← Search

Chenming Shang

2 accepted papers

2025

HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation

NeurIPS 2025poster

The remarkable success of the autoregressive paradigm has made significant advancement in Multimodal Large Language Models (MLLMs), with powerful models like Show-o, Transfusion and Emu3 made notable strides in unified image understanding and generation. For the first time, we uncover a common pheno…

Cited by 0SourcecodeScholar
2025

ShifCon: Enhancing Non-Dominant Language Capabilities with a Shift-based Multilingual Contrastive Framework

ACL 2025long

Although fine-tuning Large Language Models (LLMs) with multilingual data can rapidly enhance the multilingual capabilities of LLMs, they still exhibit a performance gap between the dominant language (e.g., English) and non-dominant ones due to the imbalance of training data across languages. To furt…