3 papers
cs.CL2026
One Token Is Enough: Improving Diffusion Language Models with a Sink Token
Zihou Zhang, Zheyong Xie, Li Zhong +3
Diffusion Language Models (DLMs) have emerged as a compelling alternative to autoregressive approaches, enabling parallel text generation with competitive performance. Despite thes…
cs.CV2025
MMHMER:Multi-viewer and Multi-task for Handwritten Mathematical Expression Recognition
Kehua Chen, Haoyang Shen, Lifan Zhong +1
Handwritten Mathematical Expression Recognition (HMER) methods have made remarkable progress, with most existing HMER approaches based on either a hybrid CNN/RNN-based with GRU arc…
cs.CV2025
Clip4Retrofit: Enabling Real-Time Image Labeling on Edge Devices via Cross-Architecture CLIP Distillation
Li Zhong, Ahmed Ghazal, Jun-Jun Wan +4
Foundation models like CLIP (Contrastive Language-Image Pretraining) have revolutionized vision-language tasks by enabling zero-shot and few-shot learning through cross-modal align…