraints is considered. Algorithms are given to obtain facial descriptions of the <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</tex> -step...
Beyond Personhood
This paper examines the evolution of legal personhood and explores whether historical precedents—from corporate personhood to environmental legal recognition—can inform frameworks for governing artificial intelligence (AI). By tracing the development of persona ficta in Roman law and subsequent expansions of...
Career Services
Vanderbilt Law School’s Career Services Team provides students with the resources and support they need to achieve their career goals. Career counselors meet individually with students on a regular basis to learn how to develop resumes, emphasize strengths, and identify...