Related papers: AI Model Modulation with Logits Redistribution

Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values. While recent approaches often rely on synthetic data generated by LLMs for scalability and…

Imitation Learning (IL) is an appealing approach to learn desirable autonomous behavior. However, directing IL to achieve arbitrary goals is difficult. In contrast, planning-based algorithms use dynamics models and reward functions to…

Artificial intelligence (AI) has emerged as a powerful tool for addressing complex and dynamic tasks in radio communication systems. Research in this area, however, focused on AI solutions for specific, limited conditions, hindering models…

Conventional approaches to building energy retrofit decision making suffer from limited generalizability and low interpretability, hindering adoption in diverse residential contexts. With the growth of Smart and Connected Communities,…

Autonomous intersection management (AIM) poses significant challenges due to the intricate nature of real-world traffic scenarios and the need for a highly expensive centralised server in charge of simultaneously controlling all the…

Automatic modulation classification (AMC) is of crucial importance for realizing wireless intelligence communications. Many deep learning based models especially convolution neural networks (CNNs) have been proposed for AMC. However, the…

The increasing capabilities of large generative models and their ever more widespread deployment have raised concerns about their reliability, safety, and potential misuse. To address these issues, recent works have proposed to control…

Rule-based adaptation is a foundational approach to self-adaptation, characterized by its human readability and rapid response. However, building high-performance and robust adaptation rules is often a challenge because it essentially…

Influence Maximization (IM) aims to maximize the number of people that become aware of a product by finding the `best' set of `seed' users to initiate the product advertisement. Unlike prior arts on static social networks containing fixed…

With more advanced natural language understanding and reasoning capabilities, large language model (LLM)-powered agents are increasingly developed in simulated environments to perform complex tasks, interact with other agents, and exhibit…

AI agents based on multimodal large language models (LLMs) are expected to revolutionize human-computer interaction and offer more personalized assistant services across various domains like healthcare, education, manufacturing, and…

Identifying wireless modulation schemes is essential for cognitive radio, but standard supervised models often degrade under distribution shift, and training domain-specific wireless foundation models from scratch is computationally…

An artificial intelligence (AI) model can be viewed as a function that maps inputs to outputs in high-dimensional spaces. Once designed and well trained, the AI model is applied for inference. However, even optimized AI models can produce…

Current transformer language models (LM) are large-scale models with billions of parameters. They have been shown to provide high performances on a variety of tasks but are also prone to shortcut learning and bias. Addressing such incorrect…

Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their…

Ensuring faithful interpretability in large language models is imperative for trustworthy and reliable AI. A key obstacle is self-repair, a phenomenon where networks compensate for reduced signal in one component by amplifying others,…

Contemporary artificial intelligence research has been organized around two dominant ambitions: productivity, which treats AI systems as tools for accelerating work and economic output, and alignment, which focuses on ensuring that…

With increased power and prevalence of AI systems, it is ever more critical that AI systems are designed to serve all, i.e., people with diverse values and perspectives. However, aligning models to serve pluralistic human values remains an…

With edge intelligence, AI models are increasingly pushed to the edge to serve ubiquitous users. However, due to the drift of model, data, and task, AI model deployed at the edge suffers from degraded accuracy in the inference serving…

The multi-objective alignment of Large Language Models (LLMs) is essential for ensuring foundational models conform to diverse human preferences. Current research in this field typically involves either multiple policies or multiple reward…