Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Ma, Xinyin"'
Diffusion Transformers have demonstrated remarkable capabilities in image generation but often come with excessive parameterization, resulting in considerable inference overhead in real-world applications. In this work, we present TinyFusion, a depth
Externí odkaz:
http://arxiv.org/abs/2412.01199
In the rapidly advancing field of image generation, Visual Auto-Regressive (VAR) modeling has garnered considerable attention for its innovative next-scale prediction approach. This paradigm offers substantial improvements in efficiency, scalability,
Externí odkaz:
http://arxiv.org/abs/2411.17787
Latent diffusion models have shown promising results in audio generation, making notable advancements over traditional methods. However, their performance, while impressive with short audio clips, faces challenges when extended to longer audio sequen
Externí odkaz:
http://arxiv.org/abs/2407.10468
Structured pruning reduces the computational overhead of deep neural networks by removing redundant sub-structures. However, assessing the relative importance of different sub-structures remains a significant challenge, particularly in advanced visio
Externí odkaz:
http://arxiv.org/abs/2407.04616
Diffusion models have garnered significant interest from the community for their great generative ability across various applications. However, their typical multi-step sequential-denoising nature gives rise to high cumulative latency, thereby preclu
Externí odkaz:
http://arxiv.org/abs/2406.06911
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 model wit
Externí odkaz:
http://arxiv.org/abs/2406.01733
Current approaches for compressing the Segment Anything Model (SAM) yield commendable results, yet necessitate extensive data to train a new network from scratch. Employing conventional pruning techniques can remarkably reduce data requirements but w
Externí odkaz:
http://arxiv.org/abs/2312.05284
Diffusion models have recently gained unprecedented attention in the field of image synthesis due to their remarkable generative capabilities. Notwithstanding their prowess, these models often incur substantial computational costs, primarily attribut
Externí odkaz:
http://arxiv.org/abs/2312.00858
Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. However, such impressive capability typically comes with a substantial model size, which presents significant challenges in both the deployment,
Externí odkaz:
http://arxiv.org/abs/2305.11627
Generative modeling has recently undergone remarkable advancements, primarily propelled by the transformative implications of Diffusion Probabilistic Models (DPMs). The impressive capability of these models, however, often entails significant computa
Externí odkaz:
http://arxiv.org/abs/2305.10924