paper-with-me

홈 › Papers

Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline

2026-03-05 · Guo Chen, Lidong Lu, Yicheng Liu, Liangrui Dong, Lidong Zou, Jixin Lv, Zhenquan Li, Xinyi Mao, Baoqi Pei, Shihao Wang, Zhiqi Li, Karan Sapra, Fuxiao Liu, Yin-Dong Zheng, Yifei Huang, Limin Wang, Zhiding Yu, Andrew Tao, Guilin Liu, Tong Lu arxiv

While datasets for video understanding have scaled to hour-long durations, they typically consist of densely concatenated clips that differ from natural, unscripted daily life. To bridge this gap, we introduce MM-Lifelong, a dataset designed for Multimodal Lifelong Understanding. Comprising 181.1 hours of footage, it is structured across Day, Week, and Month scales to capture varying temporal densities. Extensive evaluations reveal two critical failure modes in current paradigms: end-to-end MLLMs suffer from a Working Memory Bottleneck due to context saturation, while representative agentic baselines experience Global Localization Collapse when navigating sparse, month-long timelines. To address this, we propose the Recursive Multimodal Agent (ReMA), which employs dynamic memory management to iteratively update a recursive belief state, significantly outperforming existing methods. Finally, we establish dataset splits designed to isolate temporal and domain biases, providing a rigorous foundation for future research in supervised learning and out-of-distribution generalization.

📄 PDF Abstract BibTeX arXiv:2603.05484

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning

2026-05-08 · Jiazheng Li, Chi-Hao Wu, Yunze Liu, Kaize Ding 외 arxiv

Understanding ultra-long videos such as egocentric recordings, live streams, or surveillance footage spanning days to weeks, remains a challenge. For current multimodal LLMs: even with million-token context windows, fram…

Cross-Modal Retrieval

Visual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrieval

2026-05-15 · Aiden Yiliu Li, Nels Numan, Anthony Steed arxiv

Long video understanding requires more than large context windows. It also needs a memory mechanism that decides what visual evidence to retain, keeps it searchable over long horizons, and grounds later reasoning in reco…

A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

2025-08-10 · Jinyuan Fang, Yanwen Peng, Xi Zhang, Yingxu Wang 외 arxiv

Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manually crafted configurations that remain s…

MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs

2026-06-11 · He Li, Haoang Chi, Qizhou Wang, Yunxin Mao 외 arxiv

Multimodal large language models (MLLMs) are trained on massive multimodal data, making data unlearning increasingly important as data owners may request the removal of specific content. In practice, these requests often…

Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models

2025-03-20 · Chengkai Huang, Junda Wu, Yu Xia, Zixu Yu 외

Recent breakthroughs in Large Language Models (LLMs) have led to the emergence of agentic AI systems that extend beyond the capabilities of standalone models. By empowering LLMs to perceive external environments, integra…

Multimodal ReasoningRecommendation Systems