AI.info

Latest Research — Page 119

Browse Latest Research on AI.info.

• VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation
• ORGAN: Object-Centric Representation Learning using Cycle Consistent Generative Adversarial Networks
• Towards Inference-time Scaling for Continuous Space Reasoning
• T3former: Temporal Graph Classification with Topological Machine Learning
• SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation
• IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures
• Multimodal Assessment of Pancreatic Cancer Resectability Using Deep Learning
• Comparing Dynamical Models Through Diffeomorphic Vector Field Alignment
• BTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, Rerankers and LLMs
• Depth-Wise Probing and Pruning of the Planning Token in a Driving Vision-Language-Action Model
• Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation
• Do We Really Need Permutations? Impact of Model Width on Linear Mode Connectivity
• Beyond Pixel Simulation: Pathology Image Generation via Diagnostic Semantic Tokens and Prototype Control
• Hybrid Token Compression for Vision-Language Models
• O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning
• FINDER: Feature Inference on Noisy Datasets using Eigenspace Residuals
• FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models
• Auditing Alignment Controllability in LLMs via Political Axes
• Two-step Authentication: Multi-biometric System Using Voice and Facial Recognition
• RGMem: Renormalization Group-inspired Memory Evolution for Language Agents
• RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
• Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection
• Grounding Clinical AI Competency in Human Cognition Through the Clinical World Model and Skill-Mix Framework
• Measuring Task-Agnostic Training Data Influence Across Language Model Pretraining
• Integrating Multi-Label Classification and Generative AI for Scalable Analysis of User Feedback
• The Misclassification of Autistic Writing as AI-Generated
• Structural priors for data-efficient language learning
• Preference is More Than Comparisons: Rethinking Dueling Bandits with Augmented Human Feedback
• MEGA-GUI: Multi-stage Enhanced Grounding Agents for GUI Elements
• Steering LLMs Responses Towards Moral Foundations on the Norwegian MFQ-30
• Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models
• P-Check: Advancing Personalized Reward Model via Learning to Generate Dynamic Checklist
• PromptTailor: Multi-turn Intent-Aligned Prompt Synthesis for Lightweight LLMs
• Orchestration Framework for Financial Agents: From Algorithmic Trading to Agentic Trading
• A Graph-Theoretical Perspective on Law Design for Multiagent Systems
• SutureBot: A Precision Framework & Benchmark For Autonomous End-to-End Suturing
• Training-Free Reconstruction-Based AI-Generated Image Detectors Are Inherently Vulnerable to Adversarial Examples
• SWE-IF: Aligning Code Evaluation with Human Preference
• Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD
• QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs