Split learning is well known as a method for resolving data privacy concerns by training a model on distributed devices, thereby avoiding data sharing that rais...
Small and medium-sized enterprises (SMEs) in Iran increasingly leverage Telegram for sales, where real-time engagement is essential for conversion. However, dev...
Direct Preference Optimization (DPO) is a widely used reinforcement learning from human feedback (RLHF) method across various domains. Recent research has incre...
We study the online unweighted bipartite matching problem in the random arrival order model, with $n$ offline and $n$ online vertices, in the learning-augmented...
We present the Hierarchical AI-Meteorologist, an LLM-agent system that generates explainable weather reports using a hierarchical forecast reasoning and weather...
Unifying multimodal understanding, generation and reconstruction representation in a single tokenizer remains a key challenge in building unified models. Previo...
Novice and expert users have different systematic preferences in task-oriented dialogues. However, whether catering to these preferences actually improves user ...
Modern large language models become multimodal, analyzing various data formats like text and images. While fine-tuning is effective for adapting these multimoda...
Despite recent progress in multilingual speech processing, African languages remain under-represented in both research and deployed systems, particularly when i...
In contemporary retail, the variety of products available (e.g. clothing, groceries, cosmetics, frozen goods) make it difficult to predict the demand, prevent s...
Program synthesis is the process of generating a computer program following a set of specifications, such as a set of input-output examples. It can be modeled a...
Knowledge-enhanced text generation aims to enhance the quality of generated text by utilizing internal or external knowledge sources. While language models have...
