Related papers: TMComposites: Plug-and-Play Collaboration Between …

Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in Transformers can be…

Discrete tokenizers have emerged as indispensable components in modern machine learning systems, particularly within the context of autoregressive modeling and large language models (LLMs). These tokenizers serve as the critical interface…

Integrating General Models (GMs) such as Large Language Models (LLMs), with Specialized Models (SMs) in autonomous driving tasks presents a promising approach to mitigating challenges in data diversity and model capacity of existing…

Finding well-defined clusters in data represents a fundamental challenge for many data-driven applications, and largely depends on good data representation. Drawing on literature regarding representation learning, studies suggest that one…

Accurate forecasting in financial markets requires integrating diverse data sources, from historical prices to macroeconomic indicators and financial news. However, existing models often fail to align these modalities effectively, limiting…

Although Reinforcement Learning (RL)-based Traffic Signal Control (TSC) methods have been extensively studied, their practical applications still raise some serious issues such as high learning cost and poor generalizability. This is…

Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities in various multi-modal tasks. Nevertheless, their performance in fine-grained image understanding tasks is still limited. To address this issue, this paper…

Masked image modeling (MIM) has emerged as a promising approach for pre-training Vision Transformers (ViTs). MIMs predict masked tokens token-wise to recover target signals that are tokenized from images or generated by pre-trained models…

Tsetlin machines (TMs) have been successful in several application domains, operating with high efficiency on Boolean representations of the input data. However, Booleanizing complex data structures such as sequences, graphs, images, signal…

Computer Algebra Systems (e.g. Maple) are used in research, education, and industrial settings. One of their key functionalities is symbolic integration, where there are many sub-algorithms to choose from that can affect the form of the…

Large-scale pre-trained Vision-Language Models (VLMs) have become essential for transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, diminishing their performance on…

Large Language Models (LLMs) have shown impressive progress in mathematical reasoning. While data augmentation is promising to enhance mathematical problem-solving ability, current approaches are predominantly limited to instance-level…

Recent progress in time-series forecasting has led to rapidly increasing architectural complexity, yet many reported State-of-the-Art gains are statistically fragile or misattributed. We argue that progress requires a shift from model…

Combining multiple audio features can improve the performance of music tagging, but common deep learning-based feature fusion methods often lack interpretability. To address this problem, we propose a Genetic Programming (GP) pipeline that…

This paper presents a novel knowledge distillation neural architecture leveraging efficient transformer networks for effective image classification. Natural images display intricate arrangements encompassing numerous extraneous elements.…

Deep clustering algorithms combine representation learning and clustering by jointly optimizing a clustering loss and a non-clustering loss. In such methods, a deep neural network is used for representation learning together with a…

Mixing datasets for fine-tuning large models (LMs) has become critical for maximizing performance on downstream tasks. However, composing effective dataset mixtures typically relies on heuristics and trial-and-error, often requiring…

Machine learning potentials (MLPs) are becoming powerful tools for performing accurate atomistic simulations and crystal structure optimizations. An approach to developing MLPs employs a systematic set of polynomial invariants including…

Multimodal medical image fusion (MMIF) aims to integrate images from different modalities to produce a comprehensive image that enhances medical diagnosis by accurately depicting organ structures, tissue textures, and metabolic information.…

Thomson scattering (TS) diagnostics provide reliable, minimally perturbative measurements of fundamental plasma parameters, such as electron density ($n_e$) and electron temperature ($T_e$). Deep neural networks can provide accurate…