4/1/2026
UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG
UltRAG: Scalable recipe for knowledge graph RAG with LLMs to reduce hallucinations by integrating structured knowledge in context windows.
4/1/2026
DF-ACBlurGAN: Structure-Aware Conditional Generation of Internally Repeated Patterns for Biomaterial Microtopography Design
Conditional GAN for generating biomaterial microtopography with internally repeated periodic patterns and global structural consistency.
4/1/2026
When GPUs Fail Quietly: Observability-Aware Early Warning Beyond Numeric Telemetry
Early warning system for GPU failures using observability and structural signals beyond numeric telemetry for HPC and AI workloads.
4/1/2026
Mitigating Temporal Blindness in Kubernetes Autoscaling: An Attention-Double-LSTM Framework
Attention-LSTM framework for Kubernetes autoscaling addressing temporal blindness in serverless workload orchestration using deep reinforcement learning.
4/1/2026
Generalizable Foundation Models for Calorimetry via Mixtures-of-Experts and Parameter Efficient Fine Tuning
Foundation model for particle physics detector simulation using mixture-of-experts and parameter-efficient fine-tuning inspired by LLM techniques.
4/1/2026
WAter: A Workload-Adaptive Knob Tuning System based on Workload Compression
ML-based database parameter tuning system using workload compression to reduce configuration evaluation cost and improve DBMS performance.
4/1/2026
OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training
OptiMer: Method to optimize data mixture ratios for LLM continual pre-training by extracting and merging distribution vectors without fixed hyperparameters.
4/1/2026
Calibrated Fusion for Heterogeneous Graph-Vector Retrieval in Multi-Hop QA
Score calibration method for heterogeneous graph-vector retrieval fusion in multi-hop question answering using percentile-rank normalization.
4/1/2026
Robust Multi-Agent Reinforcement Learning for Small UAS Separation Assurance under GPS Degradation and Spoofing
Multi-agent reinforcement learning approach for unmanned aircraft separation assurance under adversarial GPS degradation and spoofing.
4/1/2026
Minimum Norm Interpolation via The Local Theory of Banach Spaces: The Role of $2$-Uniform Convexity
Theoretical analysis of minimum-norm interpolation under 2-uniform convexity assumptions for understanding generalization in overparameterized neural networks.
4/1/2026
AutoWorld: Scaling Multi-Agent Traffic Simulation with Self-Supervised World Models
Multi-agent traffic simulation framework using self-supervised world models to scale autonomous driving system testing with unlabeled sensor data.
4/1/2026
A Pontryagin Method of Model-based Reinforcement Learning via Hamiltonian Actor-Critic
Model-based reinforcement learning approach using Pontryagin methods and Hamiltonian actor-critic to address compounding model errors in long-horizon value estimation.
4/1/2026
Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research
Mimosa: evolving multi-agent framework for autonomous scientific research that synthesizes and refines LLM-based agent workflows.
4/1/2026
PolarQuant: Optimal Gaussian Weight Quantization via Hadamard Rotation for LLM Compression
PolarQuant: post-training weight quantization method for LLM compression using Hadamard rotation and Gaussian optimization.
4/1/2026
Software Vulnerability Detection Using a Lightweight Graph Neural Network
GNN-based model for software vulnerability detection that offers better scalability than LLM approaches for code analysis tasks.
4/1/2026
Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs
LiteCoST framework for document QA using chain-of-structured-thought and fine-tuned small language models for high accuracy and low latency.
4/1/2026
The Thiomi Dataset: A Large-Scale Multimodal Corpus for Low-Resource African Languages
Thiomi: large-scale multimodal dataset with 600k+ text annotations and 385k+ audio recordings across 10 African languages.
4/1/2026
MemRerank: Preference Memory for Personalized Product Reranking
MemRerank framework distilling user purchase history into preference signals for personalized LLM-based shopping agent product reranking.
4/1/2026
Beyond Corner Patches: Semantics-Aware Backdoor Attack in Federated Learning
SABLE framework for semantically-aware backdoor attacks in federated learning using realistic, in-distribution triggers.
4/1/2026
Rigorous Explanations for Tree Ensembles
Method for generating rigorous, human-interpretable explanations for tree ensemble model predictions.
4/1/2026
AP-DRL: A Synergistic Algorithm-Hardware Framework for Automatic Task Partitioning of Deep Reinforcement Learning on Versal ACAP
Hardware-software framework for automatic task partitioning of deep reinforcement learning on Xilinx Versal ACAP.
4/1/2026
AGFT: Alignment-Guided Fine-Tuning for Zero-Shot Adversarial Robustness of Vision-Language Models
Fine-tuning framework (AGFT) for improving zero-shot adversarial robustness of vision-language models while preserving alignment.
4/1/2026
Multi-AUV Cooperative Target Tracking Based on Supervised Diffusion-Aided Multi-Agent Reinforcement Learning
Multi-agent RL approach for cooperative AUV target tracking using diffusion models to address non-stationarity and coordination challenges.
4/1/2026
From Big Data to Fast Data: Towards High-Quality Datasets for Machine Learning Applications from Closed-Loop Data Collection
Framework for high-quality dataset generation from closed-loop automotive data collection for ML model development.
4/1/2026
Metriplector: From Field Theory to Neural Architecture
Novel neural architecture (Metriplector) based on metriplectic field dynamics enabling gradient-free computation.
4/1/2026
Learning to Generate Formally Verifiable Step-by-Step Logic Reasoning via Structured Formal Intermediaries
Framework (PRoSFI) for generating verifiable step-by-step reasoning in LLMs using structured formal intermediaries and process rewards.
4/1/2026
Baby Scale: Investigating Models Trained on Individual Children's Language Input
Benchmarks language models on child-scale datasets to understand data efficiency and linguistic knowledge emergence.
4/1/2026
Symphony for Medical Coding: A Next-Generation Agentic System for Scalable and Explainable Medical Coding
Agentic system for automated medical coding from clinical text using scalable, explainable approach that adapts to new codes.
4/1/2026
Unbounded Density Ratio Estimation and Its Application to Covariate Shift Adaptation
Statistical learning approach for unbounded density ratio estimation and covariate shift adaptation without assuming bounded ratios.
4/1/2026
mlr3mbo: Bayesian Optimization in R
mlr3mbo: modular R toolbox for Bayesian optimization supporting single/multi-objective, parallelization, and custom algorithm construction.
4/1/2026
Reasoning-Driven Synthetic Data Generation and Evaluation
Reasoning-driven approach for generating synthetic multi-modal training data without manual prompts, addressing scarcity of specialized AI training datasets.
4/1/2026
DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA
DIAL proposes decoupling intent and action in Vision-Language-Action models via latent world modeling to improve decision-making and training stability in end-to-end robotic control.
4/1/2026
A Hybrid Machine Learning Approach for Graduate Admission Prediction and Combined University-Program Recommendation
Hybrid machine learning framework for graduate admission prediction and university-program recommendation using 13,000 GradCafe records.
4/1/2026
Uncertainty Gating for Cost-Aware Explainable Artificial Intelligence
Method using epistemic uncertainty to identify unreliable explanations in post-hoc XAI methods, reducing explanation generation costs.
4/1/2026
Think Anywhere in Code Generation
Proposes adaptive reasoning allocation during code generation for LLMs, addressing limitations of upfront thinking approaches in handling code complexity.
4/1/2026
Early Exiting Predictive Coding Neural Networks for Edge AI
Early exiting predictive coding neural networks optimized for edge AI devices with resource constraints and privacy requirements.
4/1/2026
GenOL: Generating Diverse Examples for Name-only Online Learning
GenOL framework for online learning with only concept names (name-only setup) enabling real-time adaptation to data distribution shifts in continual learning scenarios.
4/1/2026
Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting
Introduces WEATHER-5K dataset and benchmarks physics-informed time-series forecasting models for global weather prediction.
4/1/2026
A General Control-Theoretic Approach for Reinforcement Learning: Theory and Algorithms
Control-theoretic approach to reinforcement learning with convergence guarantees, new gradient theorem, and gradient ascent algorithm.
4/1/2026
An Information-Theoretic Approach to Understanding Transformers' In-Context Learning of Variable-Order Markov Chains
Information-theoretic analysis of transformer in-context learning on variable-order Markov chains with finite-sample accuracy bounds.
4/1/2026
Value Gradient Sampler: Learning Invariant Value Functions for Equivariant Diffusion Sampling
Diffusion sampler using value functions with invariant symmetries for sampling from unnormalized target densities.
4/1/2026
Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessment
Critical evaluation of model inversion attack assessment frameworks, identifying flaws in standard evaluation methodology.
4/1/2026
Neural Graduated Assignment for Maximum Common Edge Subgraphs
Neural Graduated Assignment method for solving Maximum Common Edge Subgraph problem with improved scalability.
4/1/2026
PreMoE: Proactive Inference for Efficient Mixture-of-Experts
Training-free framework for compiling sparse Mixture-of-Experts variants with predicted expert utility metric for deployment optimization.
4/1/2026
Epistemic Errors of Imperfect Multitask Learners When Distributions Shift
Framework for characterizing epistemic errors in uncertainty-aware multitask learners under distribution shift.
4/1/2026
Denoising the Future: Top-p Distributions for Moving Through Time
Probabilistic inference speedup for Hidden Markov Models by filtering low-probability states in temporal sequences.
4/1/2026
Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting
Research on dynamic reward weighting for multi-objective RL alignment in LLMs, addressing non-convex Pareto fronts in preference learning.
4/1/2026
On the Convergence of Muon and Beyond
Theoretical convergence analysis of Muon optimizer for matrix-structured parameters in neural network training.
4/1/2026
Towards a Certificate of Trust: Task-Aware OOD Detection for Scientific AI
Out-of-distribution detection for regression tasks in scientific AI using score-based diffusion models on joint likelihood estimation.
4/1/2026
Learning Inter-Atomic Potentials without Explicit Equivariance
Transformer-based inter-atomic potential model for molecular simulations without explicit equivariance constraints.