Related papers: GrounDiT: Grounding Diffusion Transformers via Noi…
Diffusion Transformers (DiTs) deliver state-of-the-art generative performance but their quadratic training cost with sequence length makes large-scale pretraining prohibitively expensive. Token dropping can reduce training cost, yet na\"ive…
Modern AI models excel in controlled settings but often fail in real-world scenarios where data distributions shift unpredictably - a challenge known as domain generalisation (DG). This paper tackles this limitation by rigorously evaluating…
While recent vision-language-action models trained on diverse robot datasets exhibit promising generalization capabilities with limited in-domain data, their reliance on compact action heads to predict discretized or continuous actions…
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…
Recent multimodal face generation models address the spatial control limitations of text-to-image diffusion models by augmenting text-based conditioning with spatial priors such as segmentation masks, sketches, or edge maps. This multimodal…
Recent audio-to-image models have shown impressive performance in generating images of specific objects conditioned on their corresponding sounds. However, these models fail to reconstruct real-world landscapes conditioned on environmental…
Diffusion Transformers (DiT)-based video generation models with 3D full attention exhibit strong generative capabilities. Trajectory control represents a user-friendly task in the field of controllable video generation. However, existing…
Large-scale text-to-image diffusion models have made amazing advances. However, the status quo is to use text input alone, which can impede controllability. In this work, we propose GLIGEN, Grounded-Language-to-Image Generation, a novel…
Diffusion Models (DMs) have achieved State-Of-The-Art (SOTA) results in the Lidar point cloud generation task, benefiting from their stable training and iterative refinement during sampling. However, DMs often fail to realistically model…
Transferring the depth-based end-to-end policy trained in simulation to physical robots can yield an efficient and robust grasping policy, yet sensor artifacts in real depth maps like voids and noise establish a significant sim2real gap…
Diffusion Transformers (DiTs) have demonstrated remarkable generative capabilities, particularly benefiting from Transformer architectures that enhance visual and artistic fidelity. However, their inherently sequential denoising process…
Diffusion Models achieve state-of-the-art performance in generating new samples but lack a low-dimensional latent space that encodes the data into editable features. Inversion-based methods address this by reversing the denoising…
Automatic drum transcription (ADT) is traditionally formulated as a discriminative task to predict drum events from audio spectrograms. In this work, we redefine ADT as a conditional generative task and introduce Noise-to-Notes (N2N), a…
We present SinDiffusion, leveraging denoising diffusion models to capture internal distribution of patches from a single natural image. SinDiffusion significantly improves the quality and diversity of generated samples compared with…
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…
Generative models have been widely studied in computer vision. Recently, diffusion models have drawn substantial attention due to the high quality of their generated images. A key desired property of image generative models is the ability…
In light of recent breakthroughs in text-to-image (T2I) generation, particularly with diffusion transformers (DiT), subject-driven technologies are increasingly being employed for high-fidelity customized production that preserves subject…
While large language models (LLMs) have revolutionized natural language processing with their task-agnostic capabilities, visual generation tasks such as image translation, style transfer, and character customization still rely heavily on…
Diffusion models are widely recognized for generating high-quality and diverse images, but their poor real-time performance has led to numerous acceleration works, primarily focusing on UNet-based structures. With the more successful…
Diffusion Transformers (DiTs) can generate short photorealistic videos, yet directly training and sampling longer videos with full attention across the video remains computationally challenging. Alternative methods break long videos down…