Related papers: SNEAK: Faster Interactive Search-based SE
Deep search agents, which aim to answer complex questions requiring reasoning across multiple documents, can significantly speed up the information-seeking process. Collecting human annotations for this application is prohibitively…
The core of everyday tasks like reading and driving is active object recognition. Attempts to model such tasks are currently stymied by the inability to incorporate time. People show a flexible tradeoff between speed and accuracy and this…
Information processing tasks involve complex cognitive mechanisms that are shaped by various factors, including individual goals, prior experience, and system environments. Understanding such behaviors requires a sophisticated and…
Typically, search engines provide query suggestions to assist users in the search process. Query suggestions are very important for improving users search experience. However, most query suggestions are based on the user's search logs, and…
Information seeking conversations between users and Conversational Search Agents (CSAs) consist of multiple turns of interaction. While users initiate a search session, ideally a CSA should sometimes take the lead in the conversation by…
Learning-to-rank (LTR) is a set of supervised machine learning algorithms that aim at generating optimal ranking order over a list of items. A lot of ranking models have been studied during the past decades. And most of them treat each…
t-Distributed Stochastic Neighbor Embedding (t-SNE) is one of the most widely used dimensionality reduction methods for data visualization, but it has a perplexity hyperparameter that requires manual selection. In practice, proper tuning of…
Test-time compute scaling has emerged as a powerful paradigm for enhancing mathematical reasoning in large language models (LLMs) by allocating additional computational resources during inference. However, current methods employ uniform…
It is not accurate to make recommendations only based one single current session. Therefore, multi-session-based recommendation(MSBR) is a solution for the problem. Compared with the previous MSBR models, we have made three improvements in…
The merging of human intelligence and artificial intelligence has long been a subject of interest in both science fiction and academia. In this paper, we introduce a novel concept in Human-AI interaction called Symbiotic Artificial…
Human vision incorporates non-uniform resolution retina, efficient eye movement strategy, and spiking neural network (SNN) to balance the requirements in visual field size, visual resolution, energy cost, and inference latency. These…
Screening is a time-consuming and labour-intensive yet required task for medical systematic reviews, as tens of thousands of studies often need to be screened. Prioritising relevant studies to be screened allows downstream systematic review…
The study of behavioral and social dimensions of software engineering (SE) tasks characterizes behavioral software engineering (BSE);however, the increasing significance of human-AI collaboration (HAIC) brings new directions in BSE by…
Neural Architecture Search has achieved state-of-the-art performance in a variety of tasks, out-performing human-designed networks. However, many assumptions, that require human definition, related with the problems being solved or the…
State-of-the-art reasoning LLMs are powerful problem solvers, but they still occasionally make mistakes. However, adopting AI models in risk-sensitive domains often requires error rates near 0%. To address this gap, we propose collaboration…
AI tools to support real world decision making must be able to build simulation models that inform their recommendations and render them interpretable. Tools that can automate aspects of modeling practice must complement human expertise,…
Through our four years experiments on students' Scrum based agile software development (ASD) process, we have gained deep understanding into the human factors of agile methodology. We designed an agile project management tool - the HASE…
A large class of data questions can be modeled as identifying important slices of data driven by user defined metrics. This paper presents TRACE, a Time-Relational Approximate Cubing Engine that enables interactive analysis on such slices…
The collaborative ranking problem has been an important open research question as most recommendation problems can be naturally formulated as ranking problems. While much of collaborative ranking methodology assumes static ranking data, the…
Optimization of experimental materials synthesis and characterization through active learning methods has been growing over the last decade, with examples ranging from measurements of diffraction on combinatorial alloys at synchrotrons, to…