Related papers: Autolearn: Learn by Surprise, Commit by Proof
The impressive capability of modern text-to-image models to generate realistic visuals has come with a serious drawback: they can be misused to create harmful, deceptive or unlawful content. This has accelerated the push for machine…
The learning rate is one of the most important hyper-parameters for model training and generalization. However, current hand-designed parametric learning rate schedules offer limited flexibility and the predefined schedule may not match the…
Learning and decision-making in domains with naturally high noise-to-signal ratio, such as Finance or Healthcare, is often challenging, while the stakes are very high. In this paper, we study the problem of learning and acting under a…
A machine learning model that generalizes well should obtain low errors on unseen test examples. Thus, if we know how to optimally perturb training examples to account for test examples, we may achieve better generalization performance.…
Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial efforts in creating and annotating data. In this work, we…
Teaching machines to read natural language documents remains an elusive challenge. Machine reading systems can be tested on their ability to answer questions posed on the contents of documents that they have seen, but until now large scale…
Neural unsupervised parsing (UP) models learn to parse without access to syntactic annotations, while being optimized for another task like language modeling. In this work, we propose self-training for neural UP models: we leverage…
With the blooming of various Pre-trained Language Models (PLMs), Machine Reading Comprehension (MRC) has embraced significant improvements on various benchmarks and even surpass human performances. However, the existing works only target on…
Contrastive learning has been widely applied to graph representation learning, where the view generators play a vital role in generating effective contrastive samples. Most of the existing contrastive learning methods employ pre-defined…
Standard accuracy metrics indicate that reading comprehension systems are making rapid progress, but the extent to which these systems truly understand language remains unclear. To reward systems with real language understanding abilities,…
Deep learning-based recommendation has become a widely adopted technique in various online applications. Typically, a deployed model undergoes frequent re-training to capture users' dynamic behaviors from newly collected interaction logs.…
Data labeling in supervised learning is considered an expensive and infeasible tool in some conditions. The self-supervised learning method is proposed to tackle the learning effectiveness with fewer labeled data, however, there is a lack…
Autonomous machine learning systems that learn many tasks in sequence are prone to the catastrophic forgetting problem. Mathematical theory is needed in order to understand the extent of forgetting during continual learning. As a…
The idea of end-to-end learning of communications systems through neural network -based autoencoders has the shortcoming that it requires a differentiable channel model. We present in this paper a novel learning algorithm which alleviates…
The past a few years have witnessed the great success of large language models, demonstrating powerful capabilities in comprehending textual data and generating human-like languages. Large language models achieve success by being trained on…
Automatic data augmentation (AutoAugment) strategies are indispensable in supervised data-efficient training protocols of vision transformers, and have led to state-of-the-art results in supervised learning. Despite the success, its…
Large Reasoning Models (LRMs) have the ability to self-correct even when they make mistakes in their reasoning paths. However, our study reveals that when the reasoning process starts with a short but poor beginning, it becomes difficult…
Learning-based perception and prediction modules in modern autonomous driving systems typically rely on expensive human annotation and are designed to perceive only a handful of predefined object categories. This closed-set paradigm is…
Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for privacy and safety. Existing machine unlearning methods…
We propose new techniques for reducing communication in private federated learning without the need for setting or tuning compression rates. Our on-the-fly methods automatically adjust the compression rate based on the error induced during…