相关论文: AiR: Attention with Reasoning Capability

This paper is a contribution towards interpretability of the deep learning models in different applications of time-series. We propose a temporal attention layer that is capable of selecting the relevant information to perform various…

Optimizing human-AI interaction requires users to reflect on their own performance critically. Our paper examines whether people using AI to complete tasks can accurately monitor how well they perform. In Study 1, participants (N = 246)…

Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal…

Existing multimodal retrieval benchmarks largely emphasize semantic matching on daily-life images and offer limited diagnostics of professional knowledge and complex reasoning. To address this gap, we introduce ARK, a benchmark designed to…

Attention is a powerful and ubiquitous mechanism for allowing neural models to focus on particular salient pieces of information by taking their weighted average when making predictions. In particular, multi-headed attention is a driving…

Evaluating AI-generated reviews by verdict agreement is widely recognized as insufficient, yet current alternatives rarely audit which concerns a system identifies, how it prioritizes them, or whether those priorities align with the review…

Attention is a key factor for successful learning, with research indicating strong associations between (in)attention and learning outcomes. This dissertation advanced the field by focusing on the automated detection of attention-related…

Effective financial reasoning demands not only textual understanding but also the ability to interpret complex visual data such as charts, tables, and trend graphs. This paper introduces a new benchmark designed to evaluate how well AI…

We propose Self-Supervised Implicit Attention (SSIA), a new approach that adaptively guides deep neural network models to gain attention by exploiting the properties of the models themselves. SSIA is a novel attention mechanism that does…

Real-world artificial intelligence (AI) systems are increasingly required to operate autonomously in dynamic, uncertain, and continuously changing environments. However, most existing AI models rely on predefined objectives, static training…

The human capability to reason about one domain by using knowledge of other domains has been researched for more than 50 years, but models that are formally sound and predict cognitive process are sparse. We propose a formally sound method…

While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their problem-solving abilities depend on the context and textual formatting. We introduce the Robust Reasoning Benchmark (RRB), a pipeline of…

Current Artificial Intelligence (AI) methods, most based on deep learning, have facilitated progress in several fields, including computer vision and natural language understanding. The progress of these AI methods is measured using…

Visual Commonsense Reasoning (VCR) remains a significant yet challenging research problem in the realm of visual reasoning. A VCR model generally aims at answering a textual question regarding an image, followed by the rationale prediction…

Real-world scenarios demand reasoning about process, more than final outcome prediction, to discover latent causal chains and better understand complex systems. It requires the learning algorithms to offer both accurate predictions and…

ADHD is being recognized as a diagnosis which persists into adulthood impacting economic, occupational, and educational outcomes. There is an increased need to accurately diagnose and recommend interventions for this population. One…

Attention mechanism has been extensively integrated within mainstream neural network architectures, such as Transformers and graph attention networks. Yet, its underlying working principles remain somewhat elusive. What is its essence? Are…

Recent thinking models solve complex reasoning tasks by scaling test-time compute, but this scaling must be allocated in line with task difficulty. On one hand, short reasoning (underthinking) leads to errors on harder problems that require…

With the emergence of advanced reasoning models like OpenAI o3 and DeepSeek-R1, large language models (LLMs) have demonstrated remarkable reasoning capabilities. However, their ability to perform rigorous logical reasoning remains an open…

In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire this capability, models must learn when and how to use external…