Noseong Park

Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors

PDE-PFN: Prior-Data Fitted Neural PDE Solver

Graph Signal Processing Meets Mamba2: Adaptive Filter Bank via Delta Modulation

Point-wise Anomaly Detection via Fold-bifurcation ODE

ASMG: Data Structure-Aware Routing via Incremental Subspace Learning for MoE

SR-PFN: Yet Another Sequential Recommendation Paradigm

Efficient Cell Painting Image Representation Learning via Cross-Well Aligned Masked Siamese Network

SALT: Structure-Aligned Learning for Time-Series Forecasting

StreamingKV: Adaptive Low-Rank KV Caching with Test-time Updates

TUNE: Frequency-Guided Token Gating for Robust Continual Learning in LLMs

FCLoRA: Low-Rank Adaptation with Fine-Grained Component Injection

Neural Functions for Learning Periodic Signal

Efficiently Parameterized Neural Metriplectic Systems

TV-Rec: Time-Variant Convolutional Filter for Sequential Recommendation

PDEfuncta: Spectrally-Aware Neural Representation for PDE Solution Modeling

PIORF: Physics-Informed Ollivier-Ricci Flow for Long–Range Interactions in Mesh Graph Neural Networks

MaD-Scientist: AI-based Scientist solving Convection-Diffusion-Reaction Equations Using Massive PINN-Based Prior Data

Fractal-Inspired Message Passing Neural Networks with Fractal Nodes

HiLoRA: High-frequency-augmented Low-Rank Adaptation

Enhancing Time-Series Forecasting with Iterative Decomposition and Separable Training

Universal Time-series Generation using Score-based Generative Models