Related papers: Contrastive Weak-to-strong Generalization

Pre-trained language models (LMs) store knowledge in their parameters and can generate informative responses when used in conversational systems. However, LMs suffer from the problem of "hallucination:" they may generate plausible-looking…

Deep neural network-based classifiers trained with the categorical cross-entropy (CCE) loss are sensitive to label noise in the training data. One common type of method that can mitigate the impact of label noise can be viewed as supervised…

Contrastive learning has emerged as an essential approach for self-supervised learning in visual representation learning. The central objective of contrastive learning is to maximize the similarities between two augmented versions of an…

Large language models (LLMs) have demonstrated exceptional proficiency in language understanding. However, when LLMs align their outputs with deceptive and/or misleading prompts, the generated responses could deviate from the de facto…

We introduce a principled probabilistic framework for reward-guided decoding in large language models, addressing the limitations of standard decoding methods that optimize token-level likelihood rather than sequence-level quality. Our…

Contrastive learning has gained widespread adoption for retrieval tasks due to its minimal requirement for manual annotations. However, popular training frameworks typically learn from binary (positive/negative) relevance, making them…

Low-frequency word prediction remains a challenge in modern neural machine translation (NMT) systems. Recent adaptive training methods promote the output of infrequent words by emphasizing their weights in the overall training objectives.…

GRPO is a standard approach to endowing pretrained LLMs with reasoning capabilities. It estimates the advantage of an outcome from a group of $K$ outcomes, and promotes those with positive advantages inside a trust region. Since GRPO…

Noisy images are a challenge to image compression algorithms due to the inherent difficulty of compressing noise. As noise cannot easily be discerned from image details, such as high-frequency signals, its presence leads to extra bits…

Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack principled guarantees on coverage…

Learning generalizable reward functions is a core challenge in embodied intelligence. Recent work leverages contrastive vision language models (VLMs) to obtain dense, domain-agnostic rewards without human supervision. These methods adapt…

Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness In this work, we improve robustness-aware self-supervised pre-training by learning representations…

Image captioning, a popular topic in computer vision, has achieved substantial progress in recent years. However, the distinctiveness of natural descriptions is often overlooked in previous work. It is closely related to the quality of…

Contrastive learning (CL) has emerged as a powerful framework for learning representations of images and text in a self-supervised manner while enhancing model robustness against adversarial attacks. More recently, researchers have extended…

Graph neural network (GNN) is a powerful learning approach for graph-based recommender systems. Recently, GNNs integrated with contrastive learning have shown superior performance in recommendation with their data augmentation schemes,…

Trigger-word detection plays an important role as the entry point of user's communication with voice assistants. But supporting a particular word as a trigger-word involves huge amount of data collection, augmentation and labelling for that…

Models for Visual Question Answering (VQA) often rely on the spurious correlations, i.e., the language priors, that appear in the biased samples of training set, which make them brittle against the out-of-distribution (OOD) test data.…

Systematic generalization refers to the capacity to understand and generate novel combinations from known components. Despite recent progress by large language models (LLMs) across various domains, these models often fail to extend their…

Decoding strategies manipulate the probability distribution underlying the output of a language model and can therefore affect both generation quality and its uncertainty. In this study, we investigate the impact of decoding strategies on…

Graph contrastive learning (GCL) aims to contrast positive-negative counterparts to learn the node embeddings, whereas graph data augmentation methods are employed to generate these positive-negative samples. The variation, quantity, and…