activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging

Chenrui Wu, Zexi Li, Jiajun Bu +2

Reinforcement Learning with Verifiable Reward (RLVR) has emerged as a powerful post-training paradigm that surpasses Supervised Fine-Tuning (SFT) in eliciting reasoning intelligenc…

cs.LG2025

Graph Neural Architecture Search with GPT-4

Haishuai Wang, Yang Gao, Xin Zheng +3

Graph Neural Architecture Search (GNAS) has shown promising results in finding the best graph neural network architecture on a given graph dataset. However, existing GNAS methods s…

cs.LG2025

Multi-Omics Analysis for Cancer Subtype Inference via Unrolling Graph Smoothness Priors

Jielong Lu, Zhihao Wu, Jiajun Yu +2

Integrating multi-omics datasets through data-driven analysis offers a comprehensive understanding of the complex biological processes underlying various diseases, particularly can…

cs.LG2025

Guarding Graph Neural Networks for Unsupervised Graph Anomaly Detection

Yuanchen Bei, Sheng Zhou, Jinke Shi +3

Unsupervised graph anomaly detection aims at identifying rare patterns that deviate from the majority in a graph without the aid of labels, which is important for a variety of real…

cs.LG2025

ImputeINR: Time Series Imputation via Implicit Neural Representations for Disease Diagnosis with Missing Data

Mengxuan Li, Ke Liu, Jialong Guo +3

Healthcare data frequently contain a substantial proportion of missing values, necessitating effective time series imputation to support downstream disease diagnosis tasks. However…

cs.LG2025

TSINR: Capturing Temporal Continuity via Implicit Neural Representations for Time Series Anomaly Detection

Mengxuan Li, Ke Liu, Hongyang Chen +3

Time series anomaly detection aims to identify unusual patterns in data or deviations from systems' expected behavior. The reconstruction-based methods are the mainstream in this t…