most citedAdaptable and Precise: Enterprise-Scenario LLM Function-Calling Capability Training Pipeline

1 citations · 1 across the 1 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2025

SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding

Shuang Cheng, Yuhua Jiang, Zineng Zhou +5

Block-wise discrete diffusion offers an attractive balance between parallel generation and causal dependency modeling, making it a promising backbone for vision-language modeling.…