相关论文: Temporal Sampling Frequency Matters: A Capacity-Aw…

Pre-training and fine-tuning is a paradigm for alleviating the data scarcity problem in end-to-end speech translation (E2E ST). The commonplace "modality gap" between speech and text data often leads to inconsistent inputs between…

Ensembling deep learning models is a shortcut to promote its implementation in new scenarios, which can avoid tuning neural networks, losses and training algorithms from scratch. However, it is difficult to collect sufficient accurate and…

In autonomous driving, the end-to-end (E2E) driving approach that predicts vehicle control signals directly from sensor data is rapidly gaining attention. To learn a safe E2E driving system, one needs an extensive amount of driving data and…

Autonomous car racing is a challenging task, as it requires precise applications of control while the vehicle is operating at cornering speeds. Traditional autonomous pipelines require accurate pre-mapping, localization, and planning which…

End-to-end autonomous driving (E2E-AD) has rapidly emerged as a promising approach toward achieving full autonomy. However, existing E2E-AD systems typically adopt a traditional multi-task framework, addressing perception, prediction, and…

Sampling-based algorithms are widely used for motion planning in high-dimensional configuration spaces. However, due to low sampling efficiency, their performance often diminishes in complex configuration spaces with narrow corridors.…

End-to-end (E2E) models in autonomous driving aim to directly map sensor inputs to control commands, but their ability to generalize to novel and complex scenarios remains a key challenge. The common practice of fully fine-tuning the vision…

End-to-end learning has emerged as a transformative paradigm in autonomous driving. However, the inherently multimodal nature of driving behaviors and the generalization challenges in long-tail scenarios remain critical obstacles to robust…

Variational Autoencoders (VAEs) are powerful generative models that have been widely used in various fields, including image and text generation. However, one of the known challenges in using VAEs is the model's sensitivity to its…

End-to-end (E2E) autonomous driving has recently emerged as a new paradigm, offering significant potential. However, few studies have looked into the practical challenge of deployment across domains (e.g., cities). Although several works…

Latent variable models like the Variational Auto-Encoder (VAE) are commonly used to learn representations of images. However, for downstream tasks like semantic classification, the representations learned by VAE are less competitive than…

The well-established modular autonomous driving system is decoupled into different standalone tasks, e.g. perception, prediction and planning, suffering from information loss and error accumulation across modules. In contrast, end-to-end…

Sparse Autoencoders (SAEs) are widely employed for mechanistic interpretability and model steering. Within this context, steering is by design performed by means of decoding altered SAE intermediate representations. This procedure…

Electric vehicles (EVs) have the potential to reduce grid stress through smart charging strategies while simultaneously meeting user demand. This requires accurate forecasts of key charging parameters, such as energy demand and connection…

Predicting future frames of video sequences is challenging due to the complex and stochastic nature of the problem. Video prediction methods based on variational auto-encoders (VAEs) have been a great success, but they require the training…

This letter studies an ultra-reliable low latency communication problem focusing on a vehicular edge computing network in which vehicles either fetch and synthesize images recorded by surveillance cameras or acquire the synthesized image…

Edge intelligence autonomous driving (EIAD) offers computing resources in autonomous vehicles for training deep neural networks. However, wireless channels between the edge server and the autonomous vehicles are time-varying due to the…

Diffusion models have become a popular choice for decision-making tasks in robotics, and more recently, are also being considered for solving autonomous driving tasks. However, their applications and evaluations in autonomous driving remain…

Variational Autoencoders (VAEs) provide a theoretically-backed and popular framework for deep generative models. However, learning a VAE from data poses still unanswered theoretical questions and considerable practical challenges. In this…

Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be naturally understood as topic models. We propose a continuous…