2315 papers
This paper introduces an MCMC-informed neural emulator framework that decouples uncertainty quantification from network architecture by incorporating model-parameter distributions as training inputs, thereby enabling computationally efficient and accurate surrogate modeling for dynamical systems while avoiding exhaustive sampling and unphysical parameter evaluations.
This paper proposes "ForwardFlow," a frequentist deep learning framework that utilizes a branched neural network trained on simulated data to directly estimate statistical parameters, demonstrating advantages such as finite sample exactness, robustness to contamination, and the ability to automatically approximate complex algorithms like the EM-algorithm.
This paper presents a unified Bayesian optimization framework using Gaussian processes with derivative observations and advanced extensions like Optimal Transport and random Fourier features to efficiently accelerate the search for minima and saddle points on potential energy surfaces, bridging theoretical formulation with practical implementation through accompanying Rust code.
This paper proposes Factorized Neural Implicit DMD, a data-driven method that parameterizes the Koopman operator's spectral decomposition via a physics-coded neural field to decouple spatial modes and temporal evolution, thereby enabling stable long-term rollouts, parameter generalization, and spectral analysis for high-dimensional nonlinear dynamical systems.
This study demonstrates that a cross-species transfer learning approach, utilizing an attention-based BiLSTM model pretrained on mouse Patch-seq data and fine-tuned on human data, successfully improves the prediction of conserved GABAergic interneuron subclasses from electrophysiological recordings to transcriptomic identities.
This paper introduces Leech Lattice Vector Quantization (LLVQ), a practical algorithm that leverages the optimal 24-dimensional Leech lattice and an extended Golay code-based search to achieve state-of-the-art LLM compression performance without requiring explicit codebook storage.
V2M-Zero introduces a zero-pair video-to-music generation framework that achieves superior temporal synchronization and semantic alignment by leveraging shared intra-modal temporal structures via event curves, eliminating the need for paired training data or cross-modal supervision.
The paper introduces Neural Field Thermal Tomography (NeFTY), a differentiable physics framework that parameterizes 3D material diffusivity as a continuous neural field optimized via a rigorous numerical solver to achieve high-resolution, quantitative reconstruction of subsurface defects from transient surface temperature measurements, overcoming the limitations of traditional 1D approximations and soft-constrained PINNs.
XConv is a drop-in replacement for standard convolutional layers that significantly reduces memory usage during training by storing compressed activations and approximating weight gradients via randomized trace estimation, while maintaining performance comparable to exact gradient methods without imposing architectural constraints or requiring codebase modifications.
This survey systematically reviews decentralized federated learning methods from 2018 to early 2026, categorizing them into traditional distributed and blockchain-based architectures, proposing a unified challenge-driven taxonomy, and outlining future research directions to address security, privacy, and system-level trade-offs in coordinator-free settings.
This paper proves that randomly initialized, polynomially over-parameterized convolutional neural networks contain structured subnetworks capable of approximating smaller networks without training, by developing new mathematical tools to overcome previous limitations in analyzing the Strong Lottery Ticket Hypothesis for structured pruning.
This paper proposes a novel, theoretically grounded graph clustering method that constructs homophilic and heterophilic graphs to build low-pass and high-pass filters enhanced by a squeeze-and-excitation block, effectively addressing the limitations of existing approaches in handling the structural disparities of real-world graphs.
This paper proposes a deep learning framework that jointly discovers optimal coordinates and flow maps to enable precise, computationally efficient time-stepping for multiscale systems, achieving state-of-the-art predictive accuracy with reduced costs on complex models like the Fitzhugh-Nagumo neuron and Kuramoto-Sivashinsky equations.
This paper proposes a fairness-aware multi-group target detection approach for online discussions that effectively reduces bias across demographic groups while maintaining strong predictive performance, particularly in the context of toxicity detection where harm is highly dependent on the targeted group.
This paper proposes and evaluates a distributed multi-agent Q-learning solution for HD map updates in vehicular networks that reduces computational burdens and compatibility issues while significantly improving time latencies across various traffic scenarios compared to single-agent approaches.
This paper introduces Sparse Variational Student-t Processes (SVTP), a scalable framework that extends sparse inducing point methods to Student-t processes via novel inference algorithms and natural gradient optimization, achieving superior robustness to outliers and heavy-tailed data with significantly faster convergence and lower prediction error compared to sparse Gaussian processes on large datasets.
This paper introduces HYGENE, the first deep learning-based diffusion method that generates realistic and diverse hypergraphs by iteratively expanding a bipartite representation from a single connected node pair through a progressive local expansion process.
This paper introduces a unified framework that models quantization and sparsification as additive noise to derive a principled, noise-corrective gradient path, enabling the stable training of neural networks at arbitrary low precisions and sparsity levels without relying on heuristic estimators like the Straight-Through Estimator.
The paper introduces ARLBench, a flexible and efficient benchmark for hyperparameter optimization in reinforcement learning that utilizes a representative subset of tasks to enable cost-effective comparisons of diverse AutoRL methods and lower the barrier to entry for researchers with limited compute resources.
The paper introduces DRUPI (Dataset Condensation using Privileged Information), a framework that enhances dataset condensation by synthesizing auxiliary privileged information, such as feature or attention labels, alongside reduced data to significantly improve model training performance across various benchmarks.