6905 papers
FedPrism is an adaptive personalized federated learning framework that mitigates performance degradation under non-IID data by employing a Prism Decomposition method to dynamically group clients and a Dual-Stream design to balance general and local model predictions, thereby achieving superior accuracy compared to static aggregation and hard-clustering baselines.
FlowTouch is a novel view-invariant visuo-tactile prediction model that leverages an object's local 3D mesh and Flow Matching to bridge the sim-to-real gap, enabling the prediction of tactile patterns from visual inputs for downstream tasks like grasp stability prediction.
This paper introduces ReinMax-Rao and ReinMax-CV, novel gradient estimators that apply Rao-Blackwellisation and control variate techniques to the ReinMax method, effectively reducing its high variance while maintaining low bias for training variational autoencoders with discrete latent variables.
This paper presents a fully adaptive airborne magnetic navigation framework that combines an Extended Kalman Filter with a residual neural network and online natural gradient descent to achieve real-time, "cold-start" magnetic interference compensation without requiring prior calibration flights.
This paper proposes a cost-effective approach to detecting bias in financial language models by leveraging cross-model patterns to identify bias-revealing inputs early, demonstrating that up to 73% of a model's biased behaviors can be uncovered using only 20% of the input pairs when guided by another model's outputs.
The paper proposes SCL-GNN, a novel framework that enhances the generalization of Graph Neural Networks on both IID and OOD graphs by utilizing the Hilbert-Schmidt Independence Criterion to identify and mitigate spurious correlations through an efficient bi-level optimization strategy.
The paper proposes TA-RNN-Medical-Hybrid, a time-aware and interpretable deep learning framework that integrates continuous-time encoding, SNOMED-based disease representations, and a hierarchical dual-level attention mechanism to accurately predict ICU mortality risk while providing clinically meaningful explanations.
The paper introduces PolyFormer, a physics-informed machine learning framework that transforms complex physical constraints into efficient polytopic reformulations, achieving massive computational speedups and memory reductions while maintaining high solution quality for scalable optimization problems.
This paper establishes a tight Bayesian regret bound of for Gaussian Process Posterior Sampling Reinforcement Learning in continuous control with unbounded state spaces by proving that visited states remain within a near-constant radius and applying the chaining method to control regret.
This paper reveals that Sharpness-Aware Minimization (SAM) exhibits depth-dependent implicit biases in linear diagonal networks, where -SAM's convergence becomes initialization-sensitive and unstable at depth , while -SAM displays "sequential feature amplification" that prioritizes minor features early in training, demonstrating that infinite-time implicit bias analyses fail to capture SAM's critical finite-time dynamics.
This paper proposes Graph-Instructed Neural Networks (GINNs) as a robust and scalable alternative to classical reduced order methods for efficiently simulating parametric partial differential equations with varying boundary conditions by learning the direct mapping between domain descriptions and PDE solutions.
This paper introduces a concept-guided fine-tuning framework that enhances Vision Transformer robustness against distribution shifts by automatically generating and aligning model attention with fine-grained semantic concepts rather than spurious background correlations.
This paper establishes criteria for determining the sign identifiability of drift coefficients in continuous-time linear stationary stochastic differential equations with known causal structures but unknown diffusion matrices, demonstrating that edge signs can be uniquely identified under faithfulness assumptions even when the full parameters cannot.
This paper introduces a label-free framework for evaluating Multiple Instance Learning heatmaps in histopathology, demonstrating through a large-scale benchmark that perturbation, LRP, and integrated gradients outperform attention-based methods, thereby enabling more reliable model validation and biological discovery.
This paper demonstrates that while wavelet features excel in binary ECG classification, a transformer-based model utilizing Koopman operator features derived from an optimized Extended Dynamic Mode Decomposition (EDMD) with a radial basis function dictionary achieves superior performance in multi-class ECG classification, outperforming both wavelet-only and hybrid approaches.
This paper proposes replacing the dense output projection in multi-head attention with a parameter-free Walsh-Hadamard Transform and lightweight affine rescaling, achieving significant reductions in parameters, memory, and inference latency while maintaining or improving model performance across various benchmarks.
This paper introduces a gradient-based optimization method for generating time series counterfactual explanations that ensures plausibility by integrating soft-DTW alignment with k-nearest neighbors, resulting in valid and temporally realistic outputs that outperform existing approaches in distributional alignment.
This paper unifies online A/B testing and off-policy evaluation by proving that standard variance reduction methods in both domains are mathematically equivalent, specifically showing that Difference-in-Means estimators correspond to optimal Inverse Propensity Scoring and that regression adjustment techniques align with Doubly Robust estimation.
This paper models benchmarking as a strategic game to demonstrate that current evaluation protocols fail to establish a stable equilibrium, whereas a proposed "tune-before-test" protocol successfully incentivizes developers to improve latent model quality by inducing a unique Nash equilibrium.
This paper introduces a novel optimization algorithm based on Fractional Weyl Integrals that replaces instantaneous gradients with a memory-weighted historical sequence to effectively mitigate overfitting and significantly improve performance on imbalanced datasets, such as those in financial fraud detection and medical diagnostics.