Related papers: MonarchRT: Efficient Attention for Real-Time Video…
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…
Generating temporally-consistent high-fidelity videos can be computationally expensive, especially over longer temporal spans. More-recent Diffusion Transformers (DiTs) -- despite making significant headway in this context -- have only…
The practical deployment of diffusion-based Neural Video Compression (NVC) faces critical challenges, including severe information loss, prohibitive inference latency, and poor temporal consistency. To bridge this gap, we propose DiffVC-RT,…
Current hierarchical attention methods, such as NSA and InfLLMv2, select the top-k relevant key-value (KV) blocks based on coarse attention scores and subsequently apply fine-grained softmax attention on the selected tokens. However, the…
Sora-like video generation models have achieved remarkable progress with a Multi-Modal Diffusion Transformer MM-DiT architecture. However, the current video generation models predominantly focus on single-prompt, struggling to generate…
The efficiency of attention is important due to its quadratic time complexity. We enhance the efficiency of attention through two key contributions: First, we leverage the new FP4 Tensor Cores in Blackwell GPUs to accelerate attention…
Recently, Diffusion Transformers (DiTs) have emerged as a dominant architecture in video generation, surpassing U-Net-based models in terms of performance. However, the enhanced capabilities of DiTs come with significant drawbacks,…
We introduce Monarch Sparse Tuning (MoST), the first reparameterization-based parameter-efficient fine-tuning (PEFT) method tailored for 3D representation learning. Unlike existing adapter-based and prompt-tuning 3D PEFT methods, MoST…
Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…
Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerating diffusion…
Native 4K (2160$\times$3840) video generation remains a critical challenge due to the quadratic computational explosion of full-attention as spatiotemporal resolution increases, making it difficult for models to strike a balance between…
Recent advancements in video generation have been greatly driven by video diffusion models, with camera motion control emerging as a crucial challenge in creating view-customized visual content. This paper introduces trajectory attention, a…
Diffusion Transformers are fundamental for video and image generation, but their efficiency is bottlenecked by the quadratic complexity of attention. While block sparse attention accelerates computation by attending only critical key-value…
Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to…
As Large Language Models (LLMs) scale to longer context windows, the computational cost of attention mechanisms, which traditionally grows quadratically with input length, presents a critical challenge for real-time and memory-constrained…
Diffusion models can synthesize realistic co-speech video from audio for various applications, such as video creation and virtual agents. However, existing diffusion-based methods are slow due to numerous denoising steps and costly…
The self-attention mechanism has been a key factor in the advancement of vision Transformers. However, its quadratic complexity imposes a heavy computational burden in high-resolution scenarios, restricting the practical application.…
Current video generation models suffer from high computational latency, making real-time applications prohibitively costly. In this paper, we address this limitation by exploiting the temporal redundancy inherent in video latent patches. To…
Video super-resolution (VSR) seeks to reconstruct high-resolution frames from low-resolution inputs. While diffusion-based methods have substantially improved perceptual quality, extending them to video remains challenging for two reasons:…
Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation…