Related papers: Data Language Models: A New Foundation Model Class…

Despite significant advancements, large multimodal models (LMMs) still struggle to bridge the gap between low-level visual perception -- focusing on shapes, sizes, and layouts -- and high-level language reasoning, such as semantics and…

Building scalable and reusable multi-agent decision policies from offline datasets remains a challenge in offline multi-agent reinforcement learning (MARL), as existing methods often rely on fixed observation formats and action spaces that…

Diffusion Language Models (DLMs) offer attractive advantages over Auto-Regressive (AR) models, such as full-attention parallel decoding and flexible generation. However, standard DLM training uses a static, single-step masked prediction…

Existing pipelines for vision-language models (VLMs) in robotic manipulation prioritize broad semantic generalization from images and language, but typically omit execution-critical parameters required for contact-rich actions in…

While interpretability is crucial for machine learning applications in safety-critical domains and for regulatory compliance, existing tabular foundation models like TabPFN lack transparency. Generalized Additive Models (GAMs) provide the…

The advent of Large Language Models (LLMs) has significantly reshaped the trajectory of the AI revolution. Nevertheless, these LLMs exhibit a notable limitation, as they are primarily adept at processing textual information. To address this…

To advance foundation Large Language Models (LLMs) for combustion science, this study presents the first end-to-end framework for developing domain-specialized models for the combustion community. The framework comprises an AI-ready…

Table foundation models bring high hopes to data science: pre-trained on tabular data to embark knowledge or priors, they should facilitate downstream tasks on tables. One specific challenge is that of data semantics: numerical entries take…

Mathematical reasoning has long been a key benchmark for evaluating large language models. Although substantial progress has been made on math word problems, the need for reasoning over tabular data in real-world applications has been…

Robotic Foundation Models (RFMs) hold great promise as generalist, end-to-end systems for robot control. Yet their ability to generalize across new environments, tasks, and embodiments remains limited. We argue that a major bottleneck lies…

Deep learning (DL) models have gained prominence in domains such as computer vision and natural language processing but remain underutilized for regression tasks involving tabular data. In these cases, traditional machine learning (ML)…

Recent advancements in language models (LMs) have notably enhanced their ability to reason with tabular data, primarily through program-aided mechanisms that manipulate and analyze tables. However, these methods often require the entire…

Machine Learning (ML) in low-data settings remains an underappreciated yet crucial problem. Hence, data augmentation methods to increase the sample size of datasets needed for ML are key to unlocking the transformative potential of ML in…

Large language models have achieved remarkable success under the autoregressive paradigm, yet high-quality text generation need not be tied to a fixed left-to-right order. Existing alternatives still struggle to jointly achieve generation…

Large language models (LLMs) are primarily designed to understand unstructured text. When directly applied to structured formats such as tabular data, they may struggle to discern inherent relationships and overlook critical patterns. While…

Multi-step LLM reasoning over structured tables fails because planning and execution share no explicit cell-grounding contract. Existing methods constrain the planner to a left-to-right factorization at odds with table permutation…

The rapidly growing demand for high-quality data in Large Language Models (LLMs) has intensified the need for scalable, reliable, and semantically rich data preparation pipelines. However, current practices remain dominated by ad-hoc…

We study the application of large language models to zero-shot and few-shot classification of tabular data. We prompt the large language model with a serialization of the tabular data to a natural-language string, together with a short…

Tabular data synthesis is crucial in machine learning, yet existing general methods-primarily based on statistical or deep learning models-are highly data-dependent and often fall short in recommender systems. This limitation arises from…

Recent methods based on pre-trained language models have exhibited superior performance over tabular tasks (e.g., tabular NLI), despite showing inherent problems such as not using the right evidence and inconsistent predictions across…