10 papers
MOSAIK: Multi-Patch Content-Aware Spatial Allocation of Image Tokens for Efficient Generation
Mohammadreza Hami, Mohammadreza Samadi, Chao Gao +1
Pixel-space diffusion models avoid the reconstruction ceiling of latent diffusion models by generating directly in image space. However, their substantially higher token count make…
DBLAST: Dependent Block Drafting for Stochastic Speculative Decoding
Amirmohammad Karimi, Chao Gao, Negar Hassanpour
Speculative decoding accelerates large language models' inference by using a lightweight drafter to propose multiple future tokens and a target model to verify them. While recent b…
RePack then Refine: Efficient Diffusion Transformer with Vision Foundation Model
Guanfang Dong, Luke Schultz, Negar Hassanpour +1
Semantic-rich features from Vision Foundation Models (VFMs) have been leveraged to enhance Latent Diffusion Models (LDMs). However, raw VFM features are typically high-dimensional…
Griffin: Generative Reference and Layout Guided Image Composition
Aryan Mikaeili, Amirhossein Alimohammadi, Negar Hassanpour +2
Text-to-image models have achieved a level of realism that enables the generation of highly convincing images. However, text-based control can be a limiting factor when more explic…
GLASS: Global-Local Aggregation for Inference-time Sparsification of LLMs
Amirmohsen Sattarifard, Sepehr Lavasani, Kunlin Zhang +5
Inference-time sparsification is a promising path to deploy large language models (LLMs) on resource-constrained devices, yet existing training-free methods typically estimate feed…
Cora: Correspondence-aware image editing using few step diffusion
Amirhossein Alimohammadi, Aryan Mikaeili, Sauradip Nag +3
Image editing is an important task in computer graphics, vision, and VFX, with recent diffusion-based methods achieving fast and high-quality results. However, edits requiring sign…
Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone
Negar Hassanpour, Muhammad Kamran Janjua, Kunlin Zhang +4
Balancing competing objectives remains a fundamental challenge in multi-task learning (MTL), primarily due to conflicting gradients across individual tasks. A common solution relie…
PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and Generation
Liyao Jiang, Negar Hassanpour, Mohammad Salameh +4
Recent research explores the potential of Diffusion Models (DMs) for consistent object editing, which aims to modify object position, size, and composition, etc., while preserving…
QuaSeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models
Keith G. Mills, Mohammad Salameh, Ruichen Chen +3
Diffusion Models (DM) have democratized AI image generation through an iterative denoising process. Quantization is a major technique to alleviate the inference cost and reduce the…
FRAP: Faithful and Realistic Text-to-Image Generation with Adaptive Prompt Weighting
Liyao Jiang, Negar Hassanpour, Mohammad Salameh +4
Text-to-image (T2I) diffusion models have demonstrated impressive capabilities in generating high-quality images given a text prompt. However, ensuring the prompt-image alignment r…