3 papers
cs.AI2026
ReaGeo: Reasoning-Enhanced End-to-End Geocoding with LLMs
Jian Cui, Zhiyuan Ren, Desheng Weng +4
This paper proposes ReaGeo, an end-to-end geocoding framework based on large language models, designed to overcome the limitations of traditional multi-stage approaches that rely o…
cs.NI2026
Artic: AI-oriented Real-time Communication for MLLM Video Assistant
Jiangkai Wu, Zhiyuan Ren, Junquan Zhong +2
AI Video Assistant emerges as a new paradigm for Real-time Communication (RTC), where one peer is a Multimodal Large Language Model (MLLM) deployed in the cloud. This makes interac…
cs.NI2025
Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI
Jiangkai Wu, Zhiyuan Ren, Liming Liu +1
AI Video Chat emerges as a new paradigm for Real-time Communication (RTC), where one peer is not a human, but a Multimodal Large Language Model (MLLM). This makes interaction betwe…