Related papers: Learning Hard Alignments with Variational Inferenc…

Despite rapid advances in speech recognition, current models remain brittle to superficial perturbations to their inputs. Small amounts of noise can destroy the performance of an otherwise state-of-the-art model. To harden models against…

To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Window Token Concatenation (WiCo). Specifically, we employ a sliding window to concatenate spatially adjacent visual tokens.…

Regression via classification (RvC) is a common method used for regression problems in deep learning, where the target variable belongs to a set of continuous values. By discretizing the target into a set of non-overlapping classes, it has…

Semantic segmentation of histopathology images under class imbalance is typically addressed through frequency-based loss reweighting, which implicitly assumes that rare classes are difficult. However, true difficulty also arises from…

Modern vision models, trained on large-scale annotated datasets, excel at predefined tasks but struggle with personalized vision -- tasks defined at test time by users with customized objects or novel objectives. Existing personalization…

There has recently been significant interest in training reinforcement learning (RL) agents in vision-based environments. This poses many challenges, such as high dimensionality and the potential for observational overfitting through…

Although deep convolutional neural networks achieve state-of-the-art performance across nearly all image classification tasks, their decisions are difficult to interpret. One approach that offers some level of interpretability by design is…

The quadratic complexity of self-attention during the prefill phase impedes long-context inference in large language models. Existing sparse attention methods face a trade-off among context adaptivity, sampling overhead, and fine-tuning…

Active learning aims to reduce annotation cost by selectively querying informative samples for supervision under a limited labeling budget. In this work, we investigate how vision-language models (VLMs) can be leveraged to further reduce…

Transformer architectures are now central to sequence modeling tasks. At its heart is the attention mechanism, which enables effective modeling of long-term dependencies in a sequence. Recently, transformers have been successfully applied…

The self-supervised ultrasound (US) video model pretraining can use a small amount of labeled data to achieve one of the most promising results on US diagnosis. However, it does not take full advantage of multi-level knowledge for learning…

Variational inference (VI) provides a principled framework for estimating posterior distributions over model parameters, enabling explicit modeling of weight uncertainty during optimization. By capturing this uncertainty, VI improves the…

Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match specified people in infrared images to visible images without annotations, and vice versa. USVI-ReID is a challenging yet under-explored task. Most existing…

Recognizing multiple labels of images is a fundamental but challenging task in computer vision, and remarkable progress has been attained by localizing semantic-aware image regions and predicting their labels with deep convolutional neural…

Vision-Language Navigation in Continuous Environments (VLNCE), where an agent follows instructions and moves freely to reach a destination, is a key research problem in embodied AI. However, most existing approaches are sensitive to…

The significant growth of surveillance camera networks necessitates scalable AI solutions to efficiently analyze the large amount of video data produced by these networks. As a typical analysis performed on surveillance footage, video…

Transformers have had tremendous impact for several sequence related tasks, largely due to their ability to retrieve from any part of the sequence via softmax based dot-product attention. This mechanism plays a crucial role in Transformer's…

Traditional neural networks are simple to train but they typically produce overconfident predictions. In contrast, Bayesian neural networks provide good uncertainty quantification but optimizing them is time consuming due to the large…

Despite the advances in the representational capacity of approximate distributions for variational inference, the optimization process can still limit the density that is ultimately learned. We demonstrate the drawbacks of biasing the true…

Semantic segmentation in adverse weather scenarios is a critical task for autonomous driving systems. While foundation models have shown promise, the need for specialized adaptors becomes evident for handling more challenging scenarios. We…