MIRACL: A Diverse Meta-Reinforcement Learning for Multi-Objective Multi-Echelon Combinatorial Supply Chain Optimisation
arXiv:2603.05760v1 Announce Type: new Abstract: Multi-objective reinforcement learning (MORL) is effective for multi-echelon combinatorial supply chain optimisation, where tasks involve high dimensionality, uncertainty, and competing objectives. However, its deployment in dynamic environments is hindered by the need for task-specific retraining...
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...
First-Order Softmax Weighted Switching Gradient Method for Distributed Stochastic Minimax Optimization with Stochastic Constraints
arXiv:2603.05774v1 Announce Type: new Abstract: This paper addresses the distributed stochastic minimax optimization problem subject to stochastic constraints. We propose a novel first-order Softmax-Weighted Switching Gradient method tailored for federated learning. Under full client participation, our algorithm achieves the standard...
Sparse Crosscoders for diffing MoEs and Dense models
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,...
MoE Lens -- An Expert Is All You Need
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...
Self-Auditing Parameter-Efficient Fine-Tuning for Few-Shot 3D Medical Image Segmentation
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...
Test-Time Adaptation via Many-Shot Prompting: Benefits, Limits, and Pitfalls
arXiv:2603.05829v1 Announce Type: new Abstract: Test-time adaptation enables large language models (LLMs) to modify their behavior at inference without updating model parameters. A common approach is many-shot prompting, where large numbers of in-context learning (ICL) examples are injected as an...
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...
Omni-Masked Gradient Descent: Memory-Efficient Optimization via Mask Traversal with Improved Convergence
arXiv:2603.05960v1 Announce Type: new Abstract: Memory-efficient optimization methods have recently gained increasing attention for scaling full-parameter training of large language models under the GPU-memory bottleneck. Existing approaches either lack clear convergence guarantees, or only achieve the standard ${\mathcal{O}}(\epsilon^{-4})$ iteration complexity...
EvoESAP: Non-Uniform Expert Pruning for Sparse MoE
arXiv:2603.06003v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (SMoE) language models achieve strong capability at low per-token compute, yet deployment remains memory- and throughput-bound because the full expert pool must be stored and served. Post-training expert pruning reduces this cost, but...
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...
DQE: A Semantic-Aware Evaluation Metric for Time Series Anomaly Detection
arXiv:2603.06131v1 Announce Type: new Abstract: Time series anomaly detection has achieved remarkable progress in recent years. However, evaluation practices have received comparatively less attention, despite their critical importance. Existing metrics exhibit several limitations: (1) bias toward point-level coverage, (2) insensitivity...
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...
Predictive Coding Graphs are a Superset of Feedforward Neural Networks
arXiv:2603.06142v1 Announce Type: new Abstract: Predictive coding graphs (PCGs) are a recently introduced generalization to predictive coding networks, a neuroscience-inspired probabilistic latent variable model. Here, we prove how PCGs define a mathematical superset of feedforward artificial neural networks (multilayer perceptrons)....
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...
Topological descriptors of foot clearance gait dynamics improve differential diagnosis of Parkinsonism
arXiv:2603.06212v1 Announce Type: new Abstract: Differential diagnosis among parkinsonian syndromes remains a clinical challenge due to overlapping motor symptoms and subtle gait abnormalities. Accurate differentiation is crucial for treatment planning and prognosis. While gait analysis is a well established approach...
FedSCS-XGB -- Federated Server-centric surrogate XGBoost for continual health monitoring
arXiv:2603.06224v1 Announce Type: new Abstract: Wearable sensors with local data processing can detect health threats early, enhance documentation, and support personalized therapy. In the context of spinal cord injury (SCI), which involves risks such as pressure injuries and blood pressure...
Gradient Flow Polarizes Softmax Outputs towards Low-Entropy Solutions
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 ${L}(\mathbf{V} \sigma(\mathbf{a}))$,...
Legislative Text Analysis from Judicial Case Reports Using Machine Learning
Practical Consequences in Statutory Interpretation
Modern textualism has long criticized the use of practical, or consequentialist, reasoning when construing statutes. And yet in practice, textualist jurists long have invoked practical consequences arguments to help justify their statutory constructions.The postPractical Consequences in Statutory Interpretationappeared first onHarvard...
Bias in Black Boxes: A Framework for Auditing Algorithmic Fairness in Financial Lending Models
This study presents a comprehensive and practical framework for auditing algorithmic fairness in financial lending models, addressing the urgent concern of bias in machine-learning systems that increasingly influence credit decisions. As financial institutions shift toward automated underwriting and risk scoring,...
A hybrid CNN + BILSTM deep learning-based DSS for efficient prediction of judicial case decisions
Automated Extraction of Semantic Legal Metadata using Natural Language Processing
[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...
Fall 2025 Book Symposium – Serena Mayeri’s Marital Privilege: Marriage, Inequality, and the Transformation of American Law | Law Review
The relationship between infrared, optical, and ultraviolet extinction
view Abstract Citations (9701) References (43) Co-Reads Similar Papers Volume Content Graphics Metrics Export Citation NASA/ADS The Relationship between Infrared, Optical, and Ultraviolet Extinction Cardelli, Jason A. ; Clayton, Geoffrey C. ; Mathis, John S. Abstract The parameterized extinction data...