Related papers: 3DAlign-DAER: Dynamic Attention Policy and Efficie…

Graph-based Retrieval-Augmented Generation (GraphRAG) frameworks face a trade-off between the comprehensiveness of global search and the efficiency of local search. Existing methods are often challenged by navigating large-scale…

Many recent approaches of passage retrieval are using dense embeddings generated from deep neural models, called "dense passage retrieval". The state-of-the-art end-to-end dense passage retrieval systems normally deploy a deep neural model…

High-definition 3D city maps enable city planning and change detection, which is essential for municipal compliance, map maintenance, and asset monitoring, including both built structures and urban greenery. Conventional Digital Surface…

Image-text matching is an important multi-modal task with massive applications. It tries to match the image and the text with similar semantic information. Existing approaches do not explicitly transform the different modalities into a…

Multimodal remote sensing data, including spectral and lidar or photogrammetry, is crucial for achieving satisfactory land-use / land-cover classification results in urban scenes. So far, most studies have been conducted in a 2D context.…

Modeling long sequences is crucial for various large-scale models; however, extending existing architectures to handle longer sequences presents significant technical and resource challenges. In this paper, we propose an efficient and…

Untrained Physics-based Deep Learning (DL) methods for digital holography have gained significant attention due to their benefits, such as not requiring an annotated training dataset, and providing interpretability since utilizing the…

Retrieval-Augmented Generation (RAG) systems rely heavily on the retrieval stage, particularly the coarse-ranking process. Existing coarse-ranking optimization approaches often struggle to balance domain-specific knowledge learning with…

While 3D Multi-modal Large Language Models (MLLMs) demonstrate remarkable scene understanding capabilities, their practical deployment faces critical challenges due to computational inefficiency. The key bottleneck stems from processing…

In recent years, attention mechanisms have been exploited in single image super-resolution (SISR), achieving impressive reconstruction results. However, these advancements are still limited by the reliance on simple training strategies and…

We investigate the temporal concatenation of sub-policies in Markov Decision Processes (MDP) with time-varying reward functions. We introduce General Dijkstra Search (GDS), and prove that globally optimal goal-reaching policies can be…

Calibrating deep learning models to yield uncertainty-aware predictions is crucial as deep neural networks get increasingly deployed in safety-critical applications. While existing post-hoc calibration methods achieve impressive results on…

The rapid evolution of intelligent document processing systems demands robust solutions that adapt to diverse domains without extensive retraining. Traditional methods often falter with variable document types, leading to poor performance.…

Automated machine learning (AutoML) usually involves several crucial components, such as Data Augmentation (DA) policy, Hyper-Parameter Optimization (HPO), and Neural Architecture Search (NAS). Although many strategies have been developed…

Parameter-efficient transfer learning (PETL) is a promising task, aiming to adapt the large-scale pre-trained model to downstream tasks with a relatively modest cost. However, current PETL methods struggle in compressing computational…

Processing 3D data efficiently has always been a challenge. Spatial operations on large-scale point clouds, stored as sparse data, require extra cost. Attracted by the success of transformers, researchers are using multi-head attention for…

Fine-tuning pre-trained neural network models has become a widely adopted approach across various domains. However, it can lead to the distortion of pre-trained feature extractors that already possess strong generalization capabilities.…

Multimodal learning seeks to integrate information across diverse sensory sources, yet current approaches struggle to balance cross-modal generalizability with modality-specific structure. Continuous (implicit) methods preserve fine-grained…

Existing alignment techniques for Large Language Models (LLMs), such as Direct Preference Optimization (DPO), typically treat the model as a monolithic entity, applying uniform optimization pressure across all layers. This approach…

We propose Diverse Restormer (DART), a novel image restoration method that effectively integrates information from various sources (long sequences, local and global regions, feature dimensions, and positional dimensions) to address…