相关论文: Future-as-Label: Scalable Supervision from Real-Wo…

In the absence of large labelled datasets, self-supervised learning techniques can boost performance by learning useful representations from unlabelled data, which is often more readily available. However, there is often a domain shift…

Conventional reward modeling relies on gradient descent over neural weights, creating opaque, data-hungry "black boxes." We propose a paradigm shift from implicit to explicit reward parameterization, recasting optimization from continuous…

Language models often struggle to follow multi-constraint instructions that are crucial for real-world applications. Existing reinforcement learning (RL) approaches suffer from dependency on external supervision and sparse reward signals…

Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these…

Where do learning signals come from when there is no ground truth in post-training? We show that inference compute itself can serve as supervision. By generating parallel rollouts and converting them into reference estimates, models can…

Preference-based reinforcement learning (RL) has shown potential for teaching agents to perform the target tasks without a costly, pre-defined reward function by learning the reward with a supervisor's preference between the two agent…

Semi-supervised learning is a setting in which one has labeled and unlabeled data available. In this survey we explore different types of theoretical results when one uses unlabeled data in classification and regression tasks. Most methods…

Perceiving the world and forecasting its future state is a critical task for self-driving. Supervised approaches leverage annotated object labels to learn a model of the world -- traditionally with object detections and trajectory…

Consequential decisions are increasingly informed by sophisticated data-driven predictive models. However, to consistently learn accurate predictive models, one needs access to ground truth labels. Unfortunately, in practice, labels may…

Deep Learning heavily depends on large labeled datasets which limits further improvements. While unlabeled data is available in large amounts, in particular in image recognition, it does not fulfill the closed world assumption of…

Long-term fairness algorithms aim to satisfy fairness beyond static and short-term notions by accounting for the dynamics between decision-making policies and population behavior. Most previous approaches evaluate performance and fairness…

By training to predict the next token in an unlabeled corpus, large language models learn to perform many tasks without any labeled data. However, their next-token-prediction objective arguably limits their performance in scenarios that…

Semi-supervised learning leverages unlabeled data to enhance model performance, addressing the limitations of fully supervised approaches. Among its strategies, pseudo-supervision has proven highly effective, typically relying on one or…

Deep learning perception models require a massive amount of labeled training data to achieve good performance. While unlabeled data is easy to acquire, the cost of labeling is prohibitive and could create a tremendous burden on companies or…

Reinforcement Learning with Verifiable Rewards has recently advanced the capabilities of Large Language Models in complex reasoning tasks by providing explicit rule-based supervision. Among RLVR methods, GRPO and its variants have achieved…

Cross-modal data matching refers to retrieval of data from one modality, when given a query from another modality. In general, supervised algorithms achieve better retrieval performance compared to their unsupervised counterpart, as they…

Villalobos et al. [2024] predict that publicly available human text will be exhausted within the next decade. Thus, improving models without access to ground-truth labels becomes increasingly important. We propose a label-free…

Deep Neural Networks trained in a fully supervised fashion are the dominant technology in perception-based autonomous driving systems. While collecting large amounts of unlabeled data is already a major undertaking, only a subset of it can…

Evaluating the trustworthiness of a model's prediction is essential for differentiating between `right for the right reasons' and `right for the wrong reasons'. Identifying textual spans that determine the target label, known as faithful…

Semi-supervised learning holds great promise for many real-world applications, due to its ability to leverage both unlabeled and expensive labeled data. However, most semi-supervised learning algorithms still heavily rely on the limited…