Related papers: DiffAttn: Diffusion-Based Drivers' Visual Attentio…

Driver attention prediction is becoming an essential research problem in human-like driving systems. This work makes an attempt to predict the driver attention in driving accident scenarios (DADA). However, challenges tread on the heels of…

Recent advances in multimodal large language models (MLLMs) have enabled image-based question-answering capabilities. However, a key limitation is the use of CLIP as the visual encoder; while it can capture coarse global information, it…

Diffusion Transformers (DiT) excel at image and video generation but face computational challenges due to the quadratic complexity of self-attention operators. We propose DiTFastAttn, a post-training compression method to alleviate the…

Research interest in end-to-end autonomous driving has surged owing to its fully differentiable design integrating modular tasks, i.e. perception, prediction and planing, which enables optimization in pursuit of the ultimate goal. Despite…

Fine-grained object detection in challenging visual domains, such as vehicle damage assessment, presents a formidable challenge even for human experts to resolve reliably. While DiffusionDet has advanced the state-of-the-art through…

Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities…

Ensuring safe interactions between autonomous vehicles (AVs) and human drivers in mixed traffic systems remains a major challenge, particularly in complex, high-risk scenarios. This paper presents a cognition-decision framework that…

Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific…

Open-Vocabulary Temporal Action Detection (OV-TAD) aims to localize and classify action segments of unseen categories in untrimmed videos, where effective alignment between action semantics and video representations is critical for accurate…

BEV perception is of great importance in the field of autonomous driving, serving as the cornerstone of planning, controlling, and motion prediction. The quality of the BEV feature highly affects the performance of BEV perception. However,…

We introduce DriveAgent, a novel multi-agent autonomous driving framework that leverages large language model (LLM) reasoning combined with multimodal sensor fusion to enhance situational understanding and decision-making. DriveAgent…

Sign language translation (SLT) is challenging, as it involves converting sign language videos into natural language. Previous studies have prioritized accuracy over diversity. However, diversity is crucial for handling lexical and…

Trajectory prediction is an essential component in autonomous driving, particularly for collision avoidance systems. Considering the inherent uncertainty of the task, numerous studies have utilized generative models to produce multiple…

Safety-critical traffic simulation plays a crucial role in evaluating autonomous driving systems under rare and challenging scenarios. However, existing approaches often generate unrealistic scenarios due to insufficient consideration of…

While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lagged behind their architectural evolution. Unlike traditional…

Recent DiT-based text-to-image models increasingly adopt LLMs as text encoders, yet text conditioning remains largely static and often utilizes only a single LLM layer, despite pronounced semantic hierarchy across LLM layers and…

The autonomous driving community is increasingly focused on addressing the challenges posed by out-of-distribution (OOD) driving scenarios. A dominant research trend seeks to enhance end-to-end (E2E) driving systems by integrating…

Diffusion models (DMs) embark a new era of generative modeling and offer more opportunities for efficient generating high-quality and realistic data samples. However, their widespread use has also brought forth new challenges in model…

Autonomous driving technology has seen significant advancements, but existing models often fail to fully capture the complexity of multi-agent environments, where interactions between dynamic agents are critical. To address this, we propose…

Vehicle trajectory prediction is crucial for advancing autonomous driving and advanced driver assistance systems (ADAS), enhancing road safety and traffic efficiency. While traditional methods have laid foundational work, modern deep…