Co-designing with families for environmental sustainability relies on participatory imagination, yet habitual family roles and uneven participation, especially between adults and young children, often constrain it. A second challenge is continuity: workshop relationships and embodied ways of working do not easily survive into the final design, where artefacts travel more readily than roles or interactional dynamics. We report on a nationally toured mixed-reality installation developed through applied-theatre-led co-design with families. Across three workshops and user testing, applied theatre methods supported families to co-create narratives, artefacts, and interactional roles that shaped the public event. We show how theatrical co-design can rebalance child–adult participation through playful status shifts, and how selected workshop dynamics can be re-staged within a public mixed-reality installation. We contribute a theatrical account of participatory design in which designers work not only with artefacts and ideas, but with roles, rhythms, authority, and the social conditions that support collective imagination.

Taylor Sorensen, Pushkar Mishra, Roma Patel, Michael Henry Tessler, Michiel A. Bakker, Georgina Evans, Iason Gabriel, Noah Goodman, Verena Rieser. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Current text-to-image (T2I) models often fail to account for diverse human experiences, leading to misaligned systems. We advocate for pluralism in AI alignment, where an AI understands and is steerable towards diverse, and often conflicting, human values. Our work provides three core contributions to achieve this in T2I models. First, we introduce a novel dataset for Diverse Intersectional Visual Evaluation (DIVE) -- the first multimodal dataset for pluralistic alignment. It enables deep alignment to diverse safety perspectives through a large pool of demographically intersectional human raters who provided extensive feedback across 1000 prompts, with high replication, capturing nuanced safety perceptions. Second, we empirically confirm demographics as a crucial proxy for diverse viewpoints in this domain, revealing significant, context-dependent differences in harm perception that diverge from conventional evaluations. Finally, we discuss implications for building aligned T2I models, including efficient data collection strategies, LLM judgment capabilities, and model steerability towards diverse perspectives. This research offers foundational tools for more equitable and aligned T2I systems.Content Warning: The paper includes sensitive content that may be harmful.

We introduce RLang, a domain-specific language (DSL) for communicating domain knowledge to an RL agent. Unlike existing RL DSLs that ground to $\textit{single}$ elements of a decision-making formalism (e.g., the reward function or policy), RLang can specify information about every element of a Markov decision process. We define precise syntax and grounding semantics for RLang, and provide a parser that grounds RLang programs to an algorithm-agnostic $\textit{partial}$ world model and policy that can be exploited by an RL agent. We provide a series of example RLang programs demonstrating how different RL methods can exploit the resulting knowledge, encompassing model-free and model-based tabular algorithms, policy gradient and value-based methods, hierarchical approaches, and deep methods.

It is imperative that robots can understand natural language commands issued by humans. Such commands typically contain verbs that signify what action should be performed on a given object and that are applicable to many objects. We propose a method for generalizing manipulation skills to novel objects using verbs. Our method learns a probabilistic classifier that determines whether a given object trajectory can be described by a specific verb. We show that this classifier accurately generalizes to novel object categories with an average accuracy of 76.69% across 13 object categories and 14 verbs. We then perform policy search over the object kinematics to find an object trajectory that maximizes classifier prediction for a given verb. Our method allows a robot to generate a trajectory for a novel object based on a verb, which can then be used as input to a motion planner. We show that our model can generate trajectories that are usable for executing five verb commands applied to novel instances of two different object categories on a real robot.

Recent work on using natural language to specify commands to robots has grounded that language to LTL. However, mapping natural language task specifications to LTL task specifications using language models require probability distributions over finite vocabulary. Existing state-of-the-art methods have extended this finite vocabulary to include unseen terms from the input sequence to improve output generalization. However, novel out-of-vocabulary atomic propositions cannot be generated using these methods. To overcome this, we introduce an intermediate contextual query representation which can be learned from single positive task specification examples, associating a contextual query with an LTL template. We demonstrate that this intermediate representation allows for generalization over unseen object references, assuming accurate groundings are available. We compare our method of mapping natural language task specifications to intermediate contextual queries against state-of-the-art CopyNet models capable of translating natural language to LTL, by evaluating whether correct LTL for manipulation and navigation task specifications can be output, and show that our method outperforms the CopyNet model on unseen object references. We demonstrate that the grounded LTL our method outputs can be used for planning in a simulated OO-MDP environment. Finally, we discuss some common failure modes encountered when translating natural language task specifications to grounded LTL.

People use language in subtle and nuanced ways to convey their beliefs.For instance, saying claimed instead of said casts doubt on the truthfulness of the underlying proposition, thus representing the author's opinion on the matter.Several works have identified classes of words that induce such framing effects.In this paper, we test whether generative language models are sensitive to these linguistic cues.In particular, we test whether prompts that contain linguistic markers of author bias (e.g., hedges, implicatives, subjective intensifiers, assertives) influence the distribution of the generated text.Although these framing effects are subtle and stylistic, we find qualitative and quantitative evidence that they lead to measurable style and topic differences in the generated text, leading to language that is more polarised (both positively and negatively) and, anecdotally, appears more skewed towards controversial entities and events.

Roma Patel, Marta Garnelo, Ian Gemp, Chris Dyer, Yoram Bachrach. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

We introduce Room-Across-Room (RxR), a new Vision-and-Language Navigation (VLN) dataset.RxR is multilingual (English, Hindi, and Telugu) and larger (more paths and instructions) than other VLN datasets.It emphasizes the role of language in VLN by addressing known biases in paths and eliciting more references to visible entities.Furthermore, each word in an instruction is time-aligned to the virtual poses of instruction creators and validators.We establish baseline scores for monolingual and multilingual settings and multitask learning when including Room-to-Room annotations (Anderson et al., 2018b).We also provide results for a model that learns from synchronized pose traces by focusing only on portions of the panorama attended to in human demonstrations.The size, scope and detail of RxR dramatically expands the frontier for research on embodied language agents in simulated, photo-realistic environments.

Alex Wang, Jan Hula, Patrick Xia, Raghavendra Pappagari, R. Thomas McCoy, Roma Patel, Najoung Kim, Ian Tenney, Yinghui Huang, Katherin Yu, Shuning Jin, Berlin Chen, Benjamin Van Durme, Edouard Grave, Ellie Pavlick, Samuel R. Bowman. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019.

Interactive mirrors, typically combining semi-transparent mirrors, digital screens and interaction mechanisms have been developed for a variety of application areas. Drawing on existing techniques to create interactive mirror spaces, we investigated their performative qualities through artistic discovery and collaborative prototyping. We document a linked set of design explorations and two public, site-specific experiences that brought together artists, communities, and HCI researchers. We illustrate the abstracted interactive mirror space that practitioners in the performance art, theatre and museum sectors can work with. In turn, we also discuss six performative design strategies concerning the use of physical context, movement and narrative that HCI researchers who wish to deploy interactive mirrors in more mainstream settings need to consider.

We present a corpus of 5,000 richly annotated abstracts of medical articles describing clinical randomized controlled trials. Annotations include demarcations of text spans that describe the Patient population enrolled, the Interventions studied and to what they were Compared, and the Outcomes measured (the 'PICO' elements). These spans are further annotated at a more granular level, e.g., individual interventions within them are marked and mapped onto a structured medical vocabulary. We acquired annotations from a diverse set of workers with varying levels of expertise and cost. We describe our data collection process and the corpus itself in detail. We then outline a set of challenging NLP tasks that would aid searching of the medical literature and the practice of evidence-based medicine.

The convergence of theatre and digital technologies can play a valuable role in theatre for early years, but, how an audience of under-5's experiences and engages with these spaces is largely unexplored. We present an interactive performance installation and demonstrate how concepts from early years practice, in particular schemas, children's repeated play patterns, can be used as a design framework. We integrated sensors and microcontrollers into objects, puppets, and scenography and invited eight groups of very young children and their grownups to explore the performance. We discuss how schemas useful as a design and analysis tool in TEY, how schemas need to be expanded to include multi-sensory interactions with hybrid physical-digital objects, and how designers need to consider the roles of adults who scaffold interaction between very young children and their surroundings.