3 papers
cs.AI2026
Serving Masked Diffusion LLMs: Characterization and Design Principles from Real Hardware
Farhana Amin, Sabiha Afroz, Mona Moghadampanah +1
Masked diffusion language models (dLLMs) can in principle generate text faster than autoregressive (AR) models, since they denoise many tokens at once. Recent systems have begun bu…
cs.DC2026
Modality Inflation: Energy Characterization and Optimization Opportunities for MLLM Inference
Mona Moghadampanah, Adib Rezaei Shahmirzadi, Farhana Amin +1
Multimodal large language models (MLLMs) are built on text-only LLMs by incorporating additional modalities, enabling multimodal understanding and a broader range of applications.…
cs.LG2025
DiffPro: Joint Timestep and Layer-Wise Precision Optimization for Efficient Diffusion Inference
Farhana Amin, Sabiha Afroz, Kanchon Gharami +2
Diffusion models produce high quality images but inference is costly due to many denoising steps and heavy matrix operations. We present DiffPro, a post-training, hardware-faithful…