Related papers: No Data? No Problem: Robust Vision-Tabular Learnin…

Vision-Language Models (VLMs) have demonstrated remarkable capabilities in interpreting visual layouts and text. However, a significant challenge remains in their ability to interpret robustly and reason over multi-tabular data presented as…

In this paper, we propose SimMLM, a simple yet powerful framework for multimodal learning with missing modalities. Unlike existing approaches that rely on sophisticated network architectures or complex data imputation techniques, SimMLM…

This paper presents a detailed study of improving visual representations for vision language (VL) tasks and develops an improved object detection model to provide object-centric representations of images. Compared to the most widely used…

Randomized Controlled Trials (RCTs) represent the gold standard for causal inference yet remain a scarce resource. While large-scale observational data is often available, it is utilized only for retrospective fusion, and remains discarded…

Language models pretrained on large collections of tabular data have demonstrated their effectiveness in several downstream tasks. However, many of these models do not take into account the row/column permutation invariances, hierarchical…

Relational understanding is critical for a number of visually-rich documents (VRDs) understanding tasks. Through multi-modal pre-training, recent studies provide comprehensive contextual representations and exploit them as prior knowledge…

This paper explores training medical vision-language models (VLMs) -- where the visual and language inputs are embedded into a common space -- with a particular focus on scenarios where training data is limited, as is often the case in…

We introduce a new table detection and structure recognition approach named RobusTabNet to detect the boundaries of tables and reconstruct the cellular structure of each table from heterogeneous document images. For table detection, we…

This paper tackles the problem of robust covariance matrix estimation when the data is incomplete. Classical statistical estimation methodologies are usually built upon the Gaussian assumption, whereas existing robust estimation ones assume…

The success of VLMs often relies on the dynamic high-resolution schema that adaptively augments the input images to multiple crops, so that the details of the images can be retained. However, such approaches result in a large number of…

Accurate biomedical image classification under low-resource conditions remains challenging due to limited annotations, subtle inter-class visual differences, and complex disease semantics. While vision--language models offer a promising…

Unsupervised tabular anomaly detection methods typically learn feature patterns from normal samples during training and subsequently identify samples that deviate from these patterns as anomalies during testing. However, in practical…

Vision-Language-Action (VLA) models, particularly diffusion-based architectures, demonstrate transformative potential for embodied intelligence but are severely hampered by high computational and memory demands stemming from extensive…

We consider the problem of learning a control policy that is robust against the parameter mismatches between the training environment and testing environment. We formulate this as a distributionally robust reinforcement learning (DR-RL)…

Subtle semantic differences in retinal image and text data present great challenges for pre-training visual-language models. Moreover, false negative samples, i.e., image-text pairs having the same semantics but incorrectly regarded as…

Versatile medical image segmentation (VMIS) targets the segmentation of multiple classes, while obtaining full annotations for all classes is often impractical due to the time and labor required. Leveraging partially labeled datasets (PLDs)…

Recent work on deep learning for tabular data demonstrates the strong performance of deep tabular models, often bridging the gap between gradient boosted decision trees and neural networks. Accuracy aside, a major advantage of neural models…

Medical images are often more difficult to acquire than natural images due to the specialism of the equipment and technology, which leads to less medical image datasets. So it is hard to train a strong pretrained medical vision model. How…

We introduce FIDAVL: Fake Image Detection and Attribution using a Vision-Language Model. FIDAVL is a novel and efficient mul-titask approach inspired by the synergies between vision and language processing. Leveraging the benefits of…

Self-supervised learning on tabular data seeks to apply advances from natural language and image domains to the diverse domain of tables. However, current techniques often struggle with integrating multi-domain data and require data…