相关论文: Directed Self Guided Learning of Blended Math-Scie…

We present Logics-STEM, a state-of-the-art reasoning model fine-tuned on Logics-STEM-SFT-Dataset, a high-quality and diverse dataset at 10M scale that represents one of the largest-scale open-source long chain-of-thought corpora.…

We investigate automatic interlinear glossing in low-resource settings. We augment a hard-attentional neural model with embedded translation information extracted from interlinear glossed text. After encoding these translations using large…

Multilingual pre-trained models are able to zero-shot transfer knowledge from rich-resource to low-resource languages in machine reading comprehension (MRC). However, inherent linguistic discrepancies in different languages could make…

Federated learning enables the creation of a powerful centralized model without compromising data privacy of multiple participants. While successful, it does not incorporate the case where each participant independently designs its own…

Research on reasoning in language models (LMs) predominantly focuses on improving the correctness of their outputs. But some important applications require modeling reasoning patterns that are incorrect. For example, automated systems that…

Multimodal learning, which aims to understand and analyze information from multiple modalities, has achieved substantial progress in the supervised regime in recent years. However, the heavy dependence on data paired with expensive human…

Large language models (LLMs) are challenging to deploy for domain-specific tasks due to their massive scale. While distilling a fine-tuned LLM into a smaller student model is a promising alternative, the capacity gap between teacher and…

Nowadays, collaborative modeling performed by multiple stakeholders is gaining a growing interest in both academia and practice. However, it poses a set of research challenges, such as large and complex models management, support for…

Assessment tasks provide opportunities for students to make sense of novel contexts in light of their existing ideas. Consequently, investigations in physics education research have extensively developed and analyzed assessments that…

Art and science are different ways of exploring the world, but together they have the potential to be thought-provoking, facilitate a science-society dialogue, raise public awareness of science, and develop an understanding of art. For…

In this work, we investigate how spatially grounded auxiliary representations can provide both broad, high-level grounding as well as direct, actionable information to improve policy learning performance and generalization for dexterous…

Meta-learning represents a strong class of approaches for solving few-shot learning tasks. Nonetheless, recent research suggests that simply pre-training a generic encoder can potentially surpass meta-learning algorithms. In this paper, we…

To address the modality imbalance caused by data heterogeneity, existing multi-modal learning (MML) approaches primarily focus on balancing this difference from the perspective of optimization objectives. However, almost all existing…

The astronomical growth of data has necessitated the need for educating well-qualified data scientists to derive deep insights from large and complex data sets generated by organizations. In this paper, we present our interdisciplinary…

In recent years, there is a lot of interest in modeling students' digital traces in Learning Management System (LMS) to understand students' learning behavior patterns including aspects of meta-cognition and self-regulation, with the…

We introduce Minimal Achievable Sufficient Statistic (MASS) Learning, a training method for machine learning models that attempts to produce minimal sufficient statistics with respect to a class of functions (e.g. deep networks) being…

Deep neural state-space models (SSMs) provide a powerful tool for modeling dynamical systems solely using operational data. Typically, neural SSMs are trained using data collected from the actual system under consideration, despite the…

Recently, the progress of learning-by-synthesis has proposed a training model for synthetic images, which can effectively reduce the cost of human and material resources. However, due to the different distribution of synthetic images…

We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and…

Conventional centralised deep learning paradigms are not feasible when data from different sources cannot be shared due to data privacy or transmission limitation. To resolve this problem, federated learning has been introduced to transfer…