Related papers: Flow with FlorDB: Incremental Context Maintenance …

Cloze-style reading comprehension has been a popular task for measuring the progress of natural language understanding in recent years. In this paper, we design a novel multi-perspective framework, which can be seen as the joint training of…

Large Language Models (LLMs) have the potential to revolutionize data analytics by simplifying tasks such as data discovery and SQL query synthesis through natural language interactions. This work serves as a pivotal first step toward the…

There is a growing interest in expanding the input capacity of language models (LMs) across various domains. However, simply increasing the context window does not guarantee robust performance across diverse long-input processing tasks,…

This paper revisits building machine learning algorithms that involve interactions between entities, such as those between financial assets in an actively managed portfolio, or interactions between users in a social network. Our goal is to…

In real-world machine learning (ML) pipelines, datasets are continuously growing. Models must incorporate this new training data to improve generalization and adapt to potential distribution shifts. The cost of model retraining is…

Modern deep learning systems require huge data sets to achieve impressive performance, but there is little guidance on how much or what kind of data to collect. Over-collecting data incurs unnecessary present costs, while under-collecting…

We propose a machine-learning-based methodology for in-situ weather forecast postprocessing that is both spatially coherent and multivariate. Compared to previous work, our Flow MAtching Postprocessing (FMAP) better represents the…

This paper introduces an advanced methodology for machine translation (MT) corpus generation, integrating semi-automated, human-in-the-loop post-editing with large language models (LLMs) to enhance efficiency and translation quality.…

People get informed of a daily task plan through diverse media involving both texts and images. However, most prior research only focuses on LLM's capability of textual plan generation. The potential of large-scale models in providing…

Augmenting large language models (LLMs) with external tools has emerged as a promising approach to solving complex problems. However, traditional methods, which finetune LLMs with tool demonstration data, can be both costly and restricted…

[Context and motivation.] Extracting features from mobile app reviews is increasingly important for multiple requirements engineering (RE) tasks. However, existing methods struggle to turn noisy, ambiguous feedback into interpretable…

Text generation is the automated process of producing written or spoken language using computational methods. It involves generating coherent and contextually relevant text based on predefined rules or learned patterns. However, challenges…

MeanFlow (MF) has recently been established as a framework for one-step generative modeling. However, its ``fastforward'' nature introduces key challenges in both the training objective and the guidance mechanism. First, the original MF's…

Long-context LLMs are increasingly in demand for applications such as retrieval-augmented generation. To defray the cost of pretraining LLMs over long contexts, recent work takes an approach of synthetic context extension: fine-tuning LLMs…

Many crowdsourced NLP datasets contain systematic gaps and biases that are identified only after data collection is complete. Identifying these issues from early data samples during crowdsourcing should make mitigation more efficient,…

Rich and context-aware activity logs facilitate user behavior analysis and health monitoring, making them a key research focus in ubiquitous computing. The remarkable semantic understanding and generation capabilities of Large Language…

Software developers maintain extensive mental models of code they produce and its context, often relying on memory to retrieve or reconstruct design decisions, edge cases, and debugging experiences. These missing links and data obstruct…

The rise of Generative AI introduces a new class of HPC workloads that integrates lightweight LLMs with traditional high-throughput applications to accelerate scientific discovery. The current design of HPC clusters is inadequate to support…

Recent studies have shown that Large Language Models (LLMs) struggle to accurately retrieve information and maintain reasoning capabilities when processing long-context inputs. To address these limitations, we propose a finetuning approach…

Human agents routinely reason on instances with incomplete and muddied data (and weigh the cost of obtaining further features). In contrast, much of ML is devoted to the unrealistic, sterile environment where all features are observed and…