Related papers: Cached Adaptive Token Merging: Dynamic Token Reduc…

In large-scale distributed environments, avoiding concurrent access to the same resource by multiple processes becomes a core challenge, commonly termed distributed mutual exclusion (DME). Token-based mechanisms have long been recognized as…

Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive inference due to their iterative denoising structure. While prior methods accelerate sampling by…

Diffusion Transformer (DiT) is a crucial method for content generation. However, it needs a lot of time to sample. Many studies have attempted to use caching to reduce the time consumption of sampling. Existing caching methods accelerate…

In this paper, we address the performance degradation of efficient diffusion models by introducing Multi-architecturE Multi-Expert diffusion models (MEME). We identify the need for tailored operations at different time-steps in diffusion…

Mixture-of-Experts-based (MoE-based) diffusion models demonstrate remarkable scalability in high-fidelity image generation, yet their reliance on expert parallelism introduces critical communication bottlenecks. State-of-the-art methods…

Reconstructing high-quality point clouds from images remains challenging in computer vision. Existing generative-model-based approaches, particularly diffusion-model approaches that directly learn the posterior, may suffer from…

The application of diffusion transformers is suffering from their significant inference costs. Recently, feature caching has been proposed to solve this problem by reusing features from previous timesteps, thereby skipping computation in…

Discrete diffusion models have recently become competitive with autoregressive models for language modeling, even outperforming them on reasoning tasks requiring planning and global coherence, but they require more computation at inference…

Diffusion Models have become a cornerstone of modern generative AI for their exceptional generation quality and controllability. However, their inherent \textit{multi-step iterations} and \textit{complex backbone networks} lead to…

The exponential growth of Large Multimodal Models (LMMs) has driven advancements in cross-modal reasoning but at significant computational costs. In this work, we focus on visual language models. We highlight the redundancy and inefficiency…

We introduce Transfusion, a recipe for training a multi-modal model over discrete and continuous data. Transfusion combines the language modeling loss function (next token prediction) with diffusion to train a single transformer over…

Recent advancements in diffusion models have notably improved the perceptual quality of generated images in text-to-image synthesis tasks. However, diffusion models often struggle to produce images that accurately reflect the intended…

Despite their generative power, diffusion models struggle to maintain style consistency across images conditioned on the same style prompt, hindering their practical deployment in creative workflows. While several training-free methods…

We present DyMU, an efficient, training-free framework that dynamically reduces the computational burden of vision-language models (VLMs) while maintaining high task performance. Our approach comprises two key components. First, Dynamic…

Diffusion models have emerged as powerful generative models, but their high computation cost in iterative sampling remains a significant bottleneck. In this work, we present an in-depth and insightful study of state-of-the-art acceleration…

Diffusion models are trained by learning a sequence of models that reverse each step of noise corruption. Typically, the model parameters are fully shared across multiple timesteps to enhance training efficiency. However, since the…

Autoregressive (AR) Large Language Models (LLMs) have demonstrated significant success across numerous tasks. However, the AR modeling paradigm presents certain limitations; for instance, contemporary autoregressive LLMs are trained to…

Large-scale transformer models have emerged as a powerful tool for semantic communication systems, enabling edge devices to extract rich representations for robust inference across noisy wireless channels. However, their substantial…

Diffusion transformers have shown exceptional performance in visual generation but incur high computational costs. Token reduction techniques that compress models by sharing the denoising process among similar tokens have been introduced.…

Diffusion Transformers have recently demonstrated unprecedented generative capabilities for various tasks. The encouraging results, however, come with the cost of slow inference, since each denoising step requires inference on a transformer…