Related papers: Correctness Learning: Deductive Verification Guide…
Biological agents learn and act intelligently in spite of a highly limited capacity to process and store information. Many real-world problems involve continuous control, which represents a difficult task for artificial intelligence agents.…
Recent AI trends seek to align AI models to learned human-centric objectives, such as personal preferences, utility, or societal values. Using standard preference elicitation methods, researchers and practitioners build models of human…
In general, recommendation can be viewed as a matching problem, i.e., match proper items for proper users. However, due to the huge semantic gap between users and items, it's almost impossible to directly match users and items in their…
As hardware and software systems have grown in complexity, formal methods have been indispensable tools for rigorously specifying acceptable behaviors, synthesizing programs to meet these specifications, and validating the correctness of…
Collaborative filtering (CF) is a successful approach commonly used by many recommender systems. Conventional CF-based methods use the ratings given to items by users as the sole source of information for learning to make recommendation.…
Generating accurate and calibrated confidence estimates is critical for deploying LLMs in high-stakes or user-facing applications, and remains an open challenge. Prior research has often framed confidence as a problem of eliciting a model's…
Professional fact-checkers rely on domain knowledge and deep contextual understanding to verify claims. Large language models (LLMs) and large reasoning models (LRMs) lack such grounding and primarily reason from available evidence alone,…
The deployment of pre-trained models (PTMs) has greatly advanced the field of continual learning (CL), enabling positive knowledge transfer and resilience to catastrophic forgetting. To sustain these advantages for sequentially arriving…
Metacognition is the concept of reasoning about an agent's own internal processes, and it has recently received renewed attention with respect to artificial intelligence (AI) and, more specifically, machine learning systems. This paper…
The wide-spread adoption of representation learning technologies in clinical decision making strongly emphasizes the need for characterizing model reliability and enabling rigorous introspection of model behavior. While the former need is…
Class-Incremental Learning aims to update a deep classifier to learn new categories while maintaining or improving its accuracy on previously observed classes. Common methods to prevent forgetting previously learned classes include…
Modern visual recognition models often display overconfidence due to their reliance on complex deep neural networks and one-hot target supervision, resulting in unreliable confidence scores that necessitate calibration. While current…
Self-supervised learning (SSL) has recently achieved great success in mining the user-item interactions for collaborative filtering. As a major paradigm, contrastive learning (CL) based SSL helps address data sparsity in Web platforms by…
The deployment of large-scale models, such as large language models (LLMs) and sophisticated image generation systems, incurs substantial costs due to their computational demands. To mitigate these costs and address challenges related to…
In this paper, we discuss learning algorithms and their importance in different types of applications which includes training to identify important patterns and features in a straightforward, easy-to-understand manner. We will review the…
While Vision-Language Models (VLMs) have shown remarkable abilities in visual and language reasoning tasks, they invariably generate flawed responses. Self-correction that instructs models to refine their outputs presents a promising…
Large Language Model (LLM) image recognition is a powerful tool for extracting data from images, but accuracy depends on providing sufficient cues in the prompt - requiring a domain expert for specialized tasks. We introduce Cue Learning…
In recent years, the rapid development of AI systems has brought about the benefits of intelligent services but also concerns about security and reliability. By fostering appropriate user reliance on an AI system, both complementary team…
Human-AI shared control allows human to interact and collaborate with AI to accomplish control tasks in complex environments. Previous Reinforcement Learning (RL) methods attempt the goal-conditioned design to achieve human-controllable…
The integration of artificial intelligence [AI] into clinical trials has revolutionized the process of drug development and personalized medicine. Among these advancements, deep learning and predictive modelling have emerged as…