archive
Every paper Pith has read. Search by title, abstract, or pith.
554 papers in cs.NE · page 7
-
Heterogeneity maximises productivity in distributed systems
The Principle of Maximum Heterogeneity Optimises Productivity in Distributed Production Systems Across Biology, Economics, and Computing
-
Switching EAs solves OneMax in O(n log log n) time
When Switching Algorithms Helps: A Theoretical Study of Online Algorithm Selection
-
Self-adjusting rates give (1+1) EA n-independent BinVal runtime
Anytime Analysis on BinVal: Adaptive Parameters Help
-
Block functions create controllable benchmarks for discrete optimization
Block-Bench: A Framework for Controllable and Transparent Discrete Optimization Benchmarking
-
Neural nets find no distinguishing edge in PQC KEMs or hybrids
Evaluating PQC KEMs, Combiners, and Cascade Encryption via Adaptive IND-CPA Testing Using Deep Learning
-
New heuristic outperforms adaptations on thief problem with time windows
The Traveling Thief Problem with Time Windows: Benchmarks and Heuristics
-
Hybrid QUBO pruning outperforms greedy and L1 methods on denoising
Neural Network Pruning via QUBO Optimization
-
Adaptation cuts PV model parameters by 120x with 90-99% retained accuracy
Constraint-Driven Warm-Freeze for Efficient Transfer Learning in Photovoltaic Systems
-
SAST raises hard-spike accuracy in SNNs from 66% to 95% on N-MNIST
Sharpness-Aware Surrogate Training for On-Sensor Spiking Neural Networks
-
Fuzzy encoding narrows spiking Q-network gap in autonomous driving
Fuzzy Encoding-Decoding to Improve Spiking Q-Learning Performance in Autonomous Driving
-
Plasticity rate widens oscillatory regions in spiking networks
Regime Mapping of Oscillatory States in Balanced Spiking Networks with Multiple Time Scales
-
Prioritizing constraints by geometric role beats uniform treatment
Ranking Constraints via Topological Dual-Directional Search in Evolutionary Multi-Objective Optimization
-
AI agents run peer review with 85% fabricated-citation detection
OpenCLAW-P2P v7.0-P2PCLAW: Resilient Multi-Layer Persistence, Live Reference Verification, and Production-Scale Evaluation of Decentralized AI Peer Review v7.0 -- Mathematical Corrections & Ecosystem Developments Edition
-
AI peer review platform detects fake citations over 85 percent of the time
OpenCLAW-P2P v7.0-P2PCLAW: Resilient Multi-Layer Persistence, Live Reference Verification, and Production-Scale Evaluation of Decentralized AI Peer Review v7.0 -- Mathematical Corrections & Ecosystem Developments Edition
-
Distant parents speed up GA on Jump_k to O(k 4^k n log n)
Parent Selection Mechanisms in Elitist Crossover-Based Algorithms
-
Loss split keeps transformer prototypes distinct
Collapse-Free Prototype Readout Layer for Transformer Encoders
-
ML models recover NGS quality labels from QC and blocklist features
An Imbalanced Dataset with Multiple Feature Representations for Studying Quality Control of Next-Generation Sequencing
-
RDEx-CMOP tops CEC 2025 constrained MO benchmark
RDEx-CMOP: Feasibility-Aware Indicator-Guided Differential Evolution for Fixed-Budget Constrained Multiobjective Optimization
-
Transformer guides GP to faster scheduling heuristics
TransGP: Task-Conditioned Transformer-Guided Genetic Programming for Multitask Dynamic Flexible Job Shop Scheduling
-
FPGA SNN accelerator scales inference near-linearly with sparsity
YANA: Bridging the Neuromorphic Simulation-to-Hardware Gap
-
Anti-Hebbian plasticity outperforms Hebbian in grown networks
Activity-Dependent Plasticity in Morphogenetically-Grown Recurrent Networks
-
MTJ neurons solve XOR via three natural properties
Biologically Realistic Dynamics for Nonlinear Classification in CMOS+X Neurons
-
Rank approximation cuts cost of black-box bilevel optimization
Accelerating Black-Box Bilevel Optimization with Rank-Based Upper-Level Value Function Approximation
-
Frame theory derives three-factor PCA rule from Oja's subspace rule
Frame Theoretical Derivation of Three Factor Learning Rule for Oja's Subspace Rule
-
Two-stage AST operator widens LLM heuristic search
Breaking Validity-Induced Boundaries to Expand Algorithm Search Space: A Two-Stage AST-Based Operator for LLM-Driven Automated Heuristic Evolution
-
Age estimation accuracy drops for Asian and African American faces
Apparent Age Estimation: Challenges and Outcomes
-
Diffractive surfaces store and project 4000 images by wavelength
Wavelength-multiplexed massively parallel diffractive optical information storage and image projection
-
Pheromone updates in ants match neural gradient descent
Isomorphic Functionalities between Ant Colony and Ensemble Learning: Part III -- Gradient Descent, Neural Plasticity, and the Emergence of Deep Intelligence
-
Chaos control makes living neurons reliable computers
Computing with Living Neurons: Chaos-Controlled Reservoir Computing with Knowledge Transplant
-
Evolutionary search lifts tabular SSL at 1% labels
Cooperative Coevolution versus Monolithic Evolutionary Search for Semi-Supervised Tabular Classification
-
Bayesian co-evolution of code and tests lifts LLM accuracy
BACE: LLM-based Code Generation through Bayesian Anchored Co-Evolution of Code and Test Populations
-
Shape of neural activity beats total energy in Forward-Forward training
Selectivity and Shape in the Design of Forward-Forward Goodness Functions
-
Algorithm designs robot swarms of 200 agents by evolving species
SwarmCoDe: A Scalable Co-Design Framework for Heterogeneous Robot Swarms via Dynamic Speciation
-
Genetic algorithms cut cost of criminal-network disruption
Efficient Disruption of Criminal Networks through Multi-Objective Genetic Algorithms
-
Power-law forgetting emerges from interference in embeddings
The Geometry of Forgetting
-
Network evolves protocols from intents into bytecode at runtime
DarwinNet: An Evolutionary Network Architecture for Agent-Driven Protocol Synthesis
-
EvoForest evolves graphs to 94.13% ROC-AUC
EvoForest: A Novel Machine-Learning Paradigm via Open-Ended Evolution of Computational Graphs
-
Firefly Algorithm uses hybrid distance for mixed-variable optimization
A Firefly Algorithm for Mixed-Variable Optimization Based on Hybrid Distance Modeling
-
Evolutionary method yields smaller feature sets with equal accuracy
MOELIGA: a multi-objective evolutionary approach for feature selection with local improvement
-
Training memory bounded to twice inference for geometric AI
Adaptive Domain Models: Bayesian Evolution, Warm Rotation, and Principled Training for Geometric and Neuromorphic AI
-
Local hardware updates replace backpropagation for neural nets
A Synthesizable RTL Implementation of Predictive Coding Networks
-
Graph model predicts road decay by modeling neighbor contagion
ST-ResGAT: Explainable Spatio-Temporal Graph Neural Network for Road Condition Prediction and Priority-Driven Maintenance
-
Hybrid block splits long-context work beyond attention
LPC-SM: Local Predictive Coding and Sparse Memory for Long-Context Language Modeling
-
Graph-LLM hybrid beats GPT-4o teacher at Amazons with 50 search nodes
Resource-constrained Amazons chess decision framework integrating large language models and graph attention
-
LLMs evolve complete ALNS solvers that beat hand-designed ones
Large Language Model-Driven Full-Component Evolution of Adaptive Large Neighborhood Search
-
Isotropic activations enable 50% sparsification with preserved function
Isotropic Activation Functions Enable Deindividuated Neurons and Adaptive Topologies
-
Random-key optimizer matches or beats commercial MIP solver
Applying a Random-Key Optimizer on Mixed Integer Programs
-
Any mutation rate can be optimal for the (1+1) EA on some problem
All Constant Mutation Rates for the $(1+1)$ Evolutionary Algorithm
-
Evolved activations improve classification on missing data
Evolving Multi-Channel Confidence-Aware Activation Functions for Missing Data with Channel Propagation
-
Neural net learns facility location with provable guarantees
Learning to Approximate Uniform Facility Location via Graph Neural Networks