This paper proposes a preconditioning layer for stable weight conditioning in LLM training.

The paper proposes FOAM, an adaptive damping method that stabilizes the Shampoo optimization algorithm by dynamically controlling damping and eigendecomposition frequency, thereby reducing staleness-i…

The paper enhances the security of the PolyProtect biometric template protection method by proposing a key selection algorithm that significantly increases the difficulty of inverting protected face t…

This study explores using machine learning surrogates to accelerate complex numerical simulations of mechanical thrombectomy, achieving significant speedups but noting stability issues with complex ge…

The paper proposes using a Physics-Informed Neural Network (PINN) residual as an efficient, physics-guided indicator to guide adaptive mesh refinement (AMR) for classical finite-difference PDE solvers…

The paper proposes a novel, highly secure real-time ECG monitoring framework that uses a patient's own ECG signal characteristics to generate unique, dynamic encryption keys, ensuring confidential dat…

The paper introduces Cellular Sheaf Neural Operators, a discretization-aware framework that models constrained PDEs by representing physical states on oriented cell complexes to enforce structure-pres…

The paper introduces CORE, a contrastive evidence organization method, which significantly improves the accuracy of LLM-based predictions of gene expression changes following cellular perturbations by…

The paper introduces Dual-Spectral Flow Matching (DSFM), a novel generative framework that uses wavelet and cosine transforms to synthesize highly realistic, non-stationary fMRI time series for improv…

CSULoRA is a post-hoc method that corrects trained LoRA adapters by estimating a safety-aligned subspace and solving a penalized minimum-change problem to attenuate unsafe update directions while pres…

The paper proposes a novel framework combining evolutionary algorithms and Secure Multi-Party Computation (MPC) to enable privacy-preserving distributed optimization that meets strict time deadlines.

The paper introduces a theoretically grounded evaluation framework for watermarking generative models, proposing a novel method (SSB) that allows for systematic design across all security-robustness-f…

The paper proposes GloResNet, a lightweight 3D CNN that effectively predicts brain injury in preterm infants using T2-weighted MRI, achieving an average accuracy of 75.18%.

The paper introduces Multifidelity Proper Orthogonal Decomposition (MFPOD), a method that significantly reduces the computational cost of dimension reduction by intelligently combining data from cheap…

HARP introduces a novel, adaptive, learnable orthogonal processor that significantly improves the robustness and accuracy of extreme low-bit LLM quantization compared to fixed methods.

The paper analyzes a new class of asynchronous adaptive first-order optimization methods and proves their stochastic convergence rate is O(1/sqrt{t}) for non-convex functions.

The paper introduces Sparse Memory-Efficient Training (SMET), a method that stabilizes and optimizes Dynamic Sparse Training (DST) for large language models, enabling stable and memory-efficient spars…

The paper introduces an improved PULSE method to efficiently estimate the thermodynamic properties of chemically disordered compounds by sampling and estimating the system's partition function, demons…

The paper proposes a novel convolutional block and optimization algorithm to implement resource-efficient 1D-CNNs for atrial fibrillation detection on tiny smart sensor systems, achieving high accurac…

This paper introduces a local information-operator framework to analyze spatial identifiability in inverse problems where spatially varying fields are inferred from heterogeneous observations.