Author

Zi-Dan Wang

2 papers indexed here

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.

#artificial intelligence Preprint Oct 2026

Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder

CLIP serves as a foundational vision-language model and the de facto vision encoder for downstream VLMs such as LLaVA. Post-training offers a lightweight route to refine CLIP, but recent work argues that the standard contrastive loss is unsuitable for post-training due to catastrophic forgetting under small batches, mo...

Zi-Dan Wang, Ya-Qian Li, Xiao-Kai Zhang et al. · 0 citations

#artificial intelligence Mar 2026

Separators in Enhancing Autoregressive Pretraining for Vision Mamba

Under the evaluated four-image setting, these results indicate that separator-based long-sequence pretraining improves recognition robustness and dense visual prediction relative to ARM.

Han Liu, Zi-Dan Wang, Shuo-Xi Zhang et al. · arXiv.org · 0 citations