Implicit Bias and Loss of Plasticity in Matrix Completion: Depth Promotes Low-Rankness
arXiv:2603.04703v1 Announce Type: new Abstract: We study matrix completion via deep matrix factorization (a.k.a. deep linear neural networks) as a simplified testbed to examine how network depth influences training dynamics. Despite the simplicity and importance of the problem, prior theory...
Count Bridges enable Modeling and Deconvolving Transcriptomic Data
arXiv:2603.04730v1 Announce Type: new Abstract: Many modern biological assays, including RNA sequencing, yield integer-valued counts that reflect the number of molecules detected. These measurements are often not at the desired resolution: while the unit of interest is typically a single...
Multilevel Training for Kolmogorov Arnold Networks
arXiv:2603.04827v1 Announce Type: new Abstract: Algorithmic speedup of training common neural architectures is made difficult by the lack of structure guaranteed by the function compositions inherent to such networks. In contrast to multilayer perceptrons (MLPs), Kolmogorov-Arnold networks (KANs) provide more...
Differential Privacy in Two-Layer Networks: How DP-SGD Harms Fairness and Robustness
arXiv:2603.04881v1 Announce Type: new Abstract: Differentially private learning is essential for training models on sensitive data, but empirical studies consistently show that it can degrade performance, introduce fairness issues like disparate impact, and reduce adversarial robustness. The theoretical underpinnings of...
From Exact Hits to Close Enough: Semantic Caching for LLM Embeddings
arXiv:2603.03301v1 Announce Type: cross Abstract: The rapid adoption of large language models (LLMs) has created demand for faster responses and lower costs. Semantic caching, reusing semantically similar requests via their embeddings, addresses this need but breaks classic cache assumptions and...
Controllable and explainable personality sliders for LLMs at inference time
arXiv:2603.03326v1 Announce Type: cross Abstract: Aligning Large Language Models (LLMs) with specific personas typically relies on expensive and monolithic Supervised Fine-Tuning (SFT) or RLHF. While effective, these methods require training distinct models for every target personality profile. Inference-time activation steering...
Heterogeneous Time Constants Improve Stability in Equilibrium Propagation
arXiv:2603.03402v1 Announce Type: new Abstract: Equilibrium propagation (EP) is a biologically plausible alternative to backpropagation for training neural networks. However, existing EP models use a uniform scalar time step dt, which corresponds biologically to a membrane time constant that is...
Extending Neural Operators: Robust Handling of Functions Beyond the Training Set
arXiv:2603.03621v1 Announce Type: new Abstract: We develop a rigorous framework for extending neural operators to handle out-of-distribution input functions. We leverage kernel approximation techniques and provide theory for characterizing the input-output function spaces in terms of Reproducing Kernel Hilbert Spaces...
Adaptive Sensing of Continuous Physical Systems for Machine Learning
arXiv:2603.03650v1 Announce Type: new Abstract: Physical dynamical systems can be viewed as natural information processors: their systems preserve, transform, and disperse input information. This perspective motivates learning not only from data generated by such systems, but also how to measure...
Graph Negative Feedback Bias Correction Framework for Adaptive Heterophily Modeling
arXiv:2603.03662v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have emerged as a powerful framework for processing graph-structured data. However, conventional GNNs and their variants are inherently limited by the homophily assumption, leading to degradation in performance on heterophilic graphs....
UniSkill: A Dataset for Matching University Curricula to Professional Competencies
arXiv:2603.03134v1 Announce Type: new Abstract: Skill extraction and recommendation systems have been studied from recruiter, applicant, and education perspectives. While AI applications in job advertisements have received broad attention, deficiencies in the instructed skills side remain a challenge. In this...
Neural Paging: Learning Context Management Policies for Turing-Complete Agents
arXiv:2603.02228v1 Announce Type: new Abstract: The proof that Large Language Models (LLMs) augmented with external read-write memory constitute a computationally universal system has established the theoretical foundation for general-purpose agents. However, existing implementations face a critical bottleneck: the finite and...
Attn-QAT: 4-Bit Attention With Quantization-Aware Training
arXiv:2603.00040v1 Announce Type: new Abstract: Achieving reliable 4-bit attention is a prerequisite for end-to-end FP4 computation on emerging FP4-capable GPUs, yet attention remains the main obstacle due to FP4's tiny dynamic range and attention's heavy-tailed activations. This paper presents the...
CoPeP: Benchmarking Continual Pretraining for Protein Language Models
arXiv:2603.00253v1 Announce Type: new Abstract: Protein language models (pLMs) have recently gained significant attention for their ability to uncover relationships between sequence, structure, and function from evolutionary statistics, thereby accelerating therapeutic drug discovery. These models learn from large protein databases...
Weight Updates as Activation Shifts: A Principled Framework for Steering
arXiv:2603.00425v1 Announce Type: new Abstract: Activation steering promises to be an extremely parameter-efficient form of adaptation, but its effectiveness depends on critical design choices -- such as intervention location and parameterization -- that currently rely on empirical heuristics rather than...
GLUScope: A Tool for Analyzing GLU Neurons in Transformer Language Models
arXiv:2602.23826v1 Announce Type: new Abstract: We present GLUScope, an open-source tool for analyzing neurons in Transformer-based language models, intended for interpretability researchers. We focus on more recent models than previous tools do; specifically we consider gated activation functions such as...
Serendipity with Generative AI: Repurposing knowledge components during polycrisis with a Viable Systems Model approach
arXiv:2602.23365v1 Announce Type: cross Abstract: Organisations face polycrisis uncertainty yet overlook embedded knowledge. We show how generative AI can operate as a serendipity engine and knowledge transducer to discover, classify and mobilise reusable components (models, frameworks, patterns) from existing documents....
U-CAN: Utility-Aware Contrastive Attenuation for Efficient Unlearning in Generative Recommendation
arXiv:2602.23400v1 Announce Type: new Abstract: Generative Recommendation (GenRec) typically leverages Large Language Models (LLMs) to redefine personalization as an instruction-driven sequence generation task. However, fine-tuning on user logs inadvertently encodes sensitive attributes into model parameters, raising critical privacy concerns. Existing...
Intrinsic Lorentz Neural Network
arXiv:2602.23981v1 Announce Type: new Abstract: Real-world data frequently exhibit latent hierarchical structures, which can be naturally represented by hyperbolic geometry. Although recent hyperbolic neural networks have demonstrated promising results, many existing architectures remain partially intrinsic, mixing Euclidean operations with hyperbolic...
LogicGraph : Benchmarking Multi-Path Logical Reasoning via Neuro-Symbolic Generation and Verification
arXiv:2602.21044v1 Announce Type: new Abstract: Evaluations of large language models (LLMs) primarily emphasize convergent logical reasoning, where success is defined by producing a single correct proof. However, many real-world reasoning problems admit multiple valid derivations, requiring models to explore diverse...
Motivation is Something You Need
arXiv:2602.21064v1 Announce Type: new Abstract: This work introduces a novel training paradigm that draws from affective neuroscience. Inspired by the interplay of emotions and cognition in the human brain and more specifically the SEEKING motivational state, we design a dual-model...
Group Orthogonalized Policy Optimization:Group Policy Optimization as Orthogonal Projection in Hilbert Space
arXiv:2602.21269v1 Announce Type: cross Abstract: We present Group Orthogonalized Policy Optimization (GOPO), a new alignment algorithm for large language models derived from the geometry of Hilbert function spaces. Instead of optimizing on the probability simplex and inheriting the exponential curvature...
Certified Circuits: Stability Guarantees for Mechanistic Circuits
arXiv:2602.22968v1 Announce Type: new Abstract: Understanding how neural networks arrive at their predictions is essential for debugging, auditing, and deployment. Mechanistic interpretability pursues this goal by identifying circuits - minimal subnetworks responsible for specific behaviors. However, existing circuit discovery methods...
RepSPD: Enhancing SPD Manifold Representation in EEGs via Dynamic Graphs
arXiv:2602.22981v1 Announce Type: new Abstract: Decoding brain activity from electroencephalography (EEG) is crucial for neuroscience and clinical applications. Among recent advances in deep learning for EEG, geometric learning stands out as its theoretical underpinnings on symmetric positive definite (SPD) allows...
Digital Sovereignty: How Nations Are Asserting Control Over Technology Infrastructure
Countries worldwide are implementing digital sovereignty measures to control data flows, technology standards, and digital infrastructure within their borders.
Improving Spatial Allocation for Energy System Coupling with Graph Neural Networks
arXiv:2602.22249v1 Announce Type: new Abstract: In energy system analysis, coupling models with mismatched spatial resolutions is a significant challenge. A common solution is assigning weights to high-resolution geographic units for aggregation, but traditional models are limited by using only a...
Global River Forecasting with a Topology-Informed AI Foundation Model
arXiv:2602.22293v1 Announce Type: new Abstract: River systems operate as inherently interconnected continuous networks, meaning river hydrodynamic simulation ought to be a systemic process. However, widespread hydrology data scarcity often restricts data-driven forecasting to isolated predictions. To achieve systemic simulation and...
Precision Medicine and Data Privacy: Balancing Innovation with Patient Rights
The rapid advancement of precision medicine creates unprecedented opportunities for personalized treatment while raising complex data privacy and consent challenges.
Enhancing Hate Speech Detection on Social Media: A Comparative Analysis of Machine Learning Models and Text Transformation Approaches
arXiv:2602.20634v1 Announce Type: new Abstract: The proliferation of hate speech on social media platforms has necessitated the development of effective detection and moderation tools. This study evaluates the efficacy of various machine learning models in identifying hate speech and offensive...
ID-LoRA: Efficient Low-Rank Adaptation Inspired by Matrix Interpolative Decomposition
arXiv:2602.20727v1 Announce Type: new Abstract: LoRA has become a universal Parameter-Efficient Fine-Tuning (PEFT) technique that equips Large Language Models (LLMs) to adapt quickly to new tasks. However, when these models are scaled up, even the latest LoRA variants still introduce...