Related papers: Combining Data-driven Supervision with Human-in-th…

End-to-end autonomous driving has emerged as a compelling alternative to traditional modular pipelines by directly mapping raw sensor data to driving actions. While recent approaches achieve strong performance on single-domain datasets,…

Even though many machine algorithms have been proposed for entity resolution, it remains very challenging to find a solution with quality guarantees. In this paper, we propose a novel HUman and Machine cOoperation (HUMO) framework for…

Transformer models have emerged as potent solutions to a wide array of multidisciplinary challenges. The deployment of Transformer architectures is significantly hindered by their extensive computational and memory requirements,…

Currently, data and model size dominate the narrative in the training of super-large, powerful models. However, there has been a lack of exploration on the effect of other attributes of the training dataset on model performance. We…

Mislabeled, duplicated, or biased data in real-world scenarios can lead to prolonged training and even hinder model convergence. Traditional solutions prioritizing easy or hard samples lack the flexibility to handle such a variety…

Human motion generation is a critical task with a wide range of applications. Achieving high realism in generated motions requires naturalness, smoothness, and plausibility. Despite rapid advancements in the field, current generation…

Entity resolution (ER) is the task of identifying records belonging to the same entity (e.g. individual, group) across one or multiple databases. Ironically, it has multiple names: deduplication and record linkage, among others. In this…

Layout generation plays a crucial role in enhancing both user experience and design efficiency. However, current approaches suffer from task-specific generation capabilities and perceptually misaligned evaluation metrics, leading to limited…

In response to everyday queries, humans explicitly signal uncertainty and offer alternative answers when they are unsure. Machine learning models that output calibrated prediction sets through conformal prediction mimic this human…

While the availability of large datasets is perceived to be a key requirement for training deep neural networks, it is possible to train such models with relatively little data. However, compensating for the absence of large datasets…

Large language models are widely deployed in high-stakes NLP tasks, yet risks such as bias, hallucination, adversarial vulnerability and unreliable generalization remain. Probe-based auditing reveals inconsistencies in model behavior.…

The performance, reliability, cost, size and energy usage of computing systems can be improved by one or more orders of magnitude by the systematic use of modern control and optimization methods. Computing systems rely on the use of…

Frozen models trained to mimic static datasets can never improve their performance. Models that can employ internet-retrieval for up-to-date information and obtain feedback from humans during deployment provide the promise of both adapting…

Reliable evaluation protocols are of utmost importance for reproducible NLP research. In this work, we show that sometimes neither metric nor conventional human evaluation is sufficient to draw conclusions about system performance. Using…

In recent years, meta-learning, in which a model is trained on a family of tasks (i.e. a task distribution), has emerged as an approach to training neural networks to perform tasks that were previously assumed to require structured…

Modern robotics is gravitating toward increasingly collaborative human robot interaction. Tools such as acceleration policies can naturally support the realization of reactive, adaptive, and compliant robots. These tools require us to model…

Integrating human expertise into machine learning systems often reduces the role of experts to labeling oracles, a paradigm that limits the amount of information exchanged and fails to capture the nuances of human judgment. We address this…

Physics-based humanoid control relies on training with motion datasets that have diverse data distributions. However, the fixed difficulty distribution of datasets limits the performance ceiling of the trained control policies.…

Aligning language models with human preferences through reinforcement learning from human feedback is crucial for their safe and effective deployment. The human preference is typically represented through comparison where one response is…

Performance of NLP systems is typically evaluated by collecting a large-scale dataset by means of crowd-sourcing to train a data-driven model and evaluate it on a held-out portion of the data. This approach has been shown to suffer from…