AI.info

Latest Research — Page 15

Browse Latest Research on AI.info.

• BrickBench: Evaluating Agentic Brick Design
• Toward Machine Translation Literacy: How Lay Users Perceive and Rely on Imperfect Translations
• TrajEvolve: Trajectory Evolution for Reinforcement Learning with Hindsight Credit Assignment
• Extreme Event Aware ($η$-) Learning
• Distilling Counterfactual Reasoning from Language to Vision: Causal Graph Guided Post-Training for Video Understanding
• PINT: A Unified Model with Shared Predictive Intent for Robot Manipulation
• Human-like cross-language generalisation in deep neural speaker embeddings and its acoustic foundations
• Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks
• Beyond Linear Surrogates: High-Fidelity Local Explanations for Black-Box Models
• Stable and Scalable Bundle Adjustment of Holistic 3D Structures
• VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoning
• TalentCLEF at CLEF2026: Skill and Job Title Intelligence for Human Capital Management
• Right Looks, Wrong Reasons: Compositional Fidelity in Text-to-Image Generation
• Generalized Audio-Driven Synthesis of Precise Drummer Motion
• When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents
• Multimodal Duplex Interaction Agent
• A Reasoning Paradigm for Named Entity Recognition
• Rule vs.Consequence: Dissociable Internal Representations of Moral Reasoning in LLMs
• How Much Physics Can Vision Learn from Audio? Probing and Distilling Damping Structure
• Recursa: Toward Recursively Self-Improving Foundation Model Systems
• Going Deeper With Memories
• PlaylistEval: Can Video-Language Judges Be Trusted at Day Scale and Beyond?
• Privacy in Image Datasets: A Case Study on Pregnancy Ultrasounds
• QMUL_AK at AISA-ArabicFC: Schema-Constrained Function Calling with ALLaM
• A Machine Learning Approach for Detection of Mental Health Conditions and Cyberbullying from Social Media
• Unifying Stable Optimization and Reference Regularization in RLHF
• Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning
• Principles2Plan: LLM-Guided System for Operationalising Ethical Principles into Plans
• Assessing AI Companion Chatbot Safety for Vulnerable Users: A Crisis-Stage Multi-Platform Evaluation
• Probable but Not Valid: A Psychometric Audit of Decision Models as Synthetic Survey Respondents
• Group Inertial Poser: Multi-Person Pose and Global Translation from Sparse Inertial Sensors and Ultra-Wideband Ranging
• DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle
• Temporal Slice Learning for AI-Generated Video Detection with 400$\times$ Fewer FLOPs
• PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking
• Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark
• The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning
• CSF: Contrastive Semantic Features for Direct Multilingual Sign Language Generation
• Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation
• TabReX : Tabular Referenceless eXplainable Evaluation
• Bayesian Neural Networks via Dirichlet Process Priors on the Data-Generating Distribution for Randomized Value Functions in Deep Reinforcement Learning