[논문리뷰] VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing, Speaking, and ActingHaihan Gao이 arXiv에 게시한 'VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing, Speaking, and Acting' 논문에 대한 자세한 리뷰입니다.#Review#Embodied AI#Human-Robot Interaction#Vision-Language Models#Concurrency#Interruption#Robotics Control#Dual-Model Architecture#Special Tokens2025년 10월 28일댓글 수 로딩 중
[논문리뷰] SHANKS: Simultaneous Hearing and Thinking for Spoken Language ModelsKevin Lin이 arXiv에 게시한 'SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models' 논문에 대한 자세한 리뷰입니다.#Review#Spoken Language Models#Real-time Interaction#Thinking While Listening#Chain-of-Thought#Interruption#Tool Calling#Streaming ASR2025년 10월 9일댓글 수 로딩 중