Author

Yaguang Song

h-index 1 View on Semantic Scholar

We have 3 of 11 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

A Visual Dependence-Aware Framework for Multimodal Unsupervised Continual Post-Training

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. Existing unsupervised post-training methods for MLLMs typically optimize target tokens uniformly, overlooking their heterogeneous visual depend...

Kaichen Li, Zhilin Zhu, Jian-Hao Huang et al. · 0 citations

#artificial intelligence Preprint Sep 2026

CASS: Contribution-Aware Structured Sparsity for Model Merging

Model merging integrates task-specific fine-tuned models into a single multi-task model, but often suffers from parameter interference caused by conflicting task-vector updates. Existing methods typically mitigate conflicts by pruning task vectors based on weight magnitude or random heuristics, treating Transformers as...

Yan Li, Gui-Ping Cao, Meng-Du Xu et al. · 0 citations

Preprint Aug 2026

AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models

AgentPatch is proposed, a training-free coarse-to-fine repair framework that improves diverse merged backbones, alleviates weak-task degradation, and better balances weak-task recovery with the preservation of complementary search and agentic visual processing capabilities.

Zibo Shao, Baochen Xiong, Chengdong Xu et al. · 0 citations