AI.info
Latest Research — Page 114
Browse Latest Research on AI.info.
- Generative Bayesian Optimization: Generative Models as Acquisition Functions
- Cross-modal Proxy Evolving for OOD Detection with Vision-Language Models
- Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward
- Robust Alignment of the Human Embryo in 3D Ultrasound using PCA and an Ensemble of Heuristic, Atlas-based and Learning-based Classifiers Evaluated on the Rotterdam Periconceptional Cohort
- Demystifying Transition Matching: When and Why It Can Beat Flow Matching
- TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding
- Scale-Plan: Scalable Language-Enabled Task Planning for Heterogeneous Multi-Robot Teams
- Detoxifying Toxic Communication: A Design Science Approach to Responsible AI
- Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error
- Sound Clouds: Exploring ambient intelligence in public spaces to elicit deep human experience of awe, wonder, and beauty
- DataCube: A Video Retrieval Platform via Natural Language Semantic Profiling
- When AI Does the Work, What Is Learning For? Post-Instrumental Learning and the Risk of Capacity Dissolution
- Boosting Medical Visual Understanding From Multi-Granular Language Learning
- Flexible Concept Bottleneck Model
- Quantum-Inspired Modeling of Driving Behavior
- VFAD: Variational Semantic Prompting Meets Frequency-Adaptive Representation Learning for Zero-Shot Anomaly Detection
- Adaptive Evidential Learning for Temporal-Semantic Robustness in Moment Retrieval
- SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models
- LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodules
- Do It for HER: First-Order Temporal Logic Reward Specification in Reinforcement Learning (Extended Version)
- ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents
- A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
- Generalization Beyond Benchmarks: Evaluating Learnable Protein-Ligand Scoring Functions on Unseen Targets
- On the Koopman-Based Generalization Bounds for Multi-Task Deep Learning
- Towards Personalized Quantum Federated Learning for Anomaly Detection
- DARTS: Decoder-Aware Representation Tuning via Surgery for Model Merging
- Structural Plasticity as Active Inference: A Biologically-Inspired Architecture for Homeostatic Control
- Reconstruction and Secrecy under Approximate Distance Queries
- World-in-World: World Models in a Closed-Loop World
- DisasterInsight: A Multimodal Benchmark for Function-Aware and Grounded Disaster Assessment
- Learning from the Undesirable: Robust Adaptation of Language Models without Forgetting
- Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing
- From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity
- Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral Inspection
- FACE: Faithful Automatic Concept Extraction
- StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing
- From Euclidean to Graph-Structured Data: A Survey of Collaborative Learning
- Cross Modal Fine-Grained Alignment via Granularity-Aware and Region-Uncertain Modeling
- ImprovEvolve: Ask AlphaEvolve to Improve the Input Solution and Then Improvise
- Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models