Reliable Content Recommendations with Counterfactual Learning
Improve content recommendations using Entire Space Counterfactual Learning to reduce bias and enhance post-click conversion rate estimation.
Human Strategic Decision Making in Parametrized Games
Explore a new framework enhancing human strategic decision making in parametrized games with quick, informed choices under uncertainty.
PhySe-RPO: AI-Powered Surgical Smoke Removal Tech
Discover PhySe-RPO, an AI-driven framework enhancing surgical video clarity by removing smoke using physics and semantics-guided optimization.
DomAgent: AI for Domain-Specific Code Generation
DomAgent enhances domain-specific code generation using knowledge graphs and case-based reasoning to improve AI coding accuracy and relevance.
Relationship-Aware Safety Unlearning for Safer Multimodal LLMs
Discover relationship-aware safety unlearning to prevent unsafe associations in multimodal LLMs while preserving benign concept uses effectively.