Related papers: Circuit Representation Learning with Masked Gate M…

This paper introduces a novel approach to efficiently feeding knowledge to language models (LLMs) during prediction by integrating retrieval and generation processes within a unified framework. While the Retrieval-Augmented Generation (RAG)…

Molecular representation learning plays a crucial role in various downstream tasks, such as molecular property prediction and drug design. To accurately represent molecules, Graph Neural Networks (GNNs) and Graph Transformers (GTs) have…

Multimodal embeddings are widely used in downstream tasks such as multimodal retrieval, enabling alignment of interleaved modalities in a shared representation space. While recent studies show that Multimodal Large Language Models (MLLMs)…

The classification performance of the random vector functional link (RVFL), a randomized neural network, has been widely acknowledged. However, due to its shallow learning nature, RVFL often fails to consider all the relevant information…

We present Entropic Mutual-Information Geometry Large-Language Model Alignment (ENIGMA), a novel approach to Large-Language Model (LLM) training that jointly improves reasoning, alignment and robustness by treating an organisation's…

Molecular graph representation learning is widely used in chemical and biomedical research. While pre-trained 2D graph encoders have demonstrated strong performance, they overlook the rich molecular domain knowledge associated with…

Large Language Models (LLMs) are increasingly used for various tasks with graph structures. Though LLMs can process graph information in a textual format, they overlook the rich vision modality, which is an intuitive way for humans to…

We challenge black-box purely deep neural approaches for molecules and graph generation, which are limited in controllability and lack formal guarantees. We introduce Neuro-Symbolic Graph Generative Modeling (NSGGM), a neurosymbolic…

Code generation has emerged as a critical research area at the intersection of Software Engineering (SE) and Artificial Intelligence (AI), attracting significant attention from both academia and industry. Within this broader landscape,…

Contrastive learning has been widely applied to graph representation learning, where the view generators play a vital role in generating effective contrastive samples. Most of the existing contrastive learning methods employ pre-defined…

Graph representation learning methods are highly effective in handling complex non-Euclidean data by capturing intricate relationships and features within graph structures. However, traditional methods face challenges when dealing with…

Masking strategies commonly employed in natural language processing are still underexplored in vision tasks such as concept learning, where conventional methods typically rely on full images. However, using masked images diversifies…

Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction…

Most existing 3D referring expression segmentation (3DRES) methods rely on dense, high-quality point clouds, while real-world agents such as robots and mobile phones operate with only a few sparse RGB views and strict latency constraints.…

Multimodal Knowledge Graphs (MMKGs), which represent explicit knowledge across multiple modalities, play a pivotal role by complementing the implicit knowledge of Multimodal Large Language Models (MLLMs) and enabling more grounded reasoning…

Multimodal Large Language Models (MLLMs) have achieved SOTA performance in various visual language tasks by fusing the visual representations with LLMs leveraging some visual adapters. In this paper, we first establish that adapters using…

Vision-and-Language Navigation (VLN) requires an embodied agent to traverse complex environments by following natural language instructions, demanding accurate alignment between visual observations and linguistic guidance. Despite recent…

Inspired by the masked language modeling (MLM) in natural language processing tasks, the masked image modeling (MIM) has been recognized as a strong self-supervised pre-training method in computer vision. However, the high random mask ratio…

Polygon representation learning is essential for diverse applications, encompassing tasks such as shape coding, building pattern classification, and geographic question answering. While recent years have seen considerable advancements in…

How to produce expressive molecular representations is a fundamental challenge in AI-driven drug discovery. Graph neural network (GNN) has emerged as a powerful technique for modeling molecular data. However, previous supervised approaches…