Related papers: Unified Work Embeddings: Contrastive Learning of a…

Text embeddings are commonly evaluated on a small set of datasets from a single task not covering their possible applications to other tasks. It is unclear whether state-of-the-art embeddings on semantic textual similarity (STS) can be…

Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generalizable representations of numerical and categorical structured data. However, they lack…

Task embeddings are low-dimensional representations that are trained to capture task properties. In this paper, we propose MetaEval, a collection of $101$ NLP tasks. We fit a single transformer to all MetaEval tasks jointly while…

The simultaneous application of multiple treatments is increasingly common in many fields, such as healthcare and marketing. In such scenarios, it is important to estimate the single treatment effects and the interaction treatment effects…

Word embeddings have recently seen a strong increase in interest as a result of strong performance gains on a variety of tasks. However, most of this research also underlined the importance of benchmark datasets, and the difficulty of…

Multilingual Word Embeddings (MWEs) represent words from multiple languages in a single distributional vector space. Unsupervised MWE (UMWE) methods acquire multilingual embeddings without cross-lingual supervision, which is a significant…

This paper introduces Multidimensional Task Learning (MTL), a unified mathematical framework based on Generalized Einstein MLPs (GE-MLPs) that operate directly on tensors via the Einstein product. We argue that current computer vision task…

Foundation models have established unified representations for natural language processing, yet this paradigm remains largely unexplored for tabular data. Existing methods face fundamental limitations: LLM-based approaches lack…

Scene understanding is crucial for autonomous systems which intend to operate in the real world. Single task vision networks extract information only based on some aspects of the scene. In multi-task learning (MTL), on the other hand, these…

Benchmarking has long served as a foundational practice in machine learning and, increasingly, in modern AI systems such as large language models, where shared tasks, metrics, and leaderboards offer a common basis for measuring progress and…

Deep neural networks have achieved outstanding performance over various tasks, but they have a critical issue: over-confident predictions even for completely unknown samples. Many studies have been proposed to successfully filter out these…

Model merging combines independently trained models into a single multi-task model. However, most existing approaches focus primarily on avoiding task interference. We argue that its greater potential lies in enabling task synergy, where…

Industrial recommender systems commonly rely on ensemble sorting (ES) to combine predictions from multiple behavioral objectives. Traditionally, this process depends on manually designed nonlinear transformations (e.g., polynomial or…

Despite recent progress in Multi-Modal Large Language Models (MLLMs), it remains challenging to integrate diverse tasks ranging from pixel-level perception to high-fidelity generation. Existing approaches often suffer from either restricted…

The recent development and success of Large Language Models (LLMs) necessitate an evaluation of their performance across diverse NLP tasks in different languages. Although several frameworks have been developed and made publicly available,…

Tabular foundation models aim to learn universal representations of tabular data that transfer across tasks and domains, enabling applications such as table retrieval, semantic search and table-based prediction. Despite the growing number…

Pairwise human-preference platforms such as Chatbot Arena have become central to large language model (LLM) evaluation, yet reliable task-specific ranking remains challenging. Global leaderboards mask task heterogeneity, while ranking each…

Model merging integrates the weights of multiple task-specific models into a single multi-task model. Despite recent interest in the problem, a significant performance gap between the combined and single-task models remains. In this paper,…

Despite the exceptional reasoning capabilities of Multimodal Large Language Models (MLLMs), their adaptation into universal embedding models is significantly impeded by task conflict. To address this, we propose TSEmbed, a universal…

Model merging provides a scalable alternative to multi-task training by combining specialized finetuned models through parameter arithmetic, enabling efficient deployment without the need for joint training or access to all task data. While…