AI Applications

BPQP: A new differentiable convex optimization framework accelerates end-to-end learning by an order of magnitude, achieving significant efficiency gains over existing methods.

AI struggles with collaborating effectively with humans due to unpredictable human behavior. This paper introduces Collaborative Bayesian Policy Reuse (CBPR), a novel framework that leverages meta-ta…

Researchers developed AdvRM, a new adversarial patch attack against monocular depth estimation models, which effectively camouflages patches as road markings to mislead depth predictions for any obsta…

This paper introduces Belief-State Query (BSQ) constraints for user-aligned planning in partially observable settings, providing algorithms with guaranteed user alignment and computational feasibility…

BehaviorGPT, a novel autoregressive Transformer, simulates realistic traffic agent behavior by modeling each time step as ‘current’, achieving top results in the 2024 Waymo Open Sim Agents Challenge.

BAKU: A simple transformer enables efficient multi-task robot policy learning, achieving 91% success on real-world tasks with limited data.

BACKTIME unveils effective backdoor attacks on multivariate time series forecasting, highlighting vulnerabilities and offering novel defense strategies.

Autoregressive Image Diffusion (AID) generates coherent MRI image sequences from undersampled data, outperforming standard diffusion models by exploiting inter-image dependencies.

Spiking Autonomous Driving (SAD) is the first unified SNN for autonomous driving, achieving competitive performance in perception, prediction, and planning while significantly reducing energy consumpt…

AI autonomously designs highly effective hybrid digital twins by combining neural networks and mechanistic models, significantly advancing digital twin technology.

AutoDP automates multi-task learning for joint disease prediction on EHRs, significantly improving performance via automated task grouping and architecture search.

Attention boosted Individualized Regression (AIR) provides a novel individualized modeling framework for matrix data, leveraging sample-specific internal relations without needing extra sample similar…

Pattern-BERP, a novel method, boosts biological entity relationship prediction accuracy by 4-23% using association pattern-aware fusion, enhancing interpretability for real-world applications.

Popular large language model (LLM)-based time series forecasting methods perform no better than simpler alternatives, often worse, and require vastly more compute.

AR-Pro uses generative models to create counterfactual explanations for anomaly detection, formally specifying what a non-anomalous version should look like and improving interpretability.

AOPU: A novel neural network achieves superior stability in regression network training by approximating the natural gradient, minimizing variance estimation, and enhancing robustness.

Revolutionizing antibody design, ABDPO uses direct energy-based preference optimization and a pre-trained diffusion model to generate high-quality antibodies with low energy and strong binding affinit…

Autoencoder-like Nonnegative Matrix Co-Factorization (AE-NMCF) enhances student cognitive modeling by accurately estimating knowledge proficiency and predicting exercise performance, leveraging monoto…

AlterMOMA: A novel pruning framework significantly improves camera-LiDAR fusion models by identifying and removing redundant parameters through an alternative modality masking technique, achieving sta…

Fans can massively boost an artist’s song exposure on music streaming platforms by strategically placing it in their playlists, achieving up to 40x more recommendations.