cross-modal alignment 1layer-wise merging 1model merging 1multimodal pretraining 1parameter interference 1vision-language models 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.AI2026
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…
cs.CV2026
PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging
Zibo Shao, Baochen Xiong, Xiaoshan Yang +4
The paper introduces PivotMerge, a framework for merging multimodal language models trained on heterogeneous data by separating shared cross‑modal alignment patterns from domain‑sp…
cs.AI2026
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…