AI Applications

A novel regularized triangle-shaped neural network framework, T-Net, achieves highly accurate and scalable logic circuit generation, significantly outperforming existing methods.

Med-MICN: a novel end-to-end framework for medical image classification, achieving superior accuracy and multi-dimensional interpretability by aligning neural symbolic reasoning, concept semantics, an…

Greedy algorithms outperform conformal prediction in creating prediction sets that maximize human expert accuracy in classification tasks.

This study introduces novel, scalable AI-based planning strategies for controlling misinformation spread in dynamic opinion networks, significantly improving infection rate control.

TEdit: a novel diffusion model edits existing time series to meet specified attribute targets, preserving other properties, solving limitations of prior synthesis methods.

CMCD framework tackles data sparsity in cognitive diagnosis by using monotonic data augmentation to improve accuracy and fairness of diagnostic results.

Boost survival prediction accuracy with CSD-iPOT: a novel post-processing method achieving superior marginal & conditional calibration without sacrificing discrimination.

ConSurv: a novel contrastive learning approach for survival analysis enhances discrimination without sacrificing calibration by employing weighted sampling and aligning well with the assumption that p…

TopoLogic uses lane geometry and query similarity to improve lane topology reasoning in autonomous driving, significantly outperforming existing methods.

Text2CAD: AI generates CAD models from text prompts!

Team-Fictitious Play (Team-FP) enables self-interested agents to learn near-optimal team coordination in multi-team games, reaching a Team-Nash equilibrium with quantifiable error bounds.

Task-oriented time series imputation is revolutionized! This research introduces a novel approach that efficiently assesses imputation strategies based on downstream task performance without costly mo…

LoTNext framework tackles human mobility prediction’s long-tail problem by using graph and loss adjustments to improve the accuracy of predicting less-visited locations.

SWE-agent achieves state-of-the-art performance on software engineering benchmarks by creating a custom agent-computer interface that enhances LM agents’ ability to use computers.

KF-GVD: a novel knowledge fusion-based method boosts vulnerability detection accuracy by integrating task-specific knowledge into graph neural networks, achieving significant performance gains and dis…

Human understanding of formal specifications for robot validation is surprisingly poor; active learning, while improving engagement, doesn’t significantly boost accuracy.

Weighted reservoir sampling stabilizes online learning algorithms by creating a robust ensemble of intermediate solutions, significantly improving accuracy and mitigating sensitivity to outliers.

SpGesture: A source-free domain-adaptive SEMG gesture recognition system using a novel Spiking Jaccard Attentive Neural Network achieves real-time performance with high accuracy.

SOFTS: An efficient MLP-based model for multivariate time series forecasting using a novel STAR module for efficient channel interaction.

SocraticLM achieves a Socratic teaching paradigm, surpassing GPT-4 by 12%, through a novel multi-agent training pipeline and a comprehensive evaluation system.