AI.info

Latest Research — Page 78

Browse Latest Research on AI.info.

• XPolicyLab: A Unified Standard and Open Ecosystem for Robot Policy Evaluation and Deployment
• Agent-Omit: Adaptive Context Omission for Efficient LLM Agents
• Proximity3D: Shape from Capacitive Proximity on Sensing Manifold
• Binary BPE: A Family of Cross-Platform Tokenizers for Binary Analysis
• Cross-Sample Augmented Test-Time Adaptation for Personalized Intraoperative Hypotension Prediction
• A Mixed Methods Systematic Analysis of Issues and Factors Influencing Organizational Cloud Computing Adoption and Usage in the Public Sector: Initial Findings
• A Graph Neural Network Approach for Localized and High-Resolution Temperature Forecasting
• AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition
• Magnitude-Modulated Equivariant Adapter for Parameter-Efficient Fine-Tuning of Equivariant Graph Neural Networks
• Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
• An Odd Estimator for Shapley Values
• Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos
• SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes
• Actions Speak Louder than Words: Measuring Cross-Lingual Policy Retention in Tool-Using Agents
• Distribution-Based Feature Attribution for Explaining the Predictions of Any Classifier
• Financial Management System for SMEs: Real-World Deployment of Accounts Receivable and Cash Flow Prediction
• Trajectory Guard -- A Lightweight, Sequence-Aware Model for Real-Time Anomaly Detection in Agentic AI
• Towards 3D Objectness Learning in an Open World
• Do Large Language Models Hallucinate Electric Fata Morganas?
• UniABG: Unified Adversarial View Bridging and Graph Correspondence for Unsupervised Cross-View Geo-Localization
• Shifting the Breaking Point of Flow Matching for Multi-Instance Editing
• AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models
• OptiMAS: Automatically Optimize Multi-Agent System
• Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
• UniGTE: Unified Graph-Text Encoding for Zero-Shot Generalization across Graph Tasks and Domains
• Training Proactive and Personalized LLM Agents
• CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation
• SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines
• HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs
• RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
• AI Unplugged: Embodied Interactions for AI Literacy in Higher Education
• Improving Forecasts of Suicide Attempts for Patients with Little Data
• Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation
• Extracting Events Like Code: A Multi-Agent Programming Framework for Zero-Shot Event Extraction
• LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers
• THEval. Evaluation Framework for Talking Head Video Generation
• FlowTIE: Flow-based Transport of Intensity Equation for Phase Gradient Estimation from 4D-STEM Data
• ProPL: Universal Semi-Supervised Ultrasound Image Segmentation via Prompt-Guided Pseudo-Labeling
• Agentic Persona Control and Task State Tracking for Realistic User Simulation in Interactive Scenarios
• Generating Physically Sound Designs from Text and a Set of Physical Constraints