相关论文: Training-inference input alignment outweighs frame…

Artificial neural networks trained on visual tasks develop internal representations resembling those of the primate visual system, a discovery that has guided a decade of computational neuroscience. Research on building brain-aligned models…

Background: When using deep learning models, there are many possible vulnerabilities and some of the most worrying are the adversarial inputs, which can cause wrong decisions with minor perturbations. Therefore, it becomes necessary to…

While deep learning models like Vision Transformer (ViT) have achieved significant advances, they typically require large datasets. With data privacy regulations, access to many original datasets is restricted, especially medical images.…

Widespread adoption of AI for medical decision making is still hindered due to ethical and safety-related concerns. For AI-based decision support systems in healthcare settings it is paramount to be reliable and trustworthy. Common deep…

Subretinal injection is a critical procedure for delivering therapeutic agents to treat retinal diseases such as age-related macular degeneration (AMD). However, retinal motion caused by physiological factors such as respiration and…

Recurrent neural networks (RNNs) were designed for dealing with time-series data and have recently been used for creating predictive models from functional magnetic resonance imaging (fMRI) data. However, gathering large fMRI datasets for…

In Fluorescein Angiography (FA), an exogenous dye is injected in the bloodstream to image the vascular structure of the retina. The injected dye can cause adverse reactions such as nausea, vomiting, anaphylactic shock, and even death. In…

Forecasting from partial observations is central to world modeling. Many recent methods represent the world through images, and reduce forecasting to stochastic video generation. Although such methods excel at realism and visual fidelity,…

Large language models (LLMs) have exhibited impressive reasoning abilities on a wide range of complex tasks. However, enhancing these capabilities through post-training remains resource intensive, particularly in terms of data and…

Recent advances in large foundation models, such as the Segment Anything Model (SAM), have demonstrated considerable promise across various tasks. Despite their progress, these models still encounter challenges in specialized medical image…

In recent studies in hyperspectral imaging, biometrics and energy analytics, the framework of deep dictionary learning has shown promise. Deep dictionary learning outperforms other traditional deep learning tools when training data is…

Brain imaging classification is commonly approached from two perspectives: modeling the full image volume to capture global anatomical context, or constructing ROI-based graphs to encode localized and topological interactions. Although both…

Training long-context language models to capture long-range dependencies requires specialized data construction. Current approaches, such as generic text concatenation or heuristic-based variants, frequently fail to guarantee genuine…

We demonstrate that architectures which traditionally are considered to be ill-suited for a task can be trained using inductive biases from another architecture. We call a network untrainable when it overfits, underfits, or converges to…

Approximating training-point influence on test predictions is critical for deploying deep-learning vision models, essential for locating noisy data. Though the influence function was proposed for attributing how infinitesimal up-weighting…

Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear. We analyze reasoning dynamics in 18 VLMs covering instruction-tuned and…

A popular strategy to train recurrent neural networks (RNNs), known as ``teacher forcing'' takes the ground truth as input at each time step and makes the later predictions partly conditioned on those inputs. Such training strategy impairs…

Verifiable training has shown success in creating neural networks that are provably robust to a given amount of noise. However, despite only enforcing a single robustness criterion, its performance scales poorly with dataset complexity. On…

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…

Previous robustness approaches for deep learning models such as data augmentation techniques via data transformation or adversarial training cannot capture real-world variations that preserve the semantics of the input, such as a change in…