4106 papers
This paper proposes Sign-Prioritized FL (SP-FL), a novel wireless federated learning framework that enhances model training reliability under resource constraints by prioritizing the transmission of gradient signs through a hierarchical resource allocation scheme, achieving up to 9.96% higher accuracy than existing methods on the CIFAR-10 dataset.
This paper proposes a fully data-driven framework that combines adaptively computed, mechanism-aware precursors based on Optimal Time-Dependent (OTD) modes with a Transformer model to significantly extend the prediction horizons for extreme events in high-dimensional chaotic systems like Kolmogorov flow without requiring knowledge of the underlying governing equations.
This paper introduces "Super Neurons," a training-free method that leverages scalar activations from the first generated token to create highly accurate classifiers for categorical VQA, enabling extreme early exiting from the first layer and achieving up to a 5.10x speedup while improving performance over the original network.
This paper proposes an AI-driven framework that improves 5G/6G traffic demand prediction accuracy and spatial generalization by employing a context-aware two-stage splitting strategy and residual error correction to mitigate neighborhood leakage, as validated by experiments across five Canadian cities.
This paper proposes a hierarchical Graph Attention Network (HR-GAT) model that leverages public deployment records to accurately estimate fine-grained spectrum demand across multiple cities, significantly outperforming existing baselines and providing regulators with actionable insights for efficient spectrum sharing and allocation.
This paper introduces MCCOP, a framework that leverages a pretrained diffusion model within a joint sequence-structure latent space to generate minimal, biologically plausible protein mutations that flip predictive model outcomes to desired states, thereby bridging the gap between deep learning predictions and actionable protein engineering.
This paper proposes and evaluates randomized smoothing as an effective, simple, and computationally efficient defense mechanism that significantly enhances the robustness of trajectory prediction models against adversarial attacks without compromising their accuracy in standard settings.
ReTabSyn is a reinforcement learning-based pipeline for realistic tabular data synthesis that prioritizes learning conditional distributions to better preserve feature correlations and improve downstream model utility in low-data, imbalanced, and shifted settings.
The paper introduces EvoKernel, a self-evolving agentic framework that leverages value-driven memory and reinforcement learning to overcome data scarcity in NPU kernel synthesis, significantly improving model correctness and achieving substantial speedups through automated drafting and iterative refinement.
The paper proposes , a novel method that dynamically fuses a Generalist Value Model's prior with sparse RL rollouts via real-time statistical testing to minimize baseline estimation error, thereby achieving faster convergence and over 10% performance gains on mathematical reasoning benchmarks compared to GRPO and DAPO.
This paper introduces 6ABOS, an open-source Python framework that leverages the 6S radiative transfer model and Google Earth Engine to automate the atmospheric correction of EnMAP hyperspectral imagery, successfully validating its accuracy in retrieving water-leaving reflectance over diverse Mediterranean reservoirs.
SNPgen is a two-stage conditional latent diffusion framework that generates privacy-preserving, phenotype-aligned synthetic genotype data, enabling machine learning models trained on synthetic samples to achieve predictive performance comparable to those trained on real data while maintaining strict privacy guarantees and preserving key genetic structures.
The paper proposes LAtte, a novel cross-subject EEG classification framework that combines an InceptionTime-based encoder with a Lorentz Attention Module to learn shared baseline patterns and subject-specific embeddings, thereby achieving robust generalization and superior performance over state-of-the-art methods on multiple datasets.
This paper introduces a parameter-efficient Diffusion Transformer (DiT) with a 2D CNN encoder that generates high-quality, cell-type-specific synthetic regulatory DNA sequences with significantly faster convergence, reduced memorization, and enhanced regulatory activity compared to existing U-Net-based models.
This paper proposes novel kernel-based equivalence tests using kernel Stein discrepancy and Maximum Mean Discrepancy to rigorously assess the absence of statistically meaningful differences between distributions, addressing the limitations of traditional goodness-of-fit tests and existing parametric methods through asymptotic and bootstrap critical value approximations.
This paper introduces Dynamics-Predictive Sampling (DPS), a method that models prompt solving progress as a dynamical system to predict and select informative training samples via online Bayesian inference, thereby significantly reducing the computational overhead of extensive rollouts while accelerating and improving the reinforcement learning finetuning of large reasoning models.
This paper argues that the standard expected value objective in reinforcement learning is inadequate for non-ergodic environments where individual agent performance matters, and it explores the relationship between ergodic reward processes and Markov chains while presenting solutions to optimize long-term performance for single trajectories.
LookaheadKV is a lightweight KV cache eviction framework that achieves fast and accurate long-context inference by using parameter-efficient modules to predict future token importance without the computational overhead of explicit draft generation, thereby outperforming existing methods in both accuracy and speed.
This paper demonstrates that applying Combinatorial Fusion Analysis (CFA) to generate team rankings for the 2024 NCAA tournament yields a 74.60% prediction accuracy, outperforming the best of ten popular public ranking systems and validating CFA as an effective paradigm for enhancing sports prediction precision.
The paper introduces ECoLAD, a deployment-oriented evaluation protocol that reveals how throughput constraints on automotive hardware often render deep learning anomaly detectors infeasible before they lose accuracy, whereas lightweight classical methods maintain both coverage and detection performance.