AI & Machine Learning · Computer Science & AI
Neural & Evolutionary Computing
The newest papers in Neural & Evolutionary Computing that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
324 papers, from 4 September 2026 to 5 November 2026: 324 arXiv preprints.
Get the few papers worth your time in Neural & Evolutionary Computing every morning.
Follow Neural & Evolutionary Computing and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 3
The Power Watershed as a Differentiable Segmentation Layer
Can a Watershed transform, the classical tool of morphological segmentation, be placed at the end of a deep network and trained through?SpikeAD: Toward Multiplication-Free Spike-Controlled Neuromorphic Architecture for Energy-Efficient Small Object Detection
Energy-constrained aerial platforms require accurate object detection under strict power and latency budgets, yet conventional inference remains bottlenecked by multiply-accumulate (MAC) operations.State-Dependent Memristor Dynamics for Device-Informed Spike-Timing-Dependent Plasticity in Spiking Neural Networks
This work investigates device-informed spike-timing-dependent plasticity (STDP) in spiking neural networks using a literature-derived threshold-memristor model.Physiology-Informed Audio Quality and Listening Effort Estimation
Audio systems aim to maximise the listener's perceived quality, traditionally evaluated through mean opinion scoring (MOS), a subjective process that is slow, costly, and collected only after…Where Should the Evaluation Budget Go in LLM-Driven Agent Scaffold Evolution?
Large language model (LLM)-driven agent scaffold evolution improves agent workflows through iterative candidate generation and evaluation.Every route counts, but some count more: a max-plus view of the C. elegans brain
Brains do not simply add up every signal they receive: they select which routes dominate.GNBG-C: A Unified and Configurable Benchmark Generator for Constrained Continuous Optimization
Many real-world optimization tasks are governed not only by what should be optimized, but also by what is allowed: a solution must first satisfy physical, operational, safety, budgetary, or…GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting
Traffic forecasting requires modeling complex temporal dynamics and the spatial dependencies imposed by road topology.SLICE-CiM: Selective Layer-wise Inference Control Engine with Confidence-Based Early Exit for SRAM based Digital Compute-in-Memory
Digital SRAM compute-in-memory (CIM) macros enable energy-efficient CNN inference by eliminating off-chip weight transfers; however, peripheral control logic introduces three inefficiencies: bit-…Intellectual Property Protection of Hyperdimensional Computing Classifiers: Black-Box Ownership Verification via Model Watermarking
Hyperdimensional computing (HDC) offers efficient learning and inference for resource-constrained systems, yet ownership verification of its models remains underexplored.A Dynamic Decomposition Strategy for the MOEA/D With Proven Performance Guarantees
The MOEA/D is one of the most successful multi-objective evolutionary algorithms.Understanding the Co-evolutionary Solution Exchange of the MOEA/D: Already the Smallest Communication Radius Gives the Best-Possible Speed-Up
Besides domination-based algorithms such as the NSGA-II, the decomposition-based MOEA/D is one of the most popular and successful optimization heuristic for multi-objective problems.An Interactive Evolutionary Multiobjective Optimization Algorithm Based on Interpretable Active Preference Learning
Many decision-making tasks are inherently multi-objective.Agentic Algorithm Design: LLMs that Propose, Formalise, and Prove Runtime Bounds for Evolutionary Algorithms in Lean
LLMs now prove hard theorems in Lean.TRON: Transferring Naturally Evolved Network Architectures into Neuroevolution
Neural architecture search (NAS) is challenging because of the vast, non-linear space of artificial neural network (ANN) topologies.Dynamical coarse-graining of neural-network training
Dynamical coarse-graining of neural networks gives macroscopic observables and enables training to be predicted, and controlled in a state space far smaller than the parameter space.Characterizing Privacy Leakage in Spiking Neural Networks: A Systematic Analysis of Temporal Dynamics, Stochasticity, Neuronal Dynamics and Learning Mechanisms
Spiking neural networks (SNNs) encode information not only in whether neurons fire but also in when they fire, and this temporal dimension shapes what a trained network reveals about its training…ChroNoC: A Tableless TDM Circuit-Switched NoC With Delay-Aware Deployment for Time-Sensitive Neuromorphic Computing
Time-sensitive neuromorphic architectures require predictable interconnects to preserve precise event timing.Functional Superoscillations in a Wave Processor
Physical wave processors are constrained by diffraction, but the bandwidth of the mathematical functions they implement need not be set by it.Edge-Centric Adaptive Neural Activation via Parametric Tanh Functions
Within the broader landscape of artificial intelligence architectures, this paper introduces a compact, edge-centric neural framework that resolves the computational bottlenecks of modern…