61 papers
The paper introduces NOBLE, a pretraining architecture that permanently augments transformer linear layers with learnable nonlinear low-rank branches (specifically using CosNet activation), achieving significant training efficiency and speedups across various models with minimal parameter and time overhead, though its benefits may be hindered by certain stochastic data augmentations.
This paper presents a neural network implementation of Fuzzy Cognitive Maps (FHM) that utilizes Langevin differential dynamics to learn causality patterns, derive inverse solutions for output modification, and evaluates its performance across multiple datasets.
This paper demonstrates that predictive coding graphs constitute a mathematical superset of feedforward neural networks, thereby strengthening their theoretical foundation in machine learning and highlighting the importance of network topology.
This study demonstrates that symmetric reservoir topologies significantly enhance prediction accuracy for low-dimensional nonlinear dynamical systems with limited input dimensions, whereas high-dimensional chaotic systems like turbulent shear flow exhibit minimal sensitivity to such structural symmetries.
Yukthi Opus is a multi-chain hybrid metaheuristic that combines Markov Chain Monte Carlo exploration, greedy local search, and adaptive simulated annealing to achieve robust, budget-efficient optimization for large-scale NP-hard problems.
This paper introduces the Evolutionary Illusion GENerator (EIGen), a generative model based on video predictive neural networks that creates new visual motion illusions, which are confirmed to fool human participants, thereby supporting the hypothesis that such illusions arise from the brain's predictive processing rather than raw visual input and highlighting the value of studying "motivated failures" in AI research.
This paper establishes a principled dynamical theory for sequential retrieval in input-driven Hopfield networks by deriving explicit mathematical conditions for self-sustained memory transitions within a two-timescale architecture, thereby bridging classical associative memory models with modern reasoning systems.
LLEMA is a unified framework that integrates large language models with chemistry-informed evolutionary rules and memory-based refinement to efficiently discover chemically plausible, stable, and multi-objective optimized materials, outperforming existing generative and LLM-only baselines across diverse application domains.
The paper proposes CaRe-BN, a confidence-guided adaptive update and re-calibration mechanism for Batch Normalization that stabilizes training and significantly improves the performance of Spiking Neural Networks in Reinforcement Learning without compromising their energy-efficient inference.
This paper introduces Evolution 6.0, an autonomous robotic system powered by generative AI and multimodal models that enables robots to independently design and fabricate necessary tools while learning to use them to execute complex human-requested tasks.
This paper establishes a rigorous Lyapunov stability framework for a stochastic drift-diffusion model in multi-objective optimization and provides a reproducible Python implementation, demonstrating that while the method may underperform in low-dimensional settings, it offers a mathematically tractable and viable alternative for high-dimensional problems with restricted evaluation budgets.
This paper proposes a robust adaptive reformulation of an entropy-inspired KKT-based convergence indicator, utilizing quantile normalization to effectively assess stationarity in multi-objective optimization without relying on external reference sets.
This paper demonstrates that while the No Free Lunch theorem holds under uniform sampling, algebraic reformulations of permutation-based optimization benchmarks create structured local violations that alter algorithm rankings and performance patterns, necessitating problem-aware algorithm selection.
This paper introduces VietNormalizer, a lightweight, zero-dependency Python library that provides a comprehensive, rule-based pipeline for normalizing diverse Vietnamese text elements—such as numbers, dates, currency, and foreign terms—into pronounceable forms for TTS and NLP applications.
NeuroPareto is a novel framework that integrates rank-centric filtering, uncertainty disentanglement via Deep Gaussian Processes, and a history-conditioned acquisition network to efficiently navigate costly many-objective optimization problems in vast parameter spaces while outperforming existing baselines in convergence and diversity.
This paper introduces "Soft QD," a novel differentiable framework for Quality-Diversity optimization that eliminates the need for discrete behavior space discretization, thereby addressing scalability challenges in high-dimensional problems and enabling the development of the competitive SQUAD algorithm.
This paper introduces Akkumula, a scalable and transparent framework that utilizes Spiking Neural Networks to model realistic driver behavior through evidence accumulation, effectively reproducing braking, accelerating, and steering actions while overcoming the limitations of existing hand-crafted approaches.
This paper proposes a joint hardware-workload co-optimization framework using an evolutionary algorithm to design generalized in-memory computing accelerators that significantly reduce the energy-delay-area product across multiple neural network workloads, overcoming the limitations of single-workload specialized designs.
The paper introduces mlx-snn, the first native Spiking Neural Network library for Apple Silicon built on the MLX framework, which offers a comprehensive set of neuron models and training tools while demonstrating significantly faster training speeds and lower memory usage compared to existing PyTorch-based alternatives on Apple hardware.
The paper presents AutoQD, a theoretically grounded method that automatically discovers diverse, high-performing policies in continuous control tasks by generating behavioral descriptors through random Fourier feature embeddings of policy occupancy measures, thereby eliminating the need for hand-crafted descriptors in Quality-Diversity optimization.