Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Inclusion AI, Tiwei Bie, Haoxing Chen +15
We present LLaDA2.0-Uni, a unified discrete diffusion large language model (dLLM) that supports multimodal understanding and generation within a natively integrated framework. Its…
cs.CV2025
Contrastive Representation Distillation via Multi-Scale Feature Decoupling
Cuipeng Wang, Haipeng Wang
Knowledge distillation enhances the performance of compact student networks by transferring knowledge from more powerful teacher networks without introducing additional parameters.…