AI.info

Latest Research — Page 38

Browse Latest Research on AI.info.

• Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
• Path Integral Value Matching for Linear Quadratic Stochastic Optimal Control
• MedGRPO: Multi-Task Reinforcement Learning for Heterogeneous Medical Video Understanding
• Improving the Straight-Through Estimator with Zeroth-Order Information
• CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder
• Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation
• About Time: Model-free Reinforcement Learning with Timed Reward Machines
• Towards Test-time Efficient Visual Place Recognition via Asymmetric Query Processing
• Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime
• Learning Agile Quadrotor Flight in the Real World
• Spiking Heterogeneous Graph Attention Networks
• Stronger Normalization-Free Transformers
• Task Aware Modulation Using Representation Learning for Upsaling of Terrestrial Carbon Fluxes
• Securing Dual-Use Pathogen Data of Concern
• FASA: Frequency-aware Sparse Attention
• ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Models
• A Linguistics-Aware LLM Watermarking via Syntactic Predictability
• RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes
• EMGauss: Continuous Slice-to-3D Reconstruction via Dynamic Gaussian Modeling in Volume Electron Microscopy
• MetaphorStar: Image Metaphor Understanding and Reasoning with End-to-End Visual Reinforcement Learning
• Automatic Paper Reviewing with Heterogeneous Graph Reasoning over LLM-Simulated Reviewer-Author Debates
• Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"
• Concept Heterogeneity-aware Representation Steering
• On the Problem of Consistent Anomalies in Zero-Shot Industrial Anomaly Detection
• IPR-1: Interactive Physical Reasoner
• Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning
• Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs
• Single-Round Scalable Analytic Federated Learning
• CompassNav: Steering From Path Imitation To Decision Understanding In Navigation
• The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
• UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City
• DynaStride: Dynamic Stride Windowing with MMCoT for Instructional Multi-Scene Captioning
• AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent
• Learning from Generalization Patterns: An Evaluation-Driven Approach to Enhanced Data Augmentation for Fine-Tuning Small Language Models
• SIMU: Selective Influence Machine Unlearning
• PlugTrack: Multi-Perceptive Motion Analysis for Adaptive Fusion in Multi-Object Tracking
• EMMA: Concept Erasure Benchmark with Comprehensive Semantic Metrics and Diverse Categories
• Double Horizon Model-Based Policy Optimization
• Amortising Inference and Meta-Learning Priors in Neural Networks
• Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning