AI.info

Latest Research — Page 93

Browse Latest Research on AI.info.

• AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent
• From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting
• Learning from Generalization Patterns: An Evaluation-Driven Approach to Enhanced Data Augmentation for Fine-Tuning Small Language Models
• Agent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams
• DBLoss: Decomposition-based Loss Function for Time Series Forecasting
• WebAnything: From the Wild Web to Scalable Agent Environments
• SpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMs
• Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered
• SIMU: Selective Influence Machine Unlearning
• Powerful Training-Free Membership Inference Against Autoregressive Language Models
• PlugTrack: Multi-Perceptive Motion Analysis for Adaptive Fusion in Multi-Object Tracking
• Gestura: A LVLM-Powered System Bridging Motion and Semantics for Real-Time Free-Form Gesture Understanding
• 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
• Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits
• Nested Learning: The Illusion of Deep Learning Architectures
• Towards Transparent Stance Detection: A Zero-Shot Approach Using Implicit and Explicit Interpretability
• ResWorld: Temporal Residual World Model for End-to-End Autonomous Driving
• SynthAgent: A Multi-Agent LLM Framework for Realistic Patient Simulation -- A Case Study in Obesity with Mental Health Comorbidities
• From Interpretability to Performance: Optimizing Retrieval Heads for Long-Context Language Models
• IntelliProof: An Argumentation Network-based Conversational Helper for Organized Reflection
• Do LLMs Really Struggle at NL-FOL Translation? Revealing their Strengths via a Novel Benchmarking Strategy
• Learning Time-Scale Invariant Population-Level Neural Representations
• ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability
• RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning
• A Branch-and-Price Algorithm for Fast and Equitable Last-Mile Relief Aid Distribution
• $Δτ$-Bench: Pushing Agents Toward a Moving Capability
• Leveraging Generic Time Series Foundation Models for EEG Classification
• Scalable Coverage Trajectory Synthesis on GPUs as Statistical Inference
• Exposure Is Not Commitment: Double-Stratified Evaluation of Latent Monitors for Tool-Using Agents
• WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents
• Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
• CrochetBench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain?
• Stabilizing Native Low-Rank LLM Pretraining
• Bridging the Basilisk Astrodynamics Framework with ROS 2 for Modular Spacecraft Simulation and Hardware Integration
• FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning
• Probing Negation Understanding in Vision-Language Models With Object Attention
• Robust Tabular Foundation Models