Elimination-compensation pruning for fully-connected neural networks
arXiv:2602.20467v1 Announce Type: new Abstract: The unmatched ability of Deep Neural Networks in capturing complex patterns in large and noisy datasets is often associated with their large hypothesis space, and consequently to the vast amount of parameters that characterize model...
Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer
arXiv:2602.19058v1 Announce Type: new Abstract: Large vision-language models (LVLMs) have rapidly advanced across various domains, yet they still lag behind strong text-only large language models (LLMs) on tasks that require multi-step inference and compositional decision-making. Motivated by their shared transformer...
Weak-Form Evolutionary Kolmogorov-Arnold Networks for Solving Partial Differential Equations
arXiv:2602.18515v1 Announce Type: new Abstract: Partial differential equations (PDEs) form a central component of scientific computing. Among recent advances in deep learning, evolutionary neural networks have been developed to successively capture the temporal dynamics of time-dependent PDEs via parameter evolution....
Hyperbolic Busemann Neural Networks
arXiv:2602.18858v1 Announce Type: new Abstract: Hyperbolic spaces provide a natural geometry for representing hierarchical and tree-structured data due to their exponential volume growth. To leverage these benefits, neural networks require intrinsic and efficient components that operate directly in hyperbolic space....
SPQ: An Ensemble Technique for Large Language Model Compression
arXiv:2602.18420v1 Announce Type: new Abstract: This study presents an ensemble technique, SPQ (SVD-Pruning-Quantization), for large language model (LLM) compression that combines variance-retained singular value decomposition (SVD), activation-based pruning, and post-training linear quantization. Each component targets a different source of inefficiency:...
NIMMGen: Learning Neural-Integrated Mechanistic Digital Twins with LLMs
arXiv:2602.18008v1 Announce Type: cross Abstract: Mechanistic models encode scientific knowledge about dynamical systems and are widely used in downstream scientific and policy applications. Recent work has explored LLM-based agentic frameworks to automatically construct mechanistic models from data; however, existing problem...
COMBA: Cross Batch Aggregation for Learning Large Graphs with Context Gating State Space Models
arXiv:2602.17893v1 Announce Type: new Abstract: State space models (SSMs) have recently emerged for modeling long-range dependency in sequence data, with much simplified computational costs than modern alternatives, such as transformers. Advancing SMMs to graph structured data, especially for large graphs,...
An effective Genetic Programming Hyper-Heuristic for Uncertain Agile Satellite Scheduling
arXiv:2602.15070v1 Announce Type: cross Abstract: This paper investigates a novel problem, namely the Uncertain Agile Earth Observation Satellite Scheduling Problem (UAEOSSP). Unlike the static AEOSSP, it takes into account a range of uncertain factors (e.g., task profit, resource consumption, and...
ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation Patterns
arXiv:2602.15521v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) effectively scales model capacity while preserving computational efficiency through sparse expert activation. However, training high-quality MoEs from scratch is prohibitively expensive. A promising alternative is to convert pretrained dense models into sparse MoEs....
Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL
arXiv:2602.15564v1 Announce Type: new Abstract: Text-to-SQL has recently achieved impressive progress, yet remains difficult to apply effectively in real-world scenarios. This gap stems from the reliance on single static workflows, fundamentally limiting scalability to out-of-distribution and long-tail scenarios. Instead of...
STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
arXiv:2602.15620v1 Announce Type: new Abstract: Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic techniques such as entropy regularization and reweighting to maintain stability. In practice, they often experience late-stage...
Entropy-Based Data Selection for Language Models
arXiv:2602.17465v1 Announce Type: new Abstract: Modern language models (LMs) increasingly require two critical resources: computational resources and data resources. Data selection techniques can effectively reduce the amount of training data required for fine-tuning LMs. However, their effectiveness is closely related...
Sink-Aware Pruning for Diffusion Language Models
arXiv:2602.17664v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) incur high inference cost due to iterative denoising, motivating efficient pruning. Existing pruning heuristics largely inherited from autoregressive (AR) LLMs, typically preserve attention sink tokens because AR sinks serve as stable...
TopoFlow: Physics-guided Neural Networks for high-resolution air quality prediction
arXiv:2602.16821v1 Announce Type: new Abstract: We propose TopoFlow (Topography-aware pollutant Flow learning), a physics-guided neural network for efficient, high-resolution air quality prediction. To explicitly embed physical processes into the learning framework, we identify two critical factors governing pollutant dynamics: topography...
Input out, output in: towards positive-sum solutions to AI-copyright tensions
Abstract This article addresses the legal tensions between artificial intelligence (AI) development and copyright law, exploring policymaking on the use of copyrighted data for AI training at the input level and the generation of AI content at the output level....
Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation
arXiv:2602.15897v1 Announce Type: new Abstract: Training and fine-tuning large-scale language models largely benefit from collaborative learning, but the approach has been proven vulnerable to gradient inversion attacks (GIAs), which allow adversaries to reconstruct private training data from shared gradients. Existing...
A Koopman-Bayesian Framework for High-Fidelity, Perceptually Optimized Haptic Surgical Simulation
arXiv:2602.15834v1 Announce Type: new Abstract: We introduce a unified framework that combines nonlinear dynamics, perceptual psychophysics and high frequency haptic rendering to enhance realism in surgical simulation. The interaction of the surgical device with soft tissue is elevated to an...
Multi-Objective Alignment of Language Models for Personalized Psychotherapy
arXiv:2602.16053v1 Announce Type: new Abstract: Mental health disorders affect over 1 billion people worldwide, yet access to care remains limited by workforce shortages and cost constraints. While AI systems show therapeutic promise, current alignment approaches optimize objectives independently, failing to...
Investigating GNN Convergence on Large Randomly Generated Graphs with Realistic Node Feature Correlations
arXiv:2602.16145v1 Announce Type: new Abstract: There are a number of existing studies analysing the convergence behaviour of graph neural networks on large random graphs. Unfortunately, the majority of these studies do not model correlations between node features, which would naturally...
ASPEN: Spectral-Temporal Fusion for Cross-Subject Brain Decoding
arXiv:2602.16147v1 Announce Type: new Abstract: Cross-subject generalization in EEG-based brain-computer interfaces (BCIs) remains challenging due to individual variability in neural signals. We investigate whether spectral representations offer more stable features for cross-subject transfer than temporal waveforms. Through correlation analyses across...
ModalImmune: Immunity Driven Unlearning via Self Destructive Training
arXiv:2602.16197v1 Announce Type: new Abstract: Multimodal systems are vulnerable to partial or complete loss of input channels at deployment, which undermines reliability in real-world settings. This paper presents ModalImmune, a training framework that enforces modality immunity by intentionally and controllably...
Geometric Neural Operators via Lie Group-Constrained Latent Dynamics
arXiv:2602.16209v1 Announce Type: new Abstract: Neural operators offer an effective framework for learning solutions of partial differential equations for many physical systems in a resolution-invariant and data-driven manner. Existing neural operators, however, often suffer from instability in multi-layer iteration and...
Avey-B
arXiv:2602.15814v1 Announce Type: new Abstract: Compact pretrained bidirectional encoders remain the backbone of industrial NLP under tight compute and memory budgets. Their effectiveness stems from self-attention's ability to deliver high-quality bidirectional contextualization with sequence-level parallelism, as popularized by BERT-style architectures....
Prescriptive Scaling Reveals the Evolution of Language Model Capabilities
arXiv:2602.15327v1 Announce Type: cross Abstract: For deploying foundation models, practitioners increasingly need prescriptive scaling laws: given a pre training compute budget, what downstream accuracy is attainable with contemporary post training practice, and how stable is that mapping as the field...
Size Transferability of Graph Transformers with Convolutional Positional Encodings
arXiv:2602.15239v1 Announce Type: new Abstract: Transformers have achieved remarkable success across domains, motivating the rise of Graph Transformers (GTs) as attention-based architectures for graph-structured data. A key design choice in GTs is the use of Graph Neural Network (GNN)-based positional...
Complex-Valued Unitary Representations as Classification Heads for Improved Uncertainty Quantification in Deep Neural Networks
arXiv:2602.15283v1 Announce Type: new Abstract: Modern deep neural networks achieve high predictive accuracy but remain poorly calibrated: their confidence scores do not reliably reflect the true probability of correctness. We propose a quantum-inspired classification head architecture that projects backbone features...
FedPSA: Modeling Behavioral Staleness in Asynchronous Federated Learning
arXiv:2602.15337v1 Announce Type: new Abstract: Asynchronous Federated Learning (AFL) has emerged as a significant research area in recent years. By not waiting for slower clients and executing the training process concurrently, it achieves faster training speed compared to traditional federated...
ExLipBaB: Exact Lipschitz Constant Computation for Piecewise Linear Neural Networks
arXiv:2602.15499v1 Announce Type: new Abstract: It has been shown that a neural network's Lipschitz constant can be leveraged to derive robustness guarantees, to improve generalizability via regularization or even to construct invertible networks. Therefore, a number of methods varying in...
From Scarcity to Scale: A Release-Level Analysis of the Pashto Common Voice Dataset
arXiv:2602.14062v1 Announce Type: new Abstract: Large, openly licensed speech datasets are essential for building automatic speech recognition (ASR) systems, yet many widely spoken languages remain underrepresented in public resources. Pashto, spoken by more than 60 million people, has historically lacked...
Character-aware Transformers Learn an Irregular Morphological Pattern Yet None Generalize Like Humans
arXiv:2602.14100v1 Announce Type: new Abstract: Whether neural networks can serve as cognitive models of morphological learning remains an open question. Recent work has shown that encoder-decoder models can acquire irregular patterns, but evidence that they generalize these patterns like humans...