Related papers: DriveDiTFit: Fine-tuning Diffusion Transformers fo…

Diffusion models are widely used for generative tasks across domains. Given a pre-trained diffusion model, it is often desirable to fine-tune it further either to correct for errors in learning or to align with downstream applications.…

Despite recent advances in UNet-based image editing, methods for shape-aware object editing in high-resolution images are still lacking. Compared to UNet, Diffusion Transformers (DiT) demonstrate superior capabilities to effectively capture…

Diffusion models have recently shown promise in time series forecasting, particularly for probabilistic predictions. However, they often fail to achieve state-of-the-art point estimation performance compared to regression-based methods.…

End-to-end autonomous driving systems directly generate driving policies from raw sensor inputs. While these systems can extract effective environmental features for planning, relying on auxiliary perception tasks, developing perception…

This paper proposes MATT-Diff: Multimodal Active Target Tracking by Diffusion Policy, a control policy for active multi-target tracking using a mobile agent. The policy enables multiple behavior modes for the agent, including exploration,…

As autonomous driving technology matures, safety and robustness of its key components, including trajectory prediction, is vital. Though real-world datasets, such as Waymo Open Motion, provide realistic recorded scenarios for model…

Recent advances in diffusion models have demonstrated remarkable capabilities in video generation. However, the computational intensity remains a significant challenge for practical applications. While feature caching has been proposed to…

Up-to-date High-Definition (HD) maps are essential for self-driving cars. To achieve constantly updated HD maps, we present a deep neural network (DNN), Diff-Net, to detect changes in them. Compared to traditional methods based on object…

Object detectors often suffer a decrease in performance due to the large domain gap between the training data (source domain) and real-world data (target domain). Diffusion-based generative models have shown remarkable abilities in…

Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all autonomous driving systems. Existing image and video driving datasets, however, fall short of capturing the mutable nature of the real…

Perception is a cornerstone of autonomous driving, enabling vehicles to understand their surroundings and make safe, reliable decisions. Developing robust perception algorithms requires large-scale, high-quality datasets that cover diverse…

The validation of autonomous driving systems benefits greatly from the ability to generate scenarios that are both realistic and precisely controllable. Conventional approaches, such as real-world test drives, are not only expensive but…

Recent works such as REPA have shown that guiding diffusion models with external semantic features (e.g., DINO) can significantly accelerate the training of diffusion transformers (DiTs). However, the use of pretrained external features as…

Driving world models are used to simulate futures by video generation based on the condition of the current state and actions. However, current models often suffer serious error accumulations when predicting the long-term future, which…

Personalized image generation aims to produce images of user-specified concepts while enabling flexible editing. Recent training-free approaches, while exhibit higher computational efficiency than training-based methods, struggle with…

In the visual generative area, discrete diffusion models are gaining traction for their efficiency and compatibility. However, pioneered attempts still fall behind their continuous counterparts, which we attribute to noise (absorbing state)…

The performance of robots in high-level tasks depends on the quality of their lower-level controller, which requires fine-tuning. However, the intrinsically nonlinear dynamics and controllers make tuning a challenging task when it is done…

Diffusion models recently emerged as a powerful paradigm for recommender systems, offering state-of-the-art performance by modeling the generative process of user-item interactions. However, training such models from scratch is both…

Recent advancements in video diffusion models based on Diffusion Transformers (DiTs) have achieved remarkable success in generating temporally coherent videos. Yet, a fundamental question persists: how do these models internally establish…

Dataset distillation has emerged as an effective strategy, significantly reducing training costs and facilitating more efficient model deployment. Recent advances have leveraged generative models to distill datasets by capturing the…