Related papers: LiteFocus: Accelerated Diffusion Inference for Lon…
Autoregressive (AR) models remain the standard for natural language generation but still suffer from high latency due to strictly sequential decoding. Recent diffusion-inspired approaches, such as LlaDA and Dream, mitigate this by…
This paper investigates the design of effective prompt strategies for generating realistic datasets using Text-To-Audio (TTA) models. We also analyze different techniques for efficiently combining these datasets to enhance their utility in…
Diffusion models have demonstrated remarkable performance in speech synthesis, but typically require multi-step sampling, resulting in low inference efficiency. Recent studies address this issue by distilling diffusion models into…
Latent diffusion models have emerged as the leading approach for generating high-quality images and videos, utilizing compressed latent representations to reduce the computational burden of the diffusion process. While recent advancements…
The recent surge in popularity of diffusion models for image generation has brought new attention to the potential of these models in other areas of media generation. One area that has yet to be fully explored is the application of…
Training-free acceleration has emerged as an advanced research area in video generation based on diffusion models. The redundancy of latents in diffusion model inference provides a natural entry point for acceleration. In this paper, we…
High-quality long-context data is essential for training large language models (LLMs) capable of processing extensive documents, yet existing synthesis approaches using relevance-based aggregation face challenges of computational…
Given the audio-visual clip of the speaker, facial reaction generation aims to predict the listener's facial reactions. The challenge lies in capturing the relevance between video and audio while balancing appropriateness, realism, and…
The diffusion model is capable of generating high-quality data through a probabilistic approach. However, it suffers from the drawback of slow generation speed due to the requirement of a large number of time steps. To address this…
Video diffusion transformers have achieved remarkable progress in high-quality video generation, but remain computationally expensive due to the quadratic complexity of attention over high-dimensional video sequences. Recent acceleration…
High-fidelity video generation remains challenging for diffusion models due to the difficulty of modeling complex spatio-temporal dynamics efficiently. Recent video diffusion methods typically represent a video as a sequence of…
Autoregressive language models dominate modern text generation, yet their sequential nature introduces fundamental limitations: decoding is slow, and maintaining global coherence remains challenging. Diffusion models offer a promising…
This paper presents CQT-Diff, a data-driven generative audio model that can, once trained, be used for solving various different audio inverse problems in a problem-agnostic setting. CQT-Diff is a neural diffusion model with an architecture…
Advanced autoregressive (AR) video generation models have improved visual fidelity and interactivity, but the quadratic complexity of attention remains a primary bottleneck for efficient deployment. While existing sparse attention solutions…
Diffusion Language Models (DLMs) enable globally coherent, bidirectional, and controllable text generation, offering advantages over traditional autoregressive LLMs, while scaling to ultra-long sequences remains costly. Many existing…
We extend the recent latent recurrent modeling to sequential input streams. By interleaving fast, recurrent latent updates with self-organizational ability between slow observation updates, our method facilitates the learning of stable…
Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic…
Diffusion Transformers have demonstrated remarkable performance in video generation. However, their long input sequences incur substantial latency due to the quadratic complexity of full attention. Various sparse attention mechanisms have…
The rapid advancement of generative models has enabled highly realistic audio deepfakes, yet current detectors suffer from a critical bias problem, leading to poor generalization across unseen datasets. This paper proposes Artifact-Focused…
Text-to-video diffusion models enable the generation of high-quality videos that follow text instructions, making it easy to create diverse and individual content. However, existing approaches mostly focus on high-quality short video…