arXiv paper proposing Temporal Patch Shuffle data augmentation for time series forecasting preserving temporal coherence and improving generalization.
arXiv paper integrating graph-based embeddings into event sequence models for user-item interactions in fraud and recommendation systems.
arXiv paper on GeoPAS geometric probing approach for automated algorithm selection in continuous black-box optimization.
arXiv paper on EquiformerV3, advancing SE(3)-equivariant graph attention Transformers for efficiency, expressivity, and 3D atomistic modeling.
arXiv paper proposing score-driven rating system extending classical Elo rating to accommodate diverse game outcomes and rankings.
arXiv paper on CORA, conformal risk-controlled GUI agents using vision language models with formal safety guarantees for mobile automation.
arXiv paper proposing truncated rectified flow policy for maximum entropy RL enabling one-step multimodal action distribution sampling.
arXiv paper augmenting distillation process dataset with simulations for deep learning-based anomaly detection in chemical batch processes.
arXiv paper developing generalization and scaling theory for Mixture-of-Experts Transformers with covering-number bounds and routing overhead analysis.
arXiv paper on GNN-based deep reinforcement learning scheduler for cloud workflow DAGs optimizing completion time and energy consumption.
arXiv paper analyzing statistical properties of ancient I-Ching King Wen sequence, finding no improvement to neural network training.
arXiv paper proposing DiffHLS framework using GNNs and LLM code embeddings for high-level synthesis quality prediction via differential learning.
arXiv paper investigating LLM pretraining geometry and common minima to improve downstream generalization without changing loss function.
arXiv paper applying causal inference to study relationship between parking infrastructure and EV adoption in Scotland.
arXiv paper on distributed online convex optimization with compressed communication, establishing optimal regret bounds for large-scale applications.
Physics-informed meta-learning framework (KAPI) combining meta-learned predictor with least-squares corrector for solving parametric linear PDEs.
Novel stability-enhanced Gaussian process VAE for training low-dimensional LTI systems from high-dimensional video data using probabilistic and physical models.
Hierarchical deep learning framework for predicting vehicle turning movements at signalized intersections.
Online learning method for nonstationary multivariate time series with concept drift applied to sintering quality prediction.
Weakly-supervised clustering approach for handling label noise in partial multi-label learning scenarios.
Neural network method for solving high-dimensional Gross-Pitaevskii equations with dimension-independent computational cost.
Controlled study of dataset scaling laws in attention-only decoder architecture across power-of-two subset sizes.
Machine unlearning approach using relearning convergence delay metric to remove contaminated data from pretrained models.
Online activation subspace learning (OASIS) to reduce memory requirements during LLM training through low-rank projections.
Scalable method for generating node embeddings on massive distributed graphs with millions to billions of nodes.
AdaCubic optimizer using adaptive cubic regularization with Hutchinson's method for approximating Hessian in deep learning.
One-step diffusion model for efficient chest X-ray report generation reducing inference latency compared to autoregressive models.
Method for safely updating deep reinforcement learning policies while preserving safety guarantees on previously encountered tasks.
Hardware optimization using electro-optic nonlinearities to replace softmax bottleneck in transformer attention mechanisms.
Application of world models paradigm to computational epidemiology for reasoning about latent disease burden and intervention effects.
High-fidelity cyber operations simulator (NetForge_RL) using temporal graph networks for multi-agent reinforcement learning in cybersecurity.
OmniBehavior benchmark for evaluating LLMs as user simulators on long-horizon, cross-scenario behavior traces from real-world data.
Investigation of self-sovereign AI agents that can economically sustain themselves without human involvement using LLMs and agent frameworks.
Analysis of how bias mitigation reshapes embedding spaces in BERT and Llama2 through representational analysis of gender-occupation associations.
Systematic evaluation of chain-of-thought vs zero-shot prompting across temperature settings using Grok-4.1 for extended reasoning LLMs.
Research on attention-based sampling for diffusion language models enabling parallel decoding instead of sequential auto-regressive approach.
Tree-structured sparse feed-forward layers as drop-in MLP replacements in transformers enabling conditional computation via routing.
Comparative study of LLMs vs fine-tuned Arabic BERT models on sentiment classification of Gaza War news headlines.
GAN-enhanced deep reinforcement learning for semantic-aware resource allocation in 6G wireless networks.
Theoretical framework for reward fine-tuning of diffusion models using stochastic optimal control and adjoint matching.
Protocol governing autonomous agent mutations with execution-bound safety checks and evidence chains for API-centric architectures.
Open-source browser extension for AI-assisted title and abstract screening in literature review with no-code, serverless architecture.
Attack method on LLM orchestration systems where single requests decompose into benign subtasks that jointly violate security policies.
Multimodal approach for detecting hate and threats in digital forensic evidence combining images, documents, and text.
Longitudinal case study of autonomous personalization systems in CRM with human-in-the-loop oversight requirements.
Theoretical framework analyzing generalization in overparameterized interpolating estimators via spectral-transport stability.
Method to reduce hallucinations in 3D embodied AI agents using visual contrastive decoding on multimodal LLMs.
Differentiable probabilistic programming for gamma-ray astrophysical analysis using GPU acceleration and vectorization.
Multimodal inference task with text, audio, video for producing calibrated probability estimates of hypotheses with fine-grained uncertainty.
LLM application translating network quality metrics to user experience quality using large language models for multimedia systems.