About
Research & Development
Optimizing Clinical Code Prediction: A Modular AI Framework for ICD-10-CM
TLDR: This research introduces a modular AI framework to improve the accuracy and efficiency of ICD-10-CM medical code prediction. It addresses challenges in large...
Research & Development
MAPO: Improving Foundation Model Reasoning with Adaptive Policy Optimization
TLDR: MAPO (Mixed Advantage Policy Optimization) is a new strategy for improving how foundation models reason. It addresses limitations in existing reinforcement learning methods,...
Research & Development
Advancing User Profiling with Confidence-Driven AI
TLDR: CONF-PROFILE is a new AI framework for user profiling that infers user attributes like age, gender, and occupation without needing extensive pre-labeled data....
Research & Development
Unveiling LongCat-Flash-Thinking: An Efficient 560-Billion-Parameter Reasoning Model
TLDR: LongCat-Flash-Thinking is an efficient 560-billion-parameter open-source Mixture-of-Experts (MoE) AI model from Meituan. It achieves state-of-the-art performance in complex reasoning tasks like mathematics, coding,...
Research & Development
Understanding and Addressing Hallucinations in AI Agents
TLDR: This survey paper provides the first comprehensive review of hallucinations in LLM-based agents, proposing a new taxonomy that categorizes them into five types:...
Research & Development
Explaining Recommendations: How AI Bridges Model Logic and User Understanding
TLDR: This research investigates the effectiveness of Large Language Models (LLMs) in generating user-facing explanations for an inherently interpretable matrix-based recommender system (BSSMF). Through...