Related papers: HyMap: eliciting hypotheses in early-stage softwar…
The rapid evolution of artificial intelligence has led to expectations of transformative impact on science, yet current systems remain fundamentally limited in enabling genuine scientific discovery. This perspective contends that progress…
Recent advancements in large language models (LLMs) underscore the need for stronger reasoning capabilities to solve complex problems effectively. While Chain-of-Thought (CoT) reasoning has been a step forward, it remains insufficient for…
A consistent theme in software experimentation at Microsoft has been solving problems of experimentation at scale for a diverse set of products. Running experiments at scale (i.e., many experiments on many users) has become state of the art…
The rise of generative large language models (LLMs) has opened new opportunities for automating knowledge representation through concept maps, a long-standing pedagogical tool valued for fostering meaningful learning and higher-order…
In high throughput settings we inspect a great many candidate variables (e.g., genes) searching for associations with a primary variable (e.g., a phenotype). High throughput hypothesis testing can be made difficult by the presence of…
Human reasoning is grounded in an ability to identify highly abstract commonalities governing superficially dissimilar visual inputs. Recent efforts to develop algorithms with this capacity have largely focused on approaches that require…
The human ability to learn rules and solve problems has been a central concern of cognitive science research since the field's earliest days. But we do not just follow rules and solve problems given to us by others: we modify those rules,…
In the early stages of engineering design, it is essential to know how a product behaves, especially how it moves. As designers must keep adjusting the motion until it meets the intended requirements, this process is often repetitive and…
Generative AI has democratized content creation, but popular chatbot-based interfaces often prioritize execution, generating fully rendered artifacts right away. This issue can lead to premature convergence and design fixation, where users…
As AI technology is increasingly applied to high-impact, high-risk domains, there have been a number of new methods aimed at making AI models more human interpretable. Despite the recent growth of interpretability work, there is a lack of…
Vectorized High-Definition (HD) map construction requires predictions of the category and point coordinates of map elements (e.g. road boundary, lane divider, pedestrian crossing, etc.). State-of-the-art methods are mainly based on…
Current AI-assisted innovation systems typically apply a single ideation methodology (such as TRIZ or Design Thinking) using sequential prompt-based workflows that do not preserve intermediate reasoning structure. As a result, insights…
To make machines better understand sentiments, research needs to move from polarity identification to understanding the reasons that underlie the expression of sentiment. Categorizing the goals or needs of humans is one way to explain the…
Process maps provide a high-level overview of an organisation's business processes. While used for many years in different shapes and forms, there is little shared understanding of the concept and its relationship to enterprise…
Multimodal large language models (MLLMs) have demonstrated significant progress in semantic scene understanding and text-image alignment, with reasoning variants enhancing performance on more complex tasks involving mathematics and logic.…
Any act of problem-solving combines prior knowledge, local search, and a third element that is less often discussed: the extraction of information from search to update understanding. I propose a model of mathematical problem-solving as a…
Concept discovery is one of the open problems in the interpretability literature that is important for bridging the gap between non-deep learning experts and model end-users. Among current formulations, concepts defines them by as a…
Large-scale electrification is vital to addressing the climate crisis, but several scientific and technological challenges remain to fully electrify both the chemical industry and transportation. In both of these areas, new electrochemical…
Attribution methods, which employ heatmaps to identify the most influential regions of an image that impact model decisions, have gained widespread popularity as a type of explainability method. However, recent research has exposed the…
Generative AI, with its tendency to "hallucinate" incorrect results, may pose a risk to knowledge work by introducing errors. On the other hand, it may also provide unprecedented opportunities for users, particularly non-experts, to learn…