ArXiv TLDR
← All categories

Neural & Evolutionary Computing

Research on neural network architectures, evolutionary algorithms, and bio-inspired computing.

cs.NE · 188 papers

Interpreting V1 Population Activity via Image-Neural Latent Representation Alignment

DINA aligns image and V1 neural representations to interpret visual computations, revealing decoding relies on coarse, low-level visual structure.

2605.04309May 5, 2026Xin Wang, Zhuangzhi Gao, Hongyi Qin +3

QUIVER: Cost-Aware Adaptive Preference Querying in Surrogate-Assisted Evolutionary Multi-Objective Optimization

QUIVER is a cost-aware, adaptive multi-objective optimizer that intelligently balances objective evaluations and heterogeneous preference queries to minimize regret.

2605.04267May 5, 2026Florian A. D. Burnat

phys-MCP: A Control Plane for Heterogeneous Physical Neural Networks

phys-MCP enables unified control and orchestration of diverse physical neural networks across edge and cloud environments.

2605.04256May 5, 2026Stefan Fischer, Maliheh Hariri, Sebastian Otte

Exact and Evolutionary Algorithms for Sequential Multi-Objective Transmission Topology Planning

This paper introduces exact and evolutionary algorithms for sequential multi-objective transmission topology planning, providing a fast, exact solution and a benchmark.

2605.03753May 5, 2026Job Groeneveld, Miguel Muñoz, Jan Viebahn +1

Unifying Dynamical Systems and Graph Theory to Mechanistically Understand Computation in Neural Networks

Unifying dynamical systems and graph theory, this paper shows neural network computation relies on multi-hop pathways, introducing R-RNNs for improved temporal sparsity.

2605.03598May 5, 2026Jatin Sharma, Danyal Akarca, Dan F. M Goodman

Symmetry-Protected Lyapunov Neutral Modes in Equivariant Recurrent Networks

This paper proves equivariant recurrent networks have symmetry-protected neutral modes, ensuring stable long-term memory for continuous variables.

2605.03338May 5, 2026Hanson Hanxuan Mo

Neuromorphic Control for 3D Navigation in Minecraft Using Genetic Algorithms

This paper uses a genetic algorithm to train a neural network for autonomous 3D navigation and parkour in Minecraft.

2605.02628May 4, 2026Eric Zipor

MPCS: Neuroplastic Continual Learning via Multi-Component Plasticity and Topology-Aware EWC

MPCS is a neuroplastic continual learning system integrating 11 mechanisms, achieving high efficiency and demonstrating critical component insights.

2605.02509May 4, 2026Joern Hentsch

Combining Trained Models in Reinforcement Learning

A systematic review of DRL model reuse reveals patterns in transfer, ensemble, and federated learning, noting limitations in current empirical evidence.

2605.02159May 4, 2026Ujjwal Patil, Javad Ghofrani

HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Search

HERCULES introduces a new framework and taxonomy for Neural Architecture Search, integrating hardware efficiency, robustness, and continual learning for deployable AI.

2605.04103May 3, 2026Matteo Gambella, Fabrizio Pittorino, Manuel Roveri

SNNF: An SNN-based Near-Sensor Noise Filter for Dynamic Vision Sensors

SNNF is a near-sensor Spiking Neural Network filter that efficiently removes background noise from Dynamic Vision Sensors, enabling low-power edge AI.

2605.01937May 3, 2026Yahan Yang, Pradeep Kumar Gopalakrishnan, Chang Chip Hong +1

Training Non-Differentiable Networks via Optimal Transport

PolyStep is a gradient-free optimizer using optimal transport to train non-differentiable neural networks, outperforming existing methods significantly.

2605.01928May 3, 2026An T. Le

ShiftLIF: Efficient Multi-Level Spiking Neurons with Power-of-Two Quantization

ShiftLIF is a new multi-level spiking neuron that uses power-of-two quantization for efficient, high-accuracy SNNs in edge sensing.

2605.01866May 3, 2026Kaiwen Tang, Di Yu, Jiaqi Zheng +4

Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance

This paper introduces Probe-Geometry Alignment (PGA) to surgically erase hidden memorization traces in LLMs, making them unrecoverable without affecting capabilities.

2605.01699May 3, 2026Anamika Paul Rupa, Anietie Andy

Benchmarking local Hebbian learning rules for memory storage and prototype extraction

This paper benchmarks seven Hebbian learning rules for associative memory, finding Bayesian-Hebbian rules offer the highest capacity.

2605.01074May 1, 2026Anders Lansner, Andreas Knoblauch, Naresh B Ravichandran +1

Robust volatility updates for Hierarchical Gaussian Filtering

This paper introduces a robust method for updating volatility in Hierarchical Gaussian Filtering, preventing negative posterior precision errors.

2605.00966May 1, 2026Christoph Mathys, Nicolas Legrand, Peter Thestrup Waade +2

Learning to Act and Cooperate for Distributed Black-Box Consensus Optimization

This paper introduces LACMAS, a trajectory-driven framework using LLMs to self-design agent actions and cooperation for distributed black-box consensus optimization.

2605.00691May 1, 2026Zi-Bo Qin, Feng-Feng Wei, Tai-You Chen +1

Spiking Sequence Machines and Transformers

This paper reveals that Spiking Sequence Machines and Transformers independently implement the same five functional operations using cosine similarity.

2605.00662May 1, 2026Joy Bose

Affinity Is Not Enough: Recovering the Free Energy Principle in Mixture-of-Experts

Novel gating mechanisms, inspired by the Free Energy Principle, significantly improve Mixture-of-Experts routing at domain transitions.

2605.00604May 1, 2026Man Yung Wong

Scalable Learning in Structured Recurrent Spiking Neural Networks without Backpropagation

This paper introduces a structured recurrent SNN architecture with local plasticity and neuromodulatory learning for scalable, backpropagation-free training.

2605.00402May 1, 2026Bo Tang, Weiwei Xie
PreviousPage 3 of 10Next

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.