Related papers: Gmail Smart Compose: Real-Time Assisted Writing
Controlling the text generated by language models and customizing the content has been a long-standing challenge. Existing prompting techniques proposed in pursuit of providing control are task-specific and lack generality; this provides…
This paper develops an edge-device collaborative Generative Semantic Communications (Gen SemCom) framework leveraging pre-trained Multi-modal/Vision Language Models (M/VLMs) for ultra-low-rate semantic communication via textual prompts. The…
Commit Message Generation (CMG) approaches aim to automatically generate commit messages based on given code diffs, which facilitate collaboration among developers and play a critical role in Open-Source Software (OSS). Very recently, Large…
Customizing pre-trained text-to-image generation model has attracted massive research interest recently, due to its huge potential in real-world applications. Although existing methods are able to generate creative content for a novel…
Traditional recommendation systems suffer from inconsistency in multi-stage optimization objectives. Generative Recommendation (GR) mitigates them through an end-to-end framework; however, existing methods still rely on matching mechanisms…
Human communication is multimodal, with speech and gestures tightly coupled, yet most computational methods for generating speech and gestures synthesize them sequentially, weakening synchrony and prosody alignment. We introduce Gelina, a…
Existing AI Music composition tools are limited in generation duration, musical quality, and controllability. We introduce CoComposer, a multi-agent system that consists of five collaborating agents, each with a task based on the…
Prompt engineering is a challenging and important task due to the high sensitivity of Large Language Models (LLMs) to the given prompt and the inherent ambiguity of a textual task instruction. Automatic prompt engineering is essential to…
The automatic composition of web services refers to how services can be used in a complex and aggregate manner, to serve a specific and known functionality. Given a list of services described by the input and output parameters, and a…
This work is an introduction to the author's contributions to the SOC area, resulting from his PhD research activity. It focuses on the problem of automatically composing a desired service, given a set of available ones and a target…
Modern enterprise computing systems integrate numerous subsystems to resolve a common task by yielding emergent behavior. A widespread approach is using services implemented with Web technologies like REST or OpenAPI, which offer an…
Generative text-to-image models have gained great popularity among the public for their powerful capability to generate high-quality images based on natural language prompts. However, developing effective prompts for desired images can be…
We explore the potential for combining generative AI with grammar-based visualizations for biomedical data discovery. In our prototype, we use a multi-agent system to generate visualization specifications and apply filters. These…
Generative Recommendation has emerged as a promising paradigm, reformulating recommendation as a sequence-to-sequence generation task over hierarchical Semantic IDs. However, existing methods suffer from a critical issue we term Semantic…
Stickers are popularly used in messaging apps such as Hike to visually express a nuanced range of thoughts and utterances to convey exaggerated emotions. However, discovering the right sticker from a large and ever expanding pool of…
Mathematical programming is widely employed across various sectors - such as logistics, energy, and workforce planning - to model and solve industrial optimisation problems, but its use requires substantial domain expertise. Large language…
Prompting is central to interaction with AI systems, yet many users struggle to explore alternative directions, articulate creative intent, or understand how variations in prompts shape model outputs. We introduce prompt recommender systems…
In recent years, neural networks and other complex models have dominated recommender systems, often setting new benchmarks for state-of-the-art performance. Yet, despite these advancements, award-winning research has demonstrated that…
Today's image generation systems are capable of producing realistic and high-quality images. However, user prompts often contain ambiguities, making it difficult for these systems to interpret users' potential intentions. Consequently,…
Recent technological advances popularized the use of image generation among the general public. Crafting effective prompts can, however, be difficult for novice users. To tackle this challenge, we developed PromptMap, a new interaction…