[논문리뷰] Beyond Imitation: Reinforcement Learning for Active Latent PlanningWee Sun Lee이 arXiv에 게시한 'Beyond Imitation: Reinforcement Learning for Active Latent Planning' 논문에 대한 자세한 리뷰입니다.#Review#Large Language Models (LLMs)#Chain-of-Thought (CoT)#Latent Reasoning#Reinforcement Learning (RL)#Variational Autoencoder (VAE)#Active Planning#Numerical Reasoning#Coherence Reward2026년 1월 29일댓글 수 로딩 중
[논문리뷰] TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular DataJin Zeng이 arXiv에 게시한 'TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data' 논문에 대한 자세한 리뷰입니다.#Review#Tabular Data#Numerical Reasoning#Large Language Models (LLMs)#Table Question Answering (TQA)#Program-of-Thoughts (PoT)#Data Sanitization#Query Decomposition#Multi-hop Reasoning2025년 11월 9일댓글 수 로딩 중