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

Several explanation methods such as Integrated Gradients (IG) can be characterised as path-based methods, as they rely on a straight line between the data and an uninformative baseline. However, when applied to language models, these…

While human cognition inherently retrieves information from diverse and specialized knowledge sources during decision-making processes, current Retrieval-Augmented Generation (RAG) systems typically operate through single-source knowledge…

Classifier-Free Guidance (CFG) improves sample quality in diffusion models, but its dual-pass inference and reliance on null-condition training limit its use in few-step regimes. Attention-space guidance has emerged as a complementary…

Gradient-based attribution methods are model-faithful and scalable, but Integrated Gradients (IG) can be brittle because explanations depend on heuristic baselines, straight-line paths, discretization, and saturation. We propose Fisher--Rao…

In-context learning has recently been linked to implicit gradient descent in linear self-attention models, suggesting that context can induce a forward-pass update. Retrieval-augmented generation (RAG) also relies on context, but retrieved…

Uncovering hidden graph structures underlying real-world data is a critical challenge with broad applications across scientific domains. Recently, transformer-based models leveraging the attention mechanism have demonstrated strong…

Spectral gradient methods, such as the Muon optimizer, modify gradient updates by preserving directional information while discarding scale, and have shown strong empirical performance in deep learning. We investigate the mechanisms…

In cold-start scenarios, the scarcity of collaborative signals for new items exacerbates the Matthew effect, which undermines platform diversity and remains a persistent challenge in real-world recommender systems. Existing methods…

Action Quality Assessment (AQA) evaluates diverse skills but models struggle with non-stationary data. We propose Continual AQA (CAQA) to refine models using sparse new data. Feature replay preserves memory without storing raw inputs.…

Rapid growth of high-dimensional datasets in fields such as single-cell RNA sequencing and spatial genomics has led to unprecedented opportunities for scientific discovery, but it also presents unique computational and statistical…

Feature attribution is essential for interpreting deep learning models, particularly in time-series domains such as healthcare, biometrics, and human-AI interaction. However, standard attribution methods, such as Integrated Gradients or…

The integration of contextual embeddings into the optimization processes of large language models is an advancement in natural language processing. The Context-Aware Neural Gradient Mapping framework introduces a dynamic gradient adjustment…

The real-world data distribution is essentially long-tailed, which poses great challenge to the deep model. In this work, we propose a new method, Gradual Balanced Loss and Adaptive Feature Generator (GLAG) to alleviate imbalance. GLAG…

Image inpainting aims at restoring missing regions of corrupted images, which has many applications such as image restoration and object removal. However, current GAN-based generative inpainting models do not explicitly exploit the…

Neural networks are becoming increasingly better at tasks that involve classifying and recognizing images. At the same time techniques intended to explain the network output have been proposed. One such technique is the Gradient-based Class…

Embedding parameterized optimization problems as layers into machine learning architectures serves as a powerful inductive bias. Training such architectures with stochastic gradient descent requires care, as degenerate derivatives of the…

Retrieval-augmented generation (RAG) equips large language models (LLMs) with reliable knowledge memory. To strengthen cross-text associations, recent research integrates graphs and hypergraphs into RAG to capture pairwise and multi-entity…

Gradient-based attribution methods can aid in the understanding of convolutional neural networks (CNNs). However, the redundancy of attribution features and the gradient saturation problem, which weaken the ability to identify significant…

Neural implicit fields have been a de facto standard in novel view synthesis. Recently, there exist some methods exploring fusing multiple modalities within a single field, aiming to share implicit features from different modalities to…

The Average Gradient Outer Product (AGOP) governs feature learning in neural networks: the Neural Feature Ansatz states that weight Gram matrices at each layer align with the corresponding AGOP matrices computed over the training…