wovepaper — the arXiv observatory

papers

Publications (44)

cs.SE2026

OwlPath: Lossless Knowledge Compression for LLM Bug Repair

Bo Zhang, Ren Pan, Huan Chen +1

The paper introduces OwlPath, an OWL2 ontology layer that compresses source code knowledge losslessly to enable fast, token‑efficient structural queries for LLM‑based bug repair, i…

Publications (44)

OwlPath: Lossless Knowledge Compression for LLM Bug Repair

P-EAGLE: Parallel-Drafting EAGLE with Scalable Training

GraphStorm: all-in-one graph machine learning framework for industry applications

Efficient and effective training of language and graph neural network models

Toward an Organizational Science of Multi-Agent LLM Systems: Decoupling Who, How, and Which Algorithm

HSIDMamba: Exploring Bidirectional State-Space Models for Hyperspectral Denoising

Refined Edge Usage of Graph Neural Networks for Edge Prediction

Feedback Control for Multi-Objective Graph Self-Supervision

NetInfoF Framework: Measuring and Exploiting Network Usable Information

Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models

A Novel Graph based Trajectory Predictor with Pseudo Oracle

XShare: Collaborative in-Batch Expert Sharing for Faster MoE Inference

Space Rotation with Basis Transformation for Training-free Test-Time Adaptation

DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs

Deal: Distributed End-to-End GNN Inference for All Nodes

Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices

IGB: Addressing The Gaps In Labeling, Features, Heterogeneity, and Size of Public Graph Datasets for Deep Learning Research

DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype

DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts

Dynamic Mixture-of-Experts for Incremental Graph Learning

FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training

DistTGL: Distributed Memory-Based Temporal Graph Neural Network Training

Parameter-Efficient Tuning Large Language Models for Graph Representation Learning

Graph Neural Network Training with Data Tiering

DGL-KE: Training Knowledge Graph Embeddings at Scale

Spectro-Riemannian Graph Neural Networks

Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks

NetCause: Counterfactual Learning for Root Cause Analysis in Large-Scale Networks

Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need

TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs

KernelSight-LM: A Kernel-Level LLM Inference Simulator

On the Initialization of Graph Neural Networks

PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction

Network In Graph Neural Network

Repurpose Open Data to Discover Therapeutics for COVID-19 using Deep Learning

Hector: An Efficient Programming and Compilation Framework for Implementing Relational Graph Neural Networks in GPU Architectures

GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models

ColdGuess: A General and Effective Relational Graph Convolutional Network to Tackle Cold Start Cases

Distributed Hybrid CPU and GPU training for Graph Neural Networks on Billion-Scale Graphs

TouchUp-G: Improving Feature Representation through Graph-Centric Finetuning

Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications

Relatron: Automating Relational Machine Learning over Relational Databases

COVID-19 Knowledge Graph: Accelerating Information Retrieval and Discovery for Scientific Literature

Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents