May 9, 2026 · Artificial Intelligence

BARD-VL Achieves New SOTA for Multimodal Diffusion Models via Autoregressive‑Diffusion Bridge

The BARD-VL framework bridges pretrained autoregressive vision‑language models to diffusion‑based VLMs, preserving or surpassing original performance while boosting decoding throughput up to three times, through progressive block merging, stage‑wise diffusion distillation, and engineering optimizations validated on multiple benchmarks.

BARD-VLbenchmarkdiffusion

0 likes · 9 min read

BARD-VL Achieves New SOTA for Multimodal Diffusion Models via Autoregressive‑Diffusion Bridge