Author

Xiaosong Yuan

h-index 10 View on Semantic Scholar

We have 3 of 25 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

Context-Aware Cluster Decoding: Semantic Anchor-Driven Coherence in dMLLMs

A training-free decoding method that scores each masked position by a multiplicative composite of softmax confidence and neighbor proximity, promoting contextually ready tokens above isolated candidates while suppressing low-confidence positional noise, operating block-free to keep high-readiness anchors globally acces...

Yi-Kai Zhao, Qiyan Zhao, Jia-Quan Zhang et al. · 0 citations

#natural language process... Preprint Aug 2026

Information-Guided Frontier Decoding: Contextual Utility-Driven Commitment in dMLLMs

IGFD is proposed, a training-free decoding strategy that ranks candidates using token confidence, neighborhood uncertainty, and structural commitment risk and consistently outperforms existing decoding strategies across the majority of benchmarks and diffusion MLLM backbones under identical decoding budgets.

Xing-You Fang, Jin Zhong, Xiaosong Yuan et al. · 0 citations

Preprint Aug 2026

Coalition-Aware Skill Reliability for Self-Evolving Agents

Systematic skill-bank audits reveal two recurring reliability failures: coalition pollution, where bank-level gains conceal negative coalition-level skill contributions, and cross-domain utility reversal, where source-beneficial skills reverse their effects after transfer.

Qiyan Zhao, Xiao-Feng Zhang, Bo Liu et al. · 0 citations