AI.info

Latest Research — Page 108

Browse Latest Research on AI.info.

• OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery
• Bridging the gap to real-world language-grounded visual concept learning
• Edit Knowledge, Not Just Facts via Multi-Step Reasoning over Background Stories
• LLMs vs. Traditional Sentiment Tools in Psychology: An Evaluation on Belgian-Dutch Narratives
• Multi-Frequency Federated Learning for Human Activity Recognition Using Head-Worn Sensors
• Imitation Learning for Connection-Tableau Construction
• Test-Time Augmentation for LLMs: When Input Diversity Beats Output Diversity at Matched Compute
• PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression
• PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data
• ShapeCond: Fast Shapelet-Guided Dataset Condensation for Time Series Classification
• GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design
• Uncertainty Quantification for Reduced-Order Surrogate Models Applied to Cloud Microphysics
• Green-NAS: A Global-Scale Multi-Objective Neural Architecture Search for Robust and Efficient Edge-Native Weather Forecasting
• UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents
• On-Policy Self-Distillation for Multi-Turn Image Editing
• Towards Agentic Robots: Model, Data, Environment, and Harness
• Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models
• X-Planner: Event-Structured Task Planning for Embodied Intelligence
• Visual Framing for News Stance Detection via Image Generation
• A Broader Look into MLLM's Retrieval Heads
• Adaptive Momentum and Nonlinear Damping for Neural Network Training
• More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models
• Fluent Alignment with Disfluent Judges: Post-training for Lower-resource Languages
• Population Fidelity: Evaluating Population Representativeness in LLMs
• SD-LoRA: Training-Time Structural Distillation into LoRA for Few-Shot Vision-Language Adaptation
• CASL: Curvature-Augmented Self-supervised Learning for 3D Anomaly Detection
• SWE-Game: Can Coding Agents Build the Games We Want?
• CHUCKLE -- When Humans Teach AI To Learn Emotions The Easy Way
• Geometry Meets Light: Leveraging Geometric Priors for Universal Photometric Stereo under Limited Multi-Illumination Cues
• LakeMLB: Data Lake Machine Learning Benchmark
• Improving the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models
• UniData: Universal Multimodal Instruction Generation Pipeline
• Learning to Trust: Bayesian Adaptation to Varying Suggester Reliability in Sequential Decision Making
• Judge's Verdict: A Comprehensive Analysis of LLM Judge Capability Through Human Agreement
• Reasoning about Intent for Ambiguous Requests
• Open Ad-hoc Categorization with Contextualized Feature Learning
• Denotational Semantics for ODRL: Knowledge-Based Constraint Conflict Detection
• Entropy Meets Importance: A Unified Head Importance-Entropy Score for Stable and Efficient Transformer Pruning
• Knowledge-Informed Kernel State Reconstruction from Heterogeneous Partial Observations
• Graph Learning on Ensembles of Cyclic Peptides: An Investigation of Molecular Ensemble Modeling