400 papers
This paper proposes a surrogate-assisted neuroevolution framework that combines NEAT and NSGA-II to optimize multi-objective chlorine injection strategies in complex water distribution systems, demonstrating superior performance over standard reinforcement learning methods while leveraging a neural network surrogate to bypass the computational costs of traditional hydraulic simulators.
This study proposes a multi-objective genetic algorithm framework that optimizes criminal network disruption strategies by balancing network fragmentation with minimized operational costs derived from spatial distances, demonstrating superior efficiency compared to traditional centrality-based methods using the "Montagna Operation" dataset.
This paper completes a trilogy by proving that the fundamental mechanisms of deep learning, including stochastic gradient descent and neural plasticity, are mathematically isomorphic to the generational dynamics and adaptive behaviors of ant colonies, thereby suggesting a unified theory of learning that transcends biological and artificial substrates.
This paper introduces Sharpness-Aware Surrogate Training (SAST), a method that minimizes the performance gap between smooth surrogate gradients and hard binary spikes in Spiking Neural Networks, thereby significantly improving accuracy and energy efficiency on event-camera benchmarks under strict hardware constraints.
This paper proposes an evolutionary token-level prompt optimization method using a Genetic Algorithm to directly evolve CLIP token vectors, achieving significant improvements in image aesthetic quality and text-image alignment compared to baseline approaches.
This paper derives a closed-form upper bound for the maximum eigenvalue of the Hessian matrix in nonlinear smooth multilayer neural networks with cross-entropy loss, utilizing the Wolkowicz-Styan bound to analytically characterize loss sharpness without relying on numerical eigenspectrum computations.
This paper demonstrates that while heterogeneous fan-in profiles in static sparse networks offer no accuracy advantage over uniform random connectivity due to arbitrary hub placement, initializing dynamic sparse training (RigL) with lognormal profiles matching the equilibrium fan-in distribution significantly improves performance by allowing optimization to refine weights rather than rearrange topology.
This paper demonstrates that the statistical laws governing artificial intelligence architectural evolution, including the distribution of fitness effects and patterns of convergence, mirror those of biological evolution, suggesting that evolutionary dynamics are substrate-independent and driven by fitness landscape topology rather than specific selection mechanisms.
This paper introduces INCRT, an incremental Transformer architecture that autonomously determines its optimal structure during training by dynamically adding and pruning attention heads based on a geometric measure of task requirements, achieving minimal, sufficient models that match or exceed BERT-base performance with significantly fewer parameters and no pre-training.
This paper proposes a ResNet-based patchwise classification method for segmenting intraretinal cysts in Optical Coherence Tomography images, which outperforms previous state-of-the-art approaches by achieving over 70% Dice coefficient across diverse vendors and noise levels using a novel publicly available dataset.
This paper presents a negative result demonstrating that K-way energy probes in standard discriminative Predictive Coding Networks do not provide a richer signal than softmax, as they mathematically reduce to a monotone function of the softmax margin and empirically underperform it across various training and inference conditions on CIFAR-10.
This paper presents a reproducible, zero-shot pipeline for constructing and querying knowledge graphs using local LLMs on consumer hardware, demonstrating that while self-consistency and multi-model diversity significantly enhance multi-hop reasoning performance, strong model consensus can paradoxically indicate collective hallucination, ultimately achieving competitive results with a minimal carbon footprint.
This paper introduces PBT-NCA, a population-based training algorithm that evolves Petri Dish Neural Cellular Automata to sustain open-ended complexity and diverse emergent lifelike phenomena by rewarding behavioral novelty and visual diversity while penalizing static or random states.
PaceLLM is a brain-inspired large language model that enhances long-context understanding and mitigates information decay by integrating a Persistent Activity mechanism for dynamic state retrieval and Cortical Expert clustering for semantic reorganization, achieving significant performance gains on long-context benchmarks without requiring structural overhauls.
This paper demonstrates that the gradient-free evolutionary optimizer sep-CMA-ES outperforms the gradient-based Adam optimizer in inference-time prompt-embedding search for Stable Diffusion XL Turbo, achieving superior aesthetic-quality and prompt-alignment trade-offs with lower resource costs across diverse objectives.
The paper introduces LottaLoRA, a training paradigm demonstrating that low-rank LoRA adapters trained on frozen, randomly initialized backbones can achieve near-full performance across diverse architectures while training only a tiny fraction of parameters, revealing that task-specific information occupies a significantly smaller subspace than the full model size suggests.
This paper argues that despite the distributed architectures of digital neuromorphic processors designed to overcome the von Neumann bottleneck, the high area and energy costs of on-chip memory systems have created a new "memory wall" that threatens their competitiveness in edge applications, necessitating a re-evaluation of memory organization for future research.
The Hierarchical Kernel Transformer (HKT) introduces a multi-scale attention mechanism with trainable causal downsampling that achieves consistent performance gains over standard attention baselines across diverse tasks while maintaining a bounded computational overhead of approximately 1.31x and providing rigorous theoretical guarantees on kernel properties, attention decomposition, and approximation error.
The paper proposes GemS-T, a novel Spiking Vision Transformer architecture that employs multi-dimensional grouped computation and a Grouped-Exponential-Coding-based IF model to simultaneously optimize memory overhead, learning capability, and energy efficiency, overcoming the limitations of existing ANN-SNN conversion and STBP methods.
This paper proposes a multi-agent active inference model demonstrating how the dialectical interplay between conformity and creativity on structured networks endogenously generates shared social realities while simultaneously enabling the formation of distinct cultural niches through selective creative propagation.