This paper presents a novel generative framework for learning shared latent representations across multimodal data. Many advanced multimodal methods focus on capturing all combinations of modality-specific details across inputs, which can inadvertently obscure the high-level semantic concepts that are shared across modalities. Notably, Multimodal VAEs with low-dimensional latent variables are designed to capture shared representations, enabling various tasks such as joint multimodal synthesis and cross-modal inference. However, multimodal VAEs often struggle to design expressive joint variational posteriors and suffer from low-quality synthesis. In this work, ShaLa addresses these challenges by integrating a novel architectural inference model and a second-stage expressive diffusion prior, which not only facilitates effective inference of shared latent representation but also significantly improves the quality of downstream multimodal synthesis. We validate ShaLa extensively across multiple benchmarks, demonstrating superior coherence and synthesis quality compared to state-of-the-art multimodal VAEs. Furthermore, ShaLa scales to many more modalities while prior multimodal VAEs have fallen short in capturing the increasing complexity of the shared latent space.

Generative AI enables designers to more broadly and rapidly explore design spaces. However, the sheer scale at which designs can be generated makes it difficult to identify which generated concepts deserve further attention. To support this identification process, we explore pupillometry—specifically pupil dilation—as a support signal for design evaluation. We conducted a study with 40 participants who viewed AI-generated bicycle designs while wearing eye tracking glasses to measure pupil dilation and rated designs on perceived surprise, valence, and feasibility.

Text-to-Image (T2I) Diffusion Models have achieved remarkable performance in generating high quality images. However, enabling precise control of continuous attributes, especially multiple attributes simultaneously, in a new domain (e.g., numeric values like eye openness or car width) with text-only guidance remains a significant challenge. To address this, we introduce the Attribute (Att) Adapter, a novel plug-and-play module designed to enable fine-grained, multi-attributes control in pretrained diffusion models. Our approach learns a single control adapter from a set of sample images that can be unpaired and contain multiple visual attributes. The Att-Adapter leverages the decoupled cross attention module to naturally harmonize the multiple domain attributes with text conditioning. We further introduce Conditional Variational Autoencoder (CVAE) to the Att-Adapter to mitigate overfitting, matching the diverse nature of the visual world. Evaluations on two public datasets show that Att-Adapter outperforms all LoRA-based baselines in controlling continuous attributes. Additionally, our method enables a broader control range and also improves disentanglement across multiple attributes, surpassing StyleGAN-based techniques. Notably, Att-Adapter is flexible, requiring no paired synthetic data for training, and is easily scalable to multiple attributes within a single model.

Narrative story generation has gained emerging interest in the field of large language models. The present paper aims to compare stories generated by an LLM only (non-interleaved) with those generated by interleaving human-generated and LLM-generated text (interleaved). The study’s hypothesis is that interleaved stories would perform better than non-interleaved stories. To verify this hypothesis, we conducted two tests with roughly 500 participants each. Participants were asked to rate stories of each type, including an overall score or preference and four facets—logical soundness, plausibility, understandability, and novelty. Our findings indicate that interleaved stories were in fact less preferred than non-interleaved stories. The result has implications for the design and implementation of our story generators. This study contributes new insights into the potential uses and restrictions of interleaved and non-interleaved systems regarding generating narrative stories, which may help to improve the performance of such story generators.

Our research aims at developing intelligent systems to reduce the transportation-related energy expenditure of a large city by influencing individual behavior. We introduce Copter - an intelligent travel assistant that evaluates multi-modal travel alternatives to find a plan that is acceptable to a person given their context and preferences. We propose a formulation for acceptable planning that brings together ideas from AI, machine learning, and economics. This formulation has been incorporated in Copter producing acceptable plans in real-time. We adopt a novel empirical evaluation framework that combines human decision data with high-fidelity simulation to demonstrate a 4% energy reduction and 20% delay reduction in a realistic deployment scenario in Los Angeles, California, USA.

Our research aims at developing intelligent systems to reduce the transportation-related energy expenditure of a large city by influencing individual behavior. We introduce Copter - an intelligent travel assistant that evaluates multi-modal travel alternatives to find a plan that is acceptable to a person given their context and preferences. We propose a formulation for acceptable planning that brings together ideas from AI, machine learning, and economics. This formulation has been incorporated in Copter that produces acceptable plans in real-time. We adopt a novel empirical evaluation framework that combines human decision data with a high fidelity multi-modal transportation simulation to demonstrate a 4% energy reduction and 20% delay reduction in a realistic deployment scenario in Los Angeles, California, USA. This article is part of the special track on AI and Society.

This paper presents an approach to applying model-based diagnosis to the task of interpreting in- formation from a wide variety of sources: text, video, meta-data, audio, etc. Much of the information contained in the sources is contradictory, incomplete, purposely deceptive or biased. People make critical decisions based on such murky information. By automating the construction of alternatives, we can design systems that support intelligence analysts and ordinary citizens in understanding the world. We have developed a preliminary version of our HCDX tool (hypothesis construction through diagnosis). We plan to distribute this tool as open source.

Qualitative reasoning can play an important role in early stage design. Currently, engineers explore the design space using simulation models built in languages such as Modelica. To make qualitative reasoning useful to them, designs specified in their languages must be translated into a qualitative modeling language for analysis. The contribution of this paper is a sound and effective mapping between Modelica and qualitative reasoning. To achieve a sound mapping, we extend envisioning, the process of generating all relevant qualitative behaviors, to support Modelica's declarative events. For an effective mapping, we identify three classes of additional constraints that should be inferred from the Modelica representation thereby exponentially reducing the number of unrealizable trajectories. We support this contribution with examples and a case study.

To operate autonomously in complex environments, an agent must monitor its environment and determine how to respond to new situations. To be considered intelligent, an agent should select actions in pursuit of its goals, and adapt accordingly when its goals need revision. However, most agents assume that their goals are given to them; they cannot recognize when their goals should change. Thus, they have difficulty coping with the complex environments of strategy simulations that are continuous, partially observable, dynamic, and open with respect to new objects. To increase intelligent agent autonomy, we are investigating a conceptual model for goal reasoning called Goal‐Driven Autonomy (GDA), which allows agents to generate and reason about their goals in response to environment changes. Our hypothesis is that GDA enables an agent to respond more effectively to unexpected events in complex environments. We instantiate the GDA model in ARTUE (Autonomous Response to Unexpected Events), a domain‐independent autonomous agent. We evaluate ARTUE on scenarios from two complex strategy simulations, and report on its comparative benefits and limitations. By employing goal reasoning, ARTUE outperforms an off‐line planner and a discrepancy‐based replanner on scenarios requiring reasoning about unobserved objects and facts and on scenarios presenting opportunities outside the scope of its current mission.

In order to collaborate with people in the real world, cognitive systems must be able to represent and reason about spatial regions in human environments. Consider the command "go to the front of the classroom". The spatial region mentioned (the front of the classroom) is not perceivable using geometry alone. Instead it is defined by its functional use, implied by nearby objects and their configuration. In this paper, we define such areas as context-dependent spatial regions and present a cognitive system able to learn them by combining qualitative spatial representations, semantic labels, and analogy. The system is capable of generating a collection of qualitative spatial representations describing the configuration of the entities it perceives in the world. It can then be taught context-dependent spatial regions using anchor pointsdefined on these representations. From this we then demonstrate how an existing computational model of analogy can be used to detect context-dependent spatial regions in previously unseen rooms. To evaluate this process we compare detected regions to annotations made on maps of real rooms by human volunteers.

One of the central problems of artificial intelligence is capturing the breadth and flexibility of human common sense reasoning. One way to evaluate common sense is to use versions of human tests that rely on everyday reasoning. The Bennett Mechanical Comprehension Test consists of everyday reasoning problems posed via pictures and is used to evaluate technicians. This test is challenging because it requires conceptual knowledge spanning a broad range of domains, experience with a wide variety of everyday situations, and spatial reasoning. This article describes how we have extended our Companion Cognitive Architecture, which treats analogical processing as central, to perform well over a subset of the Bennett test. We introduce analogical model formulation as a robust method for reasoning about everyday scenarios, by analogy with cases that represent prior experiences. This enables a companion to perform qualitative reasoning (QR) without a complete domain theory, as typically required for QR. We introduce sketch annotations to communicate linkages between visual and conceptual properties in sketches. We introduce analogical reference frames to enable comparative analysis to operate over a broader range of problems than prior techniques. We show that these techniques enable a companion to score reasonably well on a difficult subset of the Bennett test.

Planning in dynamic continuous environments requires reasoning about nonlinear continuous effects, which previous Hierarchical Task Network (HTN) planners do not support. In this paper, we extend an existing HTN planner with a new state projection algorithm. To our knowledge, this is the first HTN planner that can reason about nonlinear continuous effects. We use a wait action to instruct this planner to consider continuous effects in a given state. We also introduce a new planning domain to demonstrate the benefits of planning with nonlinear continuous effects. We compare our approach with a linear continuous effects planner and a discrete effects HTN planner on a benchmark domain, which reveals that its additional costs are largely mitigated by domain knowledge. Finally, we present an initial application of this algorithm in a practical domain, a Navy training simulation, illustrating the utility of this approach for planning in dynamic continuous environments.

Modern complex games and simulations pose many challenges for an intelligent agent, including partial observability, continuous time and effects, hostile opponents, and exogenous events. We present ARTUE (Autonomous Response to Unexpected Events), a domain-independent autonomous agent that dynamically reasons about what goals to pursue in response to unexpected circumstances in these types of environments. ARTUE integrates AI research in planning, environment monitoring, explanation, goal generation, and goal management. To explain our conceptualization of the problem ARTUE addresses, we present a new conceptual framework, goal-driven autonomy, for agents that reason about their goals. We evaluate ARTUE on scenarios in the TAO Sandbox, a Navy training simulation, and demonstrate its novel architecture, which includes components for Hierarchical Task Network planning, explanation, and goal management. Our evaluation shows that ARTUE can perform well in a complex environment and that each component is necessary and contributes to the performance of the integrated system.