AI Research Paper Feed

TLDR: SpectraKAN enhances spectral neural operators by conditioning them on input data, significantly improving performance on PDE benchmarks.

TLDR: AIMMD is a new algorithm that uses machine learning to improve the efficiency of transition path sampling for studying molecular processes.

TLDR: The paper presents a method to achieve differentially private prediction with reduced dependence on the number of queries, improving efficiency in streaming settings.

TLDR: Open-weight large language models (LLMs) show promise for social media moderation, with performance comparable to proprietary models in detecting harmful content on platforms like Bluesky.

TLDR: The paper introduces a flow matching-based framework for disentangled representation learning that improves semantic alignment and disentanglement scores by using a non-overlap regularizer to reduce factor interference.

TLDR: The paper provides finite-particle convergence rates for the regularized Stein variational gradient descent (R-SVGD) algorithm, offering non-asymptotic bounds and guidance on parameter tuning.

TLDR: This paper introduces relaxed unitary convolutions for graph neural networks to improve performance in dynamics modeling by balancing smoothness preservation with natural physical system requirements.

TLDR: The paper introduces new Radon--Wasserstein gradient flows for efficient high-dimensional sampling using interacting particles with linear scaling costs.

TLDR: The paper proposes a new sequential experimental design approach that improves decision-making by focusing on directional uncertainty, leading to better optimization outcomes than traditional methods.

TLDR: The paper introduces exPreCast, a deterministic model for accurate and efficient nowcasting of both normal and extreme rainfall using a balanced dataset from the Korea Meteorological Administration.

TLDR: ADANA, an optimizer with time-varying schedules for hyperparameters, improves large-scale language model training efficiency by up to 40% compared to AdamW.

TLDR: The paper introduces Concept DAS (CDAS), a novel intervention-based model steering method that uses distribution matching to achieve more faithful and stable control compared to traditional preference-optimization methods.

TLDR: This paper introduces Sequential Flow Matching, a Bayesian filtering approach that accelerates real-time sequential prediction by efficiently updating predictive distributions, reducing inference latency compared to traditional methods.

TLDR: PatchFlow improves defect detection in die casting using local patch features and a flow-based model, reducing error rates significantly on multiple datasets.

TLDR: OpenMAG is a comprehensive benchmark designed to evaluate Multimodal-Attributed Graph (MAG) models across various domains, encoders, and tasks, addressing existing limitations in fair evaluation standards.

TLDR: This paper establishes optimal convergence rates for the last iterate of stochastic proximal algorithms without assuming bounded variance, applicable to problems in multi-task and federated learning.

TLDR: The Hinge Regression Tree (HRT) is a new method for creating oblique decision trees using a Newton method that improves split quality and convergence speed, outperforming traditional tree models.

TLDR: The paper introduces PAIR, a framework for concept erasure in text-to-image models that maintains semantic consistency by aligning unsafe concepts with safe alternatives.

TLDR: Bilinear MLPs with multiplicative interactions improve structural disentanglement and model editability by leveraging architectural inductive bias for better representation and unlearning capabilities.

TLDR: SHaSaM is a novel approach that improves fairness in facial attribute recognition by using submodular hard sample mining to address data imbalance and reduce bias from sensitive attributes.