Related papers: Manifold-Aligned Guided Integrated Gradients for R…

We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works. We identify two fundamental axioms---Sensitivity and Implementation Invariance that attribution…

With the growing demand for interpretable deep learning models, this paper introduces Integrative CAM, an advanced Class Activation Mapping (CAM) technique aimed at providing a holistic view of feature importance across Convolutional Neural…

Out-of-Distribution (OOD) detection is critical for safely deploying deep models in open-world environments, where inputs may lie outside the training distribution. During inference on a model trained exclusively with In-Distribution (ID)…

Multimodal Machine Translation (MMT) has demonstrated the significant help of visual information in machine translation. However, existing MMT methods face challenges in leveraging the modality gap by enforcing rigid visual-linguistic…

Meta-learning offers a principled framework leveraging \emph{task-invariant} priors from related tasks, with which \emph{task-specific} models can be fine-tuned on downstream tasks, even with limited data records. Gradient-based…

Retrieval-Augmented Generation (RAG), by incorporating external knowledge with parametric memory of language models, has become the state-of-the-art architecture for open-domain QA tasks. However, common knowledge bases are inherently…

Multimodal tabular-image fusion is an emerging task that has received increasing attention in various domains. However, existing methods may be hindered by gradient conflicts between modalities, misleading the optimization of the unimodal…

Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights. However, most…

Graph-level anomaly detection aims to identify anomalous graphs or subgraphs within graph datasets, playing a vital role in various fields such as fraud detection, review classification, and biochemistry. While Graph Neural Networks (GNNs)…

Recent research has demonstrated that feature attribution methods for deep networks can themselves be incorporated into training; these attribution priors optimize for a model whose attributions have certain desirable properties -- most…

Deep neural networks often suffer from poor performance or even training failure due to the ill-conditioned problem, the vanishing/exploding gradient problem, and the saddle point problem. In this paper, a novel method by acting the…

Previous studies have demonstrated the effectiveness of point-based neural models on the point cloud analysis task. However, there remains a crucial issue on producing the efficient input embedding for raw point coordinates. Moreover,…

Retrieval Augmented Generation (RAG) has emerged as an effective solution for mitigating hallucinations in Large Language Models (LLMs). The retrieval stage in RAG typically involves a pre-trained embedding model, which converts queries and…

This paper introduces the design and development of a framework that integrates a large language model (LLM) with a retrieval-augmented generation (RAG) approach leveraging both a knowledge graph and user interaction history. The framework…

Graphical User Interface (GUI) grounding - the task of mapping natural language instructions to screen coordinates - is essential for autonomous agents and accessibility technologies. Existing systems rely on monolithic models or one-shot…

While the manifold hypothesis is widely adopted in modern machine learning, complex data is often better modeled as stratified spaces -- unions of manifolds (strata) of varying dimensions. Stratified learning is challenging due to varying…

This work focuses on full-body co-speech gesture generation. Existing methods typically employ an autoregressive model accompanied by vector-quantized tokens for gesture generation, which results in information loss and compromises the…

The design of diffusion-based audio generation systems has been investigated from diverse perspectives, such as data space, network architecture, and conditioning techniques, while most of these innovations require model re-training. In…

Fine-grained visual classification (FGVC) is challenging but more critical than traditional classification tasks. It requires distinguishing different subcategories with the inherently subtle intra-class object variations. Previous works…

Manifold alignment (MA) involves a set of techniques for learning shared representations across domains, yet many traditional MA methods are incapable of performing out-of-sample extension, limiting their real-world applicability. We…