Retrieval-augmented generation (RAG) has become a key technique in enhancing the capabilities of LLMs by incorporating external knowledge into their outputs. RAG methods enable LLMs to access additional information from external sources, such as web-based databases, scientific literature, or domain-specific corpora, which improves their performance in knowledge-intensive tasks. RAG systems can generate more contextually accurate… →
Multimodal Attributed Graphs (MMAGs) have received little attention despite their versatility in image generation. MMAGs represent relationships between entities with combinatorial complexity in a graph-structured manner. Nodes in the graph contain both image and text information. Compared to text or image conditioning models, graphs could be converted into better and more informative images. Graph2Image is… →
The problem that this research seeks to address lies in the inherent limitations of existing large language models (LLMs) when applied to formal theorem proving. Current models are often trained or fine-tuned on specific datasets, such as those focused on undergraduate-level mathematics, but struggle to generalize to more advanced mathematical domains. These limitations become more… →
Multimodal Situational Safety is a critical aspect that focuses on the model’s ability to interpret and respond safely to complex real-world scenarios involving visual and textual information. It ensures that Multimodal Large Language Models (MLLMs) can recognize and address potential risks inherent in their interactions. These models are designed to interact seamlessly with visual and… →
Generating accurate and aesthetically appealing visual texts in text-to-image generation models presents a significant challenge. While diffusion-based models have achieved success in creating diverse and high-quality images, they often struggle to produce legible and well-placed visual text. Common issues include misspellings, omitted words, and improper text alignment, particularly when generating non-English languages such as Chinese.… →
Information Retrieval (IR) systems for search and recommendations often utilize Learning-to-Rank (LTR) solutions to prioritize relevant items for user queries. These models heavily depend on user interaction features, such as clicks and engagement data, which are highly effective for ranking. However, this reliance presents significant challenges. User Interaction data can be noisy and sparse, especially… →
While writing the code for any program or algorithm, developers can struggle to fill gaps in incomplete code and often make mistakes while trying to fit new pieces into existing code snippets or structures. These challenges arise from the difficulty of fitting the latest code with the prior and following parts, especially when the broader… →
DeepSwap DeepSwap is an AI-based tool for anyone who wants to create convincing deepfake videos and images. It is super easy to create your content by refacing videos, pictures, memes, old movies, GIFs… You name it. The app has no content restrictions, so users can upload material of any content. Besides, you can get a 50%… →
Large language models (LLMs) have emerged as powerful tools capable of performing complex tasks beyond text generation, including reasoning, tool learning, and code generation. These advancements have sparked significant interest in developing LLM-based language agents to automate scientific discovery processes. Researchers are exploring the potential of these agents to revolutionise data-driven discovery workflows across various… →
In the rapidly evolving landscape of artificial intelligence, the quality and quantity of data play a pivotal role in determining the success of machine learning models. While real-world data provides a rich foundation for training, it often faces limitations such as scarcity, bias, and privacy concerns. These challenges can hinder the development of accurate and… →