3821 papers
This paper introduces Scorio, an open-source library that formalizes and implements statistical methods for reliably ranking reasoning LLMs under test-time scaling, demonstrating that most approaches achieve high agreement with a Bayesian gold standard across multiple Olympiad-style math benchmarks.
This paper introduces a bio-inspired self-supervised learning framework for wrist-worn IMU signals that leverages motor control submovement theory to tokenize motion into segments, enabling a Transformer encoder to outperform existing baselines in human activity recognition through masked segment reconstruction on a large-scale NHANES dataset.
The paper introduces Pointy, a lightweight transformer-based point cloud architecture that, despite being trained on a small dataset of only 39k samples, outperforms larger foundation models and approaches state-of-the-art results through a carefully curated training setup and rigorous, standardized evaluation framework.
This paper introduces TOSSS, a CVE-based benchmark designed to evaluate the ability of Large Language Models to distinguish between secure and vulnerable code snippets in C/C++ and Java, revealing that current models achieve security scores ranging from 0.48 to 0.89.
This paper proposes a privacy-preserving Federated Learning framework that jointly optimizes multi-RIS configuration and eavesdropper detection in B5G cell-free mmWave networks, achieving a 30% improvement in secrecy rate while maintaining high detection accuracy through collaborative DCNN training on local Channel State Information.
This paper proposes a Federated Learning framework for LEO 6G Non-Terrestrial Networks that leverages High-Altitude Platform Stations to distribute beam selection tasks, demonstrating that a Graph Neural Network model outperforms a Multi-Layer Perceptron in prediction accuracy and stability, especially at low elevation angles.
This paper demonstrates that MLP layers in transformer models function as binary routing switches that direct continuous signals through distinct computational paths based on consensus and exception-handling neuron architectures, a mechanism that explains the limitations of smooth polynomial approximations and is validated by significant causal performance differences.
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.