Related papers: OASIS: Order-Augmented Strategy for Improved Code …

Humans interpret scenes by recognizing both the identities and positions of objects in their observations. For a robot to perform tasks such as \enquote{pick and place}, understanding both what the objects are and where they are located is…

Aligning generative real-world image super-resolution models with human visual preference is challenging due to the perception--fidelity trade-off and diverse, unknown degradations. Prior approaches rely on offline preference optimization…

The presence of label noise often misleads the training of deep neural networks. Departing from the recent literature which largely assumes the label noise rate is only determined by the true label class, the errors in human-annotated…

Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

The performance of neural code search is significantly influenced by the quality of the training data from which the neural models are derived. A large corpus of high-quality query and code pairs is demanded to establish a precise mapping…

Software development is a repetitive task, as developers usually reuse or get inspiration from existing implementations. Code search, which refers to the retrieval of relevant code snippets from a codebase according to the developer's…

Cross-modal alignment is a crucial task in multimodal learning aimed at achieving semantic consistency between vision and language. This requires that image-text pairs exhibit similar semantics. Traditional algorithms pursue embedding…

Despite the achievements of large-scale multimodal pre-training approaches, cross-modal retrieval, e.g., image-text retrieval, remains a challenging task. To bridge the semantic gap between the two modalities, previous studies mainly focus…

Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. While the mainstream technique seeks to completely filter out…

The goal of natural language semantic code search is to retrieve a semantically relevant code snippet from a fixed set of candidates using a natural language query. Existing approaches are neither effective nor efficient enough towards a…

Many real-world reinforcement learning problems have a hierarchical nature, and often exhibit some degree of partial observability. While hierarchy and partial observability are usually tackled separately (for instance by combining…

Self-supervised learning (SSL) has recently achieved promising performance for 3D medical image analysis tasks. Most current methods follow existing SSL paradigm originally designed for photographic or natural images, which cannot…

To be discoverable in an embedding-based search process, each part of a document should be reflected in its embedding representation. To quantify any potential reflection biases, we introduce a permutation-based evaluation framework. With…

Word embedding is an essential building block for deep learning methods for natural language processing. Although word embedding has been extensively studied over the years, the problem of how to effectively embed numerals, a special subset…

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…

A recent line of research on automated speaking assessment (ASA) has benefited from self-supervised learning (SSL) representations, which capture rich acoustic and linguistic patterns in non-native speech without underlying assumptions of…

Like humans, deep networks have been shown to learn better when samples are organized and introduced in a meaningful order or curriculum. Conventional curriculum learning schemes introduce samples in their order of difficulty. This forces…

With the increasing complexity of the traffic environment, the importance of safety perception in intelligent driving is growing. Conventional methods in the robust perception of intelligent driving focus on training models with anomalous…

Recently, test-time scaling has garnered significant attention from the research community, largely due to the substantial advancements of the o1 model released by OpenAI. By allocating more computational resources during the inference…