[논문리뷰] DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement LearningarXiv에 게시된 'DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.#Review#Reinforcement Learning#Length Penalty#Reasoning Efficiency#Large Language Models#RL Optimization#Accuracy-Efficiency Trade-off#Chain-of-Thought2025년 10월 20일댓글 수 로딩 중
[논문리뷰] Drax: Speech Recognition with Discrete Flow MatchingarXiv에 게시된 'Drax: Speech Recognition with Discrete Flow Matching' 논문에 대한 자세한 리뷰입니다.#Review#Automatic Speech Recognition (ASR)#Discrete Flow Matching (DFM)#Non-Autoregressive (NAR)#Generative Models#Tri-mixture Probability Path#Parallel Decoding#Accuracy-Efficiency Trade-off#Speech Synthesis2025년 10월 8일댓글 수 로딩 중