8 papers
Attacks on Approximate Caches in Text-to-Image Diffusion Models
Desen Sun, Shuncheng Jie, Sihang Liu
Diffusion models are a powerful class of generative models that produce images and other content from user prompts, but they are computationally intensive. To mitigate this cost, r…
Generate "Normal", Edit Poisoned: Branding Injection via Hint Embedding in Image Editing
Desen Sun, Jason Hon, Howe Wang +3
With the rapid advancement of generative AI, users increasingly rely on image-generation models for image design and creation. To achieve faithful outputs, users typically engage i…
Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model Serving
Yuyang Tian, Desen Sun, Yi Ding +1
As large language models (LLMs) become widely used, their environmental impact, especially carbon emission, has attracted more attention. Prior studies focus on compute-related car…
HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration
Desen Sun, Jason Hon, Jintao Zhang +1
Diffusion models have demonstrated a remarkable ability in Text-to-Image (T2I) generation applications. Despite the advanced generation output, they suffer from heavy computation o…
EnsembleCI: Ensemble Learning for Carbon Intensity Forecasting
Leyi Yan, Linda Wang, Sihang Liu +1
Carbon intensity (CI) measures the average carbon emissions generated per unit of electricity, making it a crucial metric for quantifying and managing the environmental impact. Acc…
Towards Sustainable Large Language Model Serving
Sophia Nguyen, Beihao Zhou, Yi Ding +1
In this work, we study LLMs from a carbon emission perspective, addressing both operational and embodied emissions, and paving the way for sustainable LLM serving. We characterize…