作者位次 #3/8ACL 2026Poster· Natural Language Processing
From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents
Niu Lian · Yuting Wang · Hanshu Yao · Jinpeng Wang · Bin Chen · Yaowei Wang · Min Zhang · Shu-Tao Xia
摘要
While multimodal large language models have demonstrated impressive short-term reasoning, they struggle with long-horizon video understanding due to limited context windows and static memory mechanisms that fail to mirror human cognitive efficiency. Existing paradigms typically fall into two extr...