Related papers: REX: Reasoning-aware and Grounded Explanation
Visual Question Answering (VQA) is a challenging task of predicting the answer to a question about the content of an image. Prior works directly evaluate the answering models by simply calculating the accuracy of predicted answers. However,…
Large Language Models have demonstrated remarkable reasoning capability in complex textual tasks. However, multimodal reasoning, which requires integrating visual and textual information, remains a significant challenge. Existing…
While many vision-language models (VLMs) are developed to answer well-defined, straightforward questions with highly specified targets, as in most benchmarks, they often struggle in practice with complex open-ended tasks, which usually…
The ability to navigate robots with natural language instructions in an unknown environment is a crucial step for achieving embodied artificial intelligence (AI). With the improving performance of deep neural models proposed in the field of…
The field of "explainable artificial intelligence" (XAI) seemingly addresses the desire that decisions of machine learning systems should be human-understandable. However, in its current state, XAI itself needs scrutiny. Popular methods…
EXplainable Artificial Intelligence (XAI) is a vibrant research topic in the artificial intelligence community, with growing interest across methods and domains. Much has been written about the subject, yet XAI still lacks shared…
Aligning machine representations with human understanding is key to improving interpretability of machine learning (ML) models. When classifying a new image, humans often explain their decisions by decomposing the image into concepts and…
Visual grounding is the task of localising image regions from natural language queries and is critical for reasoning capable Graphical User Interface agents. Many existing methods rely on massive, noisy synthetic datasets. This work…
Deep neural perception and control networks have become key components of self-driving vehicles. User acceptance is likely to benefit from easy-to-interpret textual explanations which allow end-users to understand what triggered a…
Vision-Language Models (VLMs) excel at many multimodal tasks, yet they frequently struggle with tasks requiring precise understanding and handling of fine-grained visual elements. This is mainly due to information loss during image encoding…
Research in artificial intelligence (AI)-assisted decision-making is experiencing tremendous growth with a constantly rising number of studies evaluating the effect of AI with and without techniques from the field of explainable AI (XAI) on…
Recognition and reasoning are two pillars of visual understanding. However, these tasks have an imbalance in focus; whereas recent advances in neural networks have shown strong empirical performance in visual recognition, there has been…
Natural language explanations play a critical role in establishing trust and acceptance of automated vehicles (AVs), yet existing approaches lack systematic frameworks for analysing how humans linguistically construct driving rationales…
The use of Artificial Intelligence (AI) models in real-world and high-risk applications has intensified the discussion about their trustworthiness and ethical usage, from both a technical and a legislative perspective. The field of…
Large Language Models (LLMs) increasingly show reasoning rationales alongside their answers, turning "reasoning" into a user-interface element. While step-by-step rationales are typically associated with model performance, how they…
This is an integrative review that address the question, "What makes for a good explanation?" with reference to AI systems. Pertinent literatures are vast. Thus, this review is necessarily selective. That said, most of the key concepts and…
Recent advancements in Vision Transformers (ViT) have demonstrated exceptional results in various visual recognition tasks, owing to their ability to capture long-range dependencies in images through self-attention mechanisms. However, the…
While multimodal AI systems (models jointly trained on heterogeneous data types such as text, time series, graphs, and images) have become ubiquitous and achieved remarkable performance across high-stakes applications, transparent and…
Multimodal reasoning remains a fundamental challenge in artificial intelligence. Despite substantial advances in text-based reasoning, even state-of-the-art models such as GPT-o3 struggle to maintain strong performance in multimodal…
Transformer-based architectures have recently demonstrated remarkable performance in the Visual Question Answering (VQA) task. However, such models are likely to disregard crucial visual cues and often rely on multimodal shortcuts and…