Related papers: Beyond Binary Success: A Diagnostic Meta-Evaluatio…

Supervised machine learning often operates on the data-driven paradigm, wherein internal model parameters are autonomously optimized to converge predicted outputs with the ground truth, devoid of explicitly programming rules or a priori…

Advances in image restoration and enhancement techniques have led to discussion about how such algorithmscan be applied as a pre-processing step to improve automatic visual recognition. In principle, techniques like deblurring and…

Modern segmentation models achieve strong predictive performance but remain largely opaque, limiting our ability to diagnose failures, understand dataset shift, or intervene in a principled manner. We introduce Med-SegLens, a model-diffing…

Accurate and robust object pose estimation for robotics applications requires verification and refinement steps. In this work, we propose to integrate hypotheses verification with object pose refinement guided by physics simulation. This…

Few-shot learning is a standard practice in most deep learning based histopathology image segmentation, given the relatively low number of digitized slides that are generally available. While many models have been developed for domain…

Despite remarkable achievements in artificial intelligence, the deployability of learning-enabled systems in high-stakes real-world environments still faces persistent challenges. For example, in safety-critical domains like autonomous…

The rapid advancement of large language models has given rise to a plethora of applications across a myriad of real-world tasks, mainly centered on aligning with human intent. However, the complexities inherent in human intent necessitate a…

Heterogeneous information networks(HINs) become popular in recent years for its strong capability of modelling objects with abundant information using explicit network structure. Network embedding has been proved as an effective method to…

There currently exist two main approaches to reproducing visual appearance using Machine Learning (ML): The first is training models that generalize over different instances of a problem, e.g., different images of a dataset. As one-shot…

We explore the scaling behaviors of artificial intelligence to establish practical techniques for training foundation models on high-resolution electro-optical (EO) datasets that exceed the current state-of-the-art scale by orders of…

Hyperparameters tuning is a fundamental, yet computationally expensive, step in optimizing machine learning models. Beyond optimization, understanding the relative importance and interaction of hyperparameters is critical to efficient model…

Semi-supervised learning has become a dominant paradigm for reducing annotation costs. However, we argue that the current progress is clouded by a twofold overconfidence problem. Algorithmically, mainstream pseudo-labeling frameworks often…

Understanding neural responses to visual stimuli remains challenging due to the inherent complexity of brain representations and the modality gap between neural data and visual inputs. Existing methods, mainly based on reducing neural…

With the rapid advances of image editing techniques in recent years, image manipulation detection has attracted considerable attention since the increasing security risks posed by tampered images. To address these challenges, a novel…

Medical diagnosis requires the effective synthesis of visual manifestations and clinical metadata. However, existing methods often treat metadata as isolated tags, failing to exploit the rich semantic knowledge embedded in clinical…

The transition from fitting empirical data to achieving true human utility is fundamentally constrained by a granularity mismatch, where fine-grained autoregressive generation is often supervised by coarse or uniform signals. This position…

Interpretation and diagnosis of machine learning models have gained renewed interest in recent years with breakthroughs in new approaches. We present Manifold, a framework that utilizes visual analysis techniques to support interpretation,…

Modern automated microscopy faces a fundamental discovery challenge: in many systems, the most important scientific information does not reside in the immediately visible image features, but in the target space of sequentially acquired…

Text-to-image (T2I) models are increasingly used for synthetic dataset generation, but generating effective synthetic training data for classification remains challenging. Fine-tuning a T2I model with a few real examples can help improve…

A central goal in understanding human vision is to uncover the visual features that drive neuronal activity. A growing body of work has used artificial neural networks as encoding models to predict cortical responses to natural images,…