4 papers
A Visual Dependence-Aware Framework for Multimodal Unsupervised Continual Post-Training
Kaichen Li, Zhilin Zhu, Jianhao Huang +7
In this paper, we explore a novel task of Multimodal Unsupervised Continual Post-Training (MU-CPT), enabling deployed MLLMs to continually evolve from streaming unlabeled data. Exi…
AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models
Zibo Shao, Baochen Xiong, Chengdong Xu +6
Agentic multimodal large language models (MLLMs) extend multimodal perception and reasoning with planning, tool use, and interaction in dynamic environments. Yet current models are…
EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems
Chengdong Xu, Kaiqiang Ke, Ziheng Liu +4
Large language model (LLM)-based multi-agent systems have shown strong potential on complex tasks through agent specialization, tool use, and collaborative reasoning. However, most…
PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging
Zibo Shao, Baochen Xiong, Xiaoshan Yang +4
Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabi…