About
Research & Development
Streamlining Large Reasoning Models: A New Approach to Shorter, Smarter Outputs
TLDR: This research introduces Length Controlled Preference Optimization (LCPO), a novel method to significantly reduce the output length of Large Reasoning Models (LRMs) without...
Research & Development
Adaptive Policy Updates Boost Multi-Agent Reinforcement Learning Performance
TLDR: This research introduces HATRPO-G and HATRPO-W, two new methods that enhance Multi-Agent Reinforcement Learning (MARL) by adaptively allocating policy update budgets (KL divergence...
Research & Development
AI Takes the Lead: A New Paradigm for Clinical Diagnosis with DxDirector-7B
TLDR: DxDirector-7B is a new AI model that reverses the traditional physician-AI relationship, acting as the primary director of full-process clinical diagnosis with minimal...
Research & Development
MSRS: Enhancing LLM Control Through Adaptive Multi-Subspace Steering
TLDR: MSRS (Multi-Subspace Representation Steering) is a new framework designed to effectively control multiple attributes in Large Language Models (LLMs) simultaneously, such as truthfulness,...
Research & Development
Unlocking Smarter Conversations: A New Approach to Personalized Recommendations
TLDR: STEP is a novel conversational recommender system that uses a multi-stage learning process (curriculum learning) and specialized prompts to better combine user dialogue...
Research & Development
Unlocking Knowledge Integration: A New Framework for Ontology Alignment
TLDR: GenOM is a novel AI framework that enhances ontology matching by using large language models (LLMs) to generate detailed textual definitions for concepts....