Latest Neural Architectures Research Papers

The newest Neural Architectures papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Neural Architectures so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• A Spiking Neural Architecture for Coordinating Arm and Locomotor Control
  Lea Steffen, Kathryn Simone, Graeme Damberger, Travis DeWolf et al. · arXiv · Jun 9, 2026

  Spiking Neural Networks (SNNs) coupled with neuromorphic hardware offer energy-efficient solutions for humanoid robot control. However, existing SNN-based motor control systems address bipedal locomotion and arm control in isolation, leavin…

• Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design
  Wenxin Wang, Yule Hou, Yu Ji, Peng Qu et al. · arXiv · Jun 9, 2026

  Local deployment of large Mixture-of-Experts (MoE) models falls short of the service quality achieved in cloud-scale environments, even under low-concurrency workloads. We identify four key gaps in local MoE inference: reliance on capacity-…

• LLM-Guided Neural Architecture Search for Robust Co-Design of Physical Neural Networks
  Tyler King, Timothee Leleu · arXiv · Jun 9, 2026

  Deploying neural networks on unconventional hardware demands architectures that co-optimize task accuracy and platform-specific constraints such as energy cost, physical non-idealities, and numerical precision. Existing neural architecture …

• Discovering Interpretable Multi-Parameter Control Policies for Evolutionary Algorithms Using Deep Reinforcement Learning
  Tai Nguyen, Phong Le, Carola Doerr, Nguyen Dang · arXiv · Jun 8, 2026

  While deep Reinforcement Learning (deep-RL) has been increasingly applied to parameter control in evolutionary algorithms, rigorous theoretical analysis of parameter control remains largely restricted to single-parameter settings, owing to …

• Spiking Neural Network inference on FPGAs with hls4ml
  Barry M. Dillon · arXiv · Jun 8, 2026

  Spiking Neural Networks (SNNs) provide a naturally temporal machine-learning framework. Their neurons maintain an internal state and propagate information through discrete spikes, enabling low-latency temporal inference. Although SNNs are o…

• Quality-Diversity Search in Sound Generation: Investigating Innovation Engines for Audio Exploration
  Björn Þór Jónsson, Çağrı Erdem, Stefano Fasciani, Kyrre Glette · arXiv · Jun 8, 2026

  This study addresses the challenges composers and sound designers face in creating and refining tools to achieve their musical goals. Using evolutionary processes to promote diversity and foster serendipitous discoveries, we automate the se…

• Hybrid Metaheuristic Combining the Dragonfly Algorithm and Tabu Search for the Traveling Salesman Problem
  Ammar Bouketta · arXiv · Jun 8, 2026

  The Traveling Salesman Problem (TSP) is a classical NP-hard combinatorial optimization problem that aims to find the shortest Hamiltonian cycle visiting each city exactly once and returning to the starting point. This paper proposes a hybri…

• Local Search on Vertex Coloring for Bipartite Graphs
  Johanna Gasse · arXiv · Jun 8, 2026

  Local search is a well-known heuristic method used in optimization. In this thesis, we explore its capabilities on the vertex coloring problem, an $NP$-hard problem with relevance in both theoretical analysis and practical application. To r…

• Quantitative Performance Analysis of Stopping Criteria for CMA-ES
  Ryoji Tanabe · arXiv · Jun 8, 2026

  Covariance matrix adaptation evolution strategy (CMA-ES) is a state-of-the-art black-box optimization algorithm. In general, CMA-ES uses a portfolio of multiple stopping criteria to automatically determine when to stop the search. This mech…

• OpenOpt: An Open-Source SRAM Optimizer Based on Equivalent Circuit Model
  Yikai Wang, Yiheng Wu, Can Wang, Bohao Liu et al. · arXiv · Jun 8, 2026

  This paper proposes a co-optimization framework that jointly optimizes SRAM architecture and transistor sizing using equivalent circuit models. The framework simplifies inactive SRAM cells into equivalent RC loads and static power models, a…

• Quantitative Promise Theory: Intentionality and Inference in Autonomous Agents
  Mark Burgess · arXiv · Jun 7, 2026

  I discuss some quantitative representations of Promise Theory for processes involving autonomous agents. Agent models are common in software systems, machine learning, and biology, for example, but may also apply to physics and other forms …

• Gray-Box Optimization and the Vertex Coloring Problem
  Johanna Gasse, Antonia Heinen, Hendrik Higl, Timo Kötzing · arXiv · Jun 6, 2026

  Gray-box optimization is an approach for making some problem-specific information available to the algorithm while still relying on fitness information as the main guide to an optimum. This approach was shown to be beneficial in various com…

• Representational Similarity and Model Behavior in Multi-Agent Interaction
  Yujin Potter, Seun Eisape, Shiyang Lai, Alexander Huth et al. · arXiv · Jun 5, 2026

  Researchers have shown that neural similarity among humans predicts social closeness and cooperative success, whereas innovation often emerges from interactions among dissimilar individuals. We investigate whether these principles extend to…

• Sparsely gated tiny linear experts
  Simon Schug · arXiv · Jun 5, 2026

  Sparsity allows scaling model parameters without proportionally increasing computational cost. While mixture of experts (MoE) models are made increasingly sparse, individual experts typically remain large and dense. Here, we demonstrate tha…

• Combinatorial Landscape Analysis for Dominating Set and Vertex Coloring
  Johanna Gasse, Antonia Heinen, Felix Knöfel, Timo Kötzing et al. · arXiv · Jun 5, 2026

  We analyze the two combinatorial problems of Dominating Set and Vertex Coloring regarding what kind of local optima are present for various instances. For a variety of graph classes each, we determine whether the induced landscapes are unim…

• LLM-Guided Evolution for Medical Decision Pipelines
  Ivan Sviridov, Artem Oskin, Ivan Panin, Iaroslav Bespalov et al. · arXiv · Jun 5, 2026

  Adapting large language models (LLMs) to clinical workflows often requires costly fine-tuning or manual prompt and pipeline engineering. We study LLM-guided MAP-Elites evolution as an inference-time alternative for discovering medical decis…

• The Whale That Outswam Evolution: Swarm Intelligence Maximises Memory in Connectome Reservoirs
  Anmol Guragain, Savvas Kakalis, Juan Ignacio Godino-Llorente · arXiv · Jun 5, 2026

  Reservoir computing exploits the fixed dynamics of a recurrent network for temporal processing, requiring only a trained linear readout. Biological neural connectomes, shaped by millions of years of evolution, may encode computational struc…

• A Data-Free Symbolic Regression Approach for Solving Equations
  Sergei Garmaev, Vinay Sharma, Olga Fink · arXiv · Jun 5, 2026

  Many equations arising in science currently cannot be solved by available analytical techniques and are therefore solved numerically, without yielding explicit symbolic expressions. Existing symbolic regression approaches can recover symbol…

• Emergent Language as an Approach to Conscious AI
  Zengqing Wu, Chuan Xiao · arXiv · Jun 4, 2026

  The question of whether artificial systems can be conscious remains open, in part because existing approaches either evaluate systems against theory-derived checklists (discriminative) or engineer consciousness-inspired modules directly (ar…

• Hub-Aware Hybrid Search: Accelerating the Locally Aligned Ant Technique
  Simone Vilardi, Reynier Peletier, Felipe Contreras, Kerstin Bunte · ESANN 2026 · Jun 4, 2026

  Finding manifold structures in noisy and high-dimensional point clouds is a challenging but important problem. In astronomical observation survey and simulation data the detection of filaments, streams (1D), walls (2D) and clusters (3D) giv…

• ITP-STDP: An Intrinsic-Timing Power-of-Two Learning Engine for On-Chip SNN Training
  Haihang Xia, Xinyu Zhao, Xuecheng Wang, John Goodenough et al. · arXiv · Jun 4, 2026

  Spiking neural networks (SNNs) have the potential to emerge as the third generation of neural networks and have attracted increasing attention across a wide range of applications. However, the large number of synaptic connections in SNNs le…

• Sample-efficient Low-level Motion Planning for Robotic Manipulation Tasks via Zero-shot Transfer Learning
  Yuanzhi He, Victor Romero-Cano, José J. Patiño, Juan David Hernández et al. · arXiv · Jun 4, 2026

  As robotic systems become more sophisticated, the growing complexity of their motion planning models and the longer training times pose substantial challenges. Evolutionary algorithms such as the Sample-efficient Cross-Entropy Method (iCEM)…

• Depth over Fidelity in Fixed-Budget Noisy Evolution Strategies
  Sichen Wang, Zhipeng Lu · arXiv · Jun 4, 2026

  Noisy evolution strategies under fixed evaluation budgets face a depth-fidelity trade-off: spending evaluations to denoise intra-generation rankings reduces the number of distribution updates the optimizer can execute. We argue for depth ov…

• Quantifying Uncertainty In Wide Two-Layer Neural Networks: On The Law Of The Limiting Fluctuation Process
  Arnaud Descours, Arnaud Guillin, Geoffrey Lacour, Manon Michel et al. · arXiv · Jun 4, 2026

  Uncertainty quantification in neural networks prediction is a main issue for usual applications. Our approach seeks at reducing computation costs by directly evaluating uncertainty using PDE's information on the asymptotic variance, rather …

• Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training
  Yucheng Chen · arXiv · Jun 4, 2026

  Forward-Forward (FF) learning [Hinton, 2022] replaces backpropagation with strictly layer-local goodness updates. Recent FF-CNN work has narrowed the gap to BP on 32x32 benchmarks, raising the question of whether layer-local training is bec…

• From Prediction to Self: Developmental Conditions for Agency in Minimal Neural Systems
  Evan Ye · arXiv · Jun 4, 2026

  How does a system that merely predicts the world come to distinguish its own causal influence from everything else? We trace this transition in a minimal 192-dimensional GRU through 40 controlled experiments arranged as a developmental sequ…

• Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution
  Can Gurkan, Forrest Stonedahl, Uri Wilensky · arXiv · Jun 3, 2026

  When an LLM repeatedly mutates a program, does it explore new forms or circle back to the same ones? We study this question by analyzing LLM-driven mutation chains in the absence of selection pressure within a domain-specific language, vary…

• Multi-Column RBF Neural Network Using Adaptive and Non-Adaptive Particle Swarm Optimization
  Ammar Hoori, Yuichi Motai · arXiv · Jun 3, 2026

  The radial basis function neural network (RBFN) trained with a gradient descending algorithm provides an effective fully connected structure in both shallow and deep networks. The error correction (ErrCor), a state-of-the-art gradient-based…

• U-Net-Accelerated Quality-Diversity Optimization for Climate-Adaptive Urban Layouts
  Alexander Hagg, Tania Guerrero, Dirk Reith · arXiv · Jun 3, 2026

  Optimizing urban layouts for climate adaptation requires balancing building density with cold-air ventilation. Because physics-based climate simulations are computationally expensive, planners typically evaluate fewer than ten manual design…

• Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning
  Damian Lebiedź, Robert Ślepaczuk · arXiv · Jun 3, 2026

  This study aims to determine whether the application of Deep Reinforcement Learning (DRL) as a specialized execution overlay can enhance pair trading in highly volatile cryptocurrency markets. Although classical implementations of the strat…