Related papers: TILBench: A Systematic Benchmark for Tabular Imbal…

As Large Language Model (LLM) alignment evolves from simple completions to complex, highly sophisticated generation, Reward Models are increasingly shifting toward rubric-guided evaluation to mitigate surface-level biases. However, the…

AI workloads, particularly those driven by deep learning, are introducing novel usage patterns to high-performance computing (HPC) systems that are not comprehensively captured by standard HPC benchmarks. As one of the largest academic…

Multi-task learning (MTL) has emerged as a promising approach for deploying deep learning models in real-life applications. Recent studies have proposed optimization-based learning paradigms to establish task-shared representations in MTL.…

Severe class imbalance is one of the main conditions that make machine learning in cybersecurity difficult. A variety of dataset preprocessing methods have been introduced over the years. These methods modify the training dataset by…

With the rapid advancement of Large Language Models (LLMs), there is an increasing need for challenging benchmarks to evaluate their capabilities in handling complex tabular data. However, existing benchmarks are either based on outdated…

Instruction-following is a foundational capability of large language models (LLMs), with its improvement hinging on scalable and accurate feedback from judge models. However, the reliability of current judge models in instruction-following…

Learning from imbalanced data is one of the most significant challenges in real-world classification tasks. In such cases, neural networks performance is substantially impaired due to preference towards the majority class. Existing…

Classification tasks require a balanced distribution of data to ensure the learner to be trained to generalize over all classes. In real-world datasets, however, the number of instances vary substantially among classes. This typically leads…

Research in AI4Science has shown promise in many science applications, including polymer design. However, current LLMs are ineffective in this problem space because: (i) most models lack polymer-specific knowledge, and (ii) existing aligned…

As compute power increases with time, more involved and larger simulations become possible. However, it gets increasingly difficult to efficiently use the provided computational resources. Especially in particle-based simulations with a…

Skills have become the de facto way to enable LLM agents to perform complex real-world tasks with customized instructions, workflows, and tools, but how to learn them automatically and effectively remains unclear. We introduce…

Robustness to label noise within data is a significant challenge in federated learning (FL). From the data-centric perspective, the data quality of distributed datasets can not be guaranteed since annotations of different clients contain…

Large Language Models (LLMs), while being increasingly dominant on a myriad of knowledge-intensive activities, have only had limited success understanding lengthy table-text mixtures, such as academic papers and financial reports. Recent…

Transformer-based tabular foundation models have recently demonstrated promising in-context learning (ICL) performance on structured data, emerging as competitive alternatives to gradient-boosted trees. However, the fairness implications of…

The growing demand for data-driven decision-making has created an urgent need for data agents that can integrate structured and unstructured data for analysis. While data agents show promise for enabling users to perform complex analytics…

The innovative Federated Multi-Task Learning (FMTL) approach consolidates the benefits of Federated Learning (FL) and Multi-Task Learning (MTL), enabling collaborative model training on multi-task learning datasets. However, a comprehensive…

The classification of imbalanced data streams, which have unequal class distributions, is a key difficulty in machine learning, especially when dealing with multiple classes. While binary imbalanced data stream classification tasks have…

Large Language Models (LLMs) show promise as data analysis agents, but existing benchmarks overlook the iterative nature of the field, where experts' decisions evolve with deeper insights of the dataset. To address this, we introduce…

Tabular data analysis is crucial in various fields, and large language models show promise in this area. However, current research mostly focuses on rudimentary tasks like Text2SQL and TableQA, neglecting advanced analysis like forecasting…

Modern translation workflows demand more than semantic equivalence. Users routinely require models to preserve JSON or HTML schemas, honor curated glossaries, disambiguate with provided context, and match prescribed registers, often several…