相关论文: TITAN-Guide: Taming Inference-Time AligNment for G…

Planning with pretrained diffusion models has emerged as a promising approach for solving test-time guided control problems. Standard gradient guidance typically performs optimally under convex, differentiable reward landscapes. However, it…

Amortized simulator-based inference offers a powerful framework for tackling Bayesian inference in computational fields such as engineering or neuroscience, increasingly leveraging modern generative methods like diffusion models to map…

Text-conditioned diffusion models can generate impressive images, but fall short when it comes to fine-grained control. Unlike direct-editing tools like Photoshop, text conditioned models require the artist to perform "prompt engineering,"…

Image generation using diffusion models have demonstrated outstanding learning capabilities, effectively capturing the full distribution of the training dataset. They are known to generate wide variations in sampled images, albeit with a…

Conditional diffusion models can create unseen images in various settings, aiding image interpolation. Interpolation in latent spaces is well-studied, but interpolation with specific conditions like text or poses is less understood. Simple…

Recent advances in diffusion models have successfully enabled text-guided image inpainting. While it seems straightforward to extend such editing capability into the video domain, there have been fewer works regarding text-guided video…

While diffusion models have shown impressive performance in 2D image/video generation, diffusion-based Text-to-Multi-view-Video (T2MVid) generation remains underexplored. The new challenges posed by T2MVid generation lie in the lack of…

Diffusion models have demonstrated superior performance across various generative tasks including images, videos, and audio. However, they encounter difficulties in directly generating high-resolution samples. Previously proposed solutions…

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward…

Diffusion models have emerged as the de facto paradigm for video generation. However, their reliance on web-scale data of varied quality often yields results that are visually unappealing and misaligned with the textual prompts. To tackle…

Text-guided image-to-video generation has made substantial progress, yet it still struggles to execute text-specified edits that require substantial changes to a reference image (\textit{e.g., object addition, removal, or modification}).…

We propose Guided-TTS 2, a diffusion-based generative model for high-quality adaptive TTS using untranscribed data. Guided-TTS 2 combines a speaker-conditional diffusion model with a speaker-dependent phoneme classifier for adaptive…

Denoising-based generative models, particularly diffusion and flow matching algorithms, have achieved remarkable success. However, aligning their output distributions with complex downstream objectives, such as human preferences,…

Recent advancements in Virtual Try-On (VTO) have demonstrated exceptional efficacy in generating realistic images and preserving garment details, largely attributed to the robust generative capabilities of text-to-image (T2I) diffusion…

Generative diffusion models for end-to-end autonomous driving often suffer from mode collapse, tending to generate conservative and homogeneous behaviors. While DiffusionDrive employs predefined anchors representing different driving…

Guiding unconditional diffusion models typically requires either retraining with conditional inputs or per-step gradient computations (e.g., classifier-based guidance), both of which incur substantial computational overhead. We present a…

Diffusion models have been widely used for conditional data cross-modal generation tasks such as text-to-image and text-to-video. However, state-of-the-art models still fail to align the generated visual concepts with high-level semantics…

Diffusion models are powerful tools for sampling from high-dimensional distributions by progressively transforming pure noise into structured data through a denoising process. When equipped with a guidance mechanism, these models can also…

The predominant approach to advancing text-to-image generation has been training-time scaling, where larger models are trained on more data using greater computational resources. While effective, this approach is computationally expensive,…

Text-to-audio (TTA) generation with fine-grained control signals, e.g., precise timing control or intelligible speech content, has been explored in recent works. However, constrained by data scarcity, their generation performance at scale…