Related papers: Sub-method, partial behavioral reflection with Ref…
Today, most large-scale conversational AI agents (e.g. Alexa, Siri, or Google Assistant) are built using manually annotated data to train the different components of the system. Typically, the accuracy of the ML models in these components…
Long chain-of-thought (CoT) reasoning improves large vision--language models, but visual information often fades during generation, limiting long-horizon multimodal reasoning. Existing methods either re-inject vision at inference or train…
Software is now ubiquitous and involved in complex interactions with the human users and the physical world in so-called cyber-physical systems where the management of time is a major issue. Separation of concerns is a key asset in the…
Making high-stakes personal decisions involves cognitive, emotional, and intuitive processes, and individuals differ in how they allocate attention across these modes. Integration of these processes has shown to benefit decision making.…
Programs have to be designed in such a way as to make them looking good and being handy for all users. Adaptive interface, with all the numerous achievements throughout 30 years of its history, contains and in reality is based on one…
This work focuses on the setting of dynamic regret in the context of online learning with full information. In particular, we analyze regret bounds with respect to the temporal variability of the loss functions. By assuming that the…
Most machine learning and data analytics applications, including performance engineering in software systems, require a large number of annotations and labelled data, which might not be available in advance. Acquiring annotations often…
Software undergoes constant changes to support new requirements, address bugs, enhance performance, and ensure maintainability. Thus, developers spend a great portion of their workday trying to understand and review the code changes of…
Human-annotated textual explanations are becoming increasingly important in Explainable Natural Language Processing. Rationale extraction aims to provide faithful (i.e., reflective of the behavior of the model) and plausible (i.e.,…
Designing seamless, frictionless user experiences has long been a dominant trend in both applied behavioral science and artificial intelligence (AI), in which the goal of making desirable actions easy and efficient informs efforts to…
The visible orientation of human eyes creates some transparency about people's spatial attention and other mental states. This leads to a dual role of the eyes as a means of sensing and communication. Accordingly, artificial eye models are…
Reflection is an often addressed design goal in Human-Computer Interaction (HCI) research. An increasing number of artefacts for reflection have been developed in recent years. However, evaluating if and how an interactive technology helps…
We consider the problem of online control of systems with time-varying linear dynamics. This is a general formulation that is motivated by the use of local linearization in control of nonlinear dynamical systems. To state meaningful…
Referring expression comprehension (REF) aims at identifying a particular object in a scene by a natural language expression. It requires joint reasoning over the textual and visual domains to solve the problem. Some popular referring…
This paper explores the concept of reflexive actuation, examining how robots may leverage both internal and external stimuli to trigger changes in the motion, performance, or physical characteristics of the robot, such as its size, shape,…
Understanding the behaviour of a system's API can be hard. Giving users access to relevant examples of how an API behaves has been shown to make this easier for them. In addition, such examples can be used to verify expected behaviour or…
Current RLHF methods such as PPO and DPO typically reduce human preferences to binary labels, which are costly to obtain and too coarse to reflect individual variation. We observe that expressions of satisfaction and dissatisfaction follow…
Recently, large language models (LLMs) have achieved significant progress in automated code generation. Despite their strong instruction-following capabilities, these models frequently struggled to align with user intent in coding…
Motivated by the challenge of nonstationarity in sequential decision making, we study Online Convex Optimization (OCO) under the coupling of two problem structures: the domain is unbounded, and the comparator sequence $u_1,\ldots,u_T$ is…
Background: Using feature toggles is a technique that allows developers to either turn a feature on or off with a variable in a conditional statement. Feature toggles are increasingly used by software companies to facilitate continuous…