pith. sign in

archive

Every paper Pith has read. Search by title, abstract, or pith.

554 papers in cs.NE · page 4

  1. cs.NE 2026-05-01 reviewed
    Kernel memories limited by crosstalk instability not geometry

    Geometric and dynamical analysis of attractor boundaries and storage limits in kernel Hopfield networks

    Akira Tamamori

  2. cs.AR 2026-04-30 reviewed
    Ring topology on FPGAs runs cortical circuit faster than real time

    NeuroRing: Scaling Spiking Neural Networks via Multi-FPGA Bidirectional Ring Topologies and Stream-Dataflow Architectures

    Muhammad Ihsan Al Hafiz +1

  3. cs.NE 2026-04-30 reviewed
  4. cs.LG 2026-04-30 reviewed
    Physical media could host trillion-parameter AI models

    Physical Foundation Models: Fixed hardware implementations of large-scale neural networks

    Logan G Wright +3

  5. cs.LG 2026-04-30 reviewed
    Dimensionality decides when modularity matters in continual learning

    When Does Structure Matter in Continual Learning? Dimensionality Controls When Modularity Shapes Representational Geometry

    Kathrin Korte +3

  6. cs.NE 2026-04-30 reviewed
    One pretrained model unifies invasive BCI across species and tasks

    UniBCI: Towards a Unified Pretrained Model for Invasive Brain-Computer Interfaces

    Binjie Hong +3

  7. cs.NE 2026-04-30 reviewed
    LLM relation reasoning guides expensive optimization without retraining

    Relation Reasoning with LLMs in Expensive Optimization

    Ye Lu +3

  8. cs.NE 2026-04-29 reviewed
    RCMAES variant of CMA-ES matches top DE algorithms on CEC suites

    RCMAES: A Robust CMA-ES Variant for CEC2026 Competition

    Khoirul Faiq Muzakka +2

  9. cs.LG 2026-04-29 reviewed
    Adaptive per-parameter decay enables selective forgetting

    Learning to Forget: Continual Learning with Adaptive Weight Decay

    Aditya A. Ramesh +2

  10. cs.LG 2026-04-29 reviewed
    Neural assemblies learn causal directions with local rules

    Causal Learning with Neural Assemblies

    Evangelia Kopadi +1

  11. cs.NE 2026-04-29 reviewed
    Spatial mating destabilizes robot evolution unless selection is deterministic

    Population Dynamics in ARIEL Robotics Systems Featuring Embodied Evolution via Spatial Mating Mechanisms

    Victoria Peterson +2

  12. cs.LG 2026-04-29 reviewed
    Adaptive growth matches oracle continual learning accuracy with fewer parameters

    NORACL: Neurogenesis for Oracle-free Resource-Adaptive Continual Learning

    Karthik Charan Raghunathan +3

  13. cs.NE 2026-04-29 reviewed
    Spiking networks get smaller and noise-tolerant through evolution

    Evolutionary feature selection for spiking neural network pattern classifiers

    Michal Valko +2

  14. cs.CL 2026-04-29 reviewed
    Text integration lets big-encoder tiny-decoder ASR models match larger ones

    Text-Utilization for Encoder-dominated Speech Recognition Models

    Albert Zeyer +3

  15. cs.LO 2026-04-29 reviewed
    BDDs compress ACAS-Xu tables while preserving every decision

    Compressing ACAS-Xu Lookup Tables with Binary Decision Diagrams

    Martin Boniol (ISAE-SUPAERO) +4

  16. cs.NE 2026-04-29 reviewed
    Spiking networks cut edge sensor energy by 31x while matching accuracy

    EdgeSpike: Spiking Neural Networks for Low-Power Autonomous Sensing in Edge IoT Architectures

    Gustav Olaf Yunus Laitinen-Fredriksson Lundstrom-Imanov +1

  17. cs.NE 2026-04-29 reviewed
    Spiking networks detect graph anomalies with neuromorphic efficiency

    Neuromorphic Graph Anomaly Detection via Adaptive STDP and Spiking Graph Neural Networks

    Abdul Joseph Fofanah +4

  18. cs.LG 2026-04-28 reviewed
    Genetic programming evolves time series classifiers that beat benchmarks

    EvoTSC: Evolving Feature Learning Models for Time Series Classification via Genetic Programming

    Xuanhao Yang +2

  19. cs.NE 2026-04-28 reviewed
    Scalar measure and file method benchmark EMO stopping criteria

    Benchmarking Stopping Criteria for Evolutionary Multi-objective Optimization

    Kenji Kitamura +1

  20. cs.NE 2026-04-27 reviewed
    Some problems thrive with 1000 individuals

    The Effects of Population Size on the Performance of BEAGLE GPU-Based Genetic Programming Runs

    Nathan Haut +6

  21. cs.NE 2026-04-27 reviewed
    Evolutionary trees recover LLM training histories from weights

    Analysis and Explainability of LLMs Via Evolutionary Methods

    Shannon K. Gallagher +5

  22. cs.CV 2026-04-27 reviewed
    Low-precision NAS recovers two-thirds of edge deployment accuracy loss

    Deployment-Aligned Low-Precision Neural Architecture Search for Spaceborne Edge AI

    Parampuneet Kaur Thind +3

  23. cs.CL 2026-04-27 reviewed
    Strategy descriptions boost LLM evolutionary search

    SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution

    Sichun Luo +9

  24. cs.CL 2026-04-27 reviewed
    Strategy-space layer lifts LLM evolutionary search by 20.6 percent

    SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution

    Sichun Luo +9

  25. cs.CC 2026-04-27 reviewed
    Every primitive recursive function is iteration of one fixed ReLU network

    Primitive Recursion without Composition: Dynamical Characterizations, from Neural Networks to Polynomial ODEs

    Olivier Bournez

  26. cs.NE 2026-04-26 reviewed
    MAEO ensemble matches or beats leading algorithms on benchmarks

    MAEO: Multiobjective Animorphic Ensemble Optimization for Scalable Large-scale Engineering Applications

    Omer F. Erdem +3

  27. cs.LG 2026-04-26 reviewed
    One non-affine function makes deep KANs universal on compacts

    Necessary and sufficient conditions for universality of Kolmogorov-Arnold networks

    Vugar Ismailov

  28. cs.LG 2026-04-26 reviewed
    One non-affine edge function makes deep KANs universal

    Necessary and sufficient conditions for universality of Kolmogorov-Arnold networks

    Vugar Ismailov

  29. cs.NE 2026-04-26 reviewed
    SNN complexity grows exponentially with depth and spike duration

    Generalization Bounds of Spiking Neural Networks via Rademacher Complexity

    Shao-Qun Zhang +1

  30. cs.CV 2026-04-25 reviewed
    Drop low-change layers to halve CNN training time

    Learn&Drop: Fast Learning of CNNs based on Layer Dropping

    Giorgio Cruciata +4

  31. cs.NE 2026-04-25 reviewed
    Tree architecture decides which formulas gradient descent recovers

    Architecture-Induced Recoverability Bias in Differentiable Symbolic Regression

    Chakshu Gupta +1

  32. cs.NE 2026-04-25 reviewed
    Spike-timing rule trains SNNs on FPGA without multiplies

    A Multiplication-Free Spike-Time Learning Algorithm and its Efficient FPGA Implementation for On-Chip SNN Training

    Maryam Mirsadeghi +2

  33. cs.LG 2026-04-24 reviewed
    Thermal inversions trap pollutants near ground in Spitsbergen models

    Collocation-based Robust Physics Informed Neural Networks for time-dependent simulations of pollution propagation under thermal inversion conditions on Spitsbergen

    Leszek Siwik +9

  34. cs.NE 2026-04-24 reviewed
    EEG structure guides diffusion to reconstruct images better

    Structure-Guided Diffusion Model for EEG-Based Visual Cognition Reconstruction

    Yongxiang Lian +4

  35. cs.LG 2026-04-24 reviewed
    Hub routing replaces quadratic attention with linear O(nM) cost

    HubRouter: A Pluggable Sub-Quadratic Routing Primitive for Hybrid Sequence Models

    Abhinaba Basu

  36. cs.CY 2026-04-24 reviewed
    Balanced governance stabilizes human-AI mutualism in model

    A Co-Evolutionary Theory of Human-AI Coexistence: Mutualism, Governance, and Dynamics in Complex Societies

    Somyajit Chakraborty

  37. cs.LG 2026-04-23 reviewed
    Linear-time B-splines speed up Kolmogorov-Arnold networks

    LTBs-KAN: Linear-Time B-splines Kolmogorov-Arnold Networks

    Eduardo Said Merin-Martinez +2

  38. cs.NE 2026-04-23 reviewed
    L-system encoding beats matrix encoding 2.7x in neural net evolution

    L-System Genetic Encoding for Scalable Neural Network Evolution: A Comparison with Direct Matrix Encoding

    Alexander Stuy +1

  39. cs.LG 2026-04-23 reviewed
    Task graph enables crossover transfer across thousands of optimization problems

    Multi-Task Optimization over Networks of Tasks

    Julian Hatzky +3

  40. cs.NE 2026-04-23 reviewed
    Oscillators forecast chaos best inside parametric resonance

    Neuromorphic Computing Based on Parametrically-Driven Oscillators and Frequency Combs

    Mahadev Sunil Kumar +1

  41. cs.LG 2026-04-23 reviewed
    Rational GEM activations narrow GELU gap on ResNets and GPT-2

    Geometric Monomial (GEM): a family of rational 2N-differentiable activation functions

    Eylon E. Krause

  42. cs.NE 2026-04-23 reviewed
    Volatile memristors reach 95.89% MNIST accuracy in reservoir computing

    On the Role of Preprocessing and Memristor Dynamics in Reservoir Computing for Image Classification

    Rishona Daniels +4

  43. cs.NE 2026-04-23 reviewed
    Novelty search generates diverse local optima networks for continuous landscapes

    Novelty-Based Generation of Continuous Landscapes with Diverse Local Optima Networks

    Kippei Mizuta +3

  44. cs.CV 2026-04-23 reviewed
    Additive trust weights raise SSL accuracy on corrupted aerial images

    Trust-SSL: Additive-Residual Selective Invariance for Robust Aerial Self-Supervised Learning

    Wadii Boulila +3

  45. cs.LG 2026-04-23 reviewed
    Co-design accelerates multimodal foundation models

    Focus Session: Hardware and Software Techniques for Accelerating Multimodal Foundation Models

    Muhammad Shafique +5

  46. math.NA 2026-04-22 reviewed
    Hybrid solver runs CO2 sequestration models over three times faster

    CO$_2$ sequestration hybrid solver using isogeometric alternating-directions and collocation-based robust variational physics informed neural networks (IGA-ADS-CRVPINN)

    Askold Vilkha +3

  47. cs.NE 2026-04-22 reviewed
    Detailed CA3 model produces multi-attractor memory dynamics

    Learning Hippo: Multi-attractor Dynamics and Stability Effects in a Biologically Detailed CA3 Extension of Hopfield Networks

    Daniele Corradetti +1

  48. cs.NE 2026-04-22 reviewed
    The paper maps the S4D state space model to a ring of nonlinear oscillators where inputs…

    An explicit operator explains end-to-end computation in the modern neural networks used for sequence and language modeling

    Anif N. Shikder +8

  49. q-bio.NC 2026-04-22 reviewed
    LPC networks reach near-minimal response times with modular designs

    Response time of lateral predictive coding and benefits of modular structures

    Guanghui Cai +3

  50. cs.LG 2026-04-22 reviewed
    Target-free critics cut QD samples by 10x on complex tasks

    Distributional Value Estimation Without Target Networks for Robust Quality-Diversity

    Behrad Koohy +1