Audiopedia is introduced (with 3 subtasks, s-AQA, m-AQA and r-AQA), a novel Audio QA task, requiring audio comprehension and external knowledge reasoning. Additionally, a framework that combines Audio Entity Linking (AEL) and a Knowledge-Augmented Audio Multimodal Model (KA2LM) is proposed to enhance large audio language models for knowledge-intensive tasks.

Animations produced by generative models are often evaluated using objective quantitative metrics that do not fully capture perceptual effects in immersive virtual environments. To address this gap, we present a preliminary perceptual evaluation of generative models for animation synthesis, conducted via a VR-based user study (N = 48). Our investigation specifically focuses on animation congruency—ensuring that generated facial expressions and body gestures are both congruent with and synchronized to driving speech. We evaluated two state-of-the-art methods: a speech-driven full-body animation model and a video-driven full-body reconstruction model, assessing their capability to produce congruent facial expressions and body gestures. Our results demonstrate a strong user preference for combined facial and body animations, highlighting that congruent multimodal animations significantly enhance perceived realism compared to animations featuring only a single modality. By incorporating VR-based perceptual feedback into training pipelines, our approach provides a foundation for developing more engaging and responsive virtual characters.

Introduction: Social interactions incorporate various nonverbal signals to convey emotions alongside speech, including facial expressions and body gestures. Generative models have demonstrated promising results in creating full-body nonverbal animations synchronized with speech; however, evaluations using statistical metrics in 2D settings fail to fully capture user-perceived emotions, limiting our understanding of the effectiveness of these models. Methods: To address this, we evaluate emotional 3D animation generative models within an immersive Virtual Reality (VR) environment, emphasizing user—centric metrics-emotional arousal realism, naturalness, enjoyment, diversity, and interaction quality—in a real-time human-agent interaction scenario. Through a user study (N = 48), we systematically examine perceived emotional quality for three state-of-the-art speech-driven 3D animation methods across two specific emotions: happiness (high arousal) and neutral (mid arousal). Additionally, we compare these generative models against real human expressions obtained via a reconstruction-based method to assess both their strengths and limitations and how closely they replicate real human facial and body expressions. Results: Our results demonstrate that methods explicitly modeling emotions lead to higher recognition accuracy compared to those focusing solely on speech-driven synchrony. Users rated the realism and naturalness of happy animations significantly higher than those of neutral animations, highlighting the limitations of current generative models in handling subtle emotional states. Discussion: Generative models underperformed compared to reconstruction-based methods in facial expression quality, and all methods received relatively low ratings for animation enjoyment and interaction quality, emphasizing the importance of incorporating user-centric evaluations into generative model development. Finally, participants positively recognized animation diversity across all generative models.

Existing methods for synthesizing 3D human gestures from speech have shown promising results but they do not explicitly model the impact of emotions on the generated gestures. Instead these methods directly output animations from speech without control over the expressed emotion. To address this limitation we present AMUSE an emotional speech-driven body animation model based on latent diffusion. Our observation is that content (i.e. gestures related to speech rhythm and word utterances) emotion and personal style are separable. To account for this AMUSE maps the driving audio to three disentangled latent vectors: one for content one for emotion and one for personal style. A latent diffusion model trained to generate gesture motion sequences is then conditioned on these latent vectors. Once trained AMUSE synthesizes 3D human gestures directly from speech with control over the expressed emotions and style by combining the content from the driving speech with the emotion and style of another speech sequence. Randomly sampling the noise of the diffusion model further generates variations of the gesture with the same emotional expressivity. Qualitative quantitative and perceptual evaluations demonstrate that AMUSE outputs realistic gesture sequences. Compared to the state of the art the generated gestures are better synchronized with the speech content and better represent the emotion expressed by the input speech. Our code is available at amuse.is.tue.mpg.de.

To be widely adopted, 3D facial avatars must be animated easily, realistically, and directly from speech signals. While the best recent methods generate 3D animations that are synchronized with the input audio, they largely ignore the impact of emotions on facial expressions. Realistic facial animation requires lip-sync together with the natural expression of emotion. To that end, we propose EMOTE (Expressive Model Optimized for Talking with Emotion), which generates 3D talking-head avatars that maintain lip-sync from speech while enabling explicit control over the expression of emotion. To achieve this, we supervise EMOTE with decoupled losses for speech (i.e., lip-sync) and emotion. These losses are based on two key observations: (1) deformations of the face due to speech are spatially localized around the mouth and have high temporal frequency, whereas (2) facial expressions may deform the whole face and occur over longer intervals. Thus we train EMOTE with a per-frame lip-reading loss to preserve the speech-dependent content, while supervising emotion at the sequence level. Furthermore, we employ a content-emotion exchange mechanism in order to supervise different emotions on the same audio, while maintaining the lip motion synchronized with the speech. To employ deep perceptual losses without getting undesirable artifacts, we devise a motion prior in the form of a temporal VAE. Due to the absence of high-quality aligned emotional 3D face datasets with speech, EMOTE is trained with 3D pseudo-ground-truth extracted from an emotional video dataset (i.e., MEAD). Extensive qualitative and perceptual evaluations demonstrate that EMOTE produces speech-driven facial animations with better lip-sync than state-of-the-art methods trained on the same data, while offering additional, high-quality emotional control.

MATSim (Multi-Agent Transport Simulation Toolkit) is an open source large-scale agent-based transportation planning project applied to various areas like road transport, public transport, freight transport, regional evacuation, etc. BEAM (Behavior, Energy, Autonomy, and Mobility) framework extends MATSim to enable powerful and scalable analysis of urban transportation systems. The agents from the BEAM simulation exhibit 'mode choice' behavior based on multinomial logit model. In our study, we consider eight mode choices viz. bike, car, walk, ride hail, driving to transit, walking to transit, ride hail to transit, and ride hail pooling. The 'alternative specific constants' for each mode choice are critical hyperparameters in a configuration file related to a particular scenario under experimentation. We use the 'Urbansim-10k' BEAM scenario (with 10,000 population size) for all our experiments. Since these hyperparameters affect the simulation in complex ways, manual calibration methods are time consuming. We present a parallel Bayesian optimization method with early stopping rule to achieve fast convergence for the given multi-in-multi-out problem to its optimal configurations. Our model is based on an open source HpBandSter package. This approach combines hierarchy of several 1D Kernel Density Estimators (KDE) with a cheap evaluator (Hyperband, a single multidimensional KDE). Our model has also incorporated extrapolation based early stopping rule. With our model, we could achieve a 25% L1 norm for a large-scale BEAM simulation in fully autonomous manner. To the best of our knowledge, our work is the first of its kind applied to large-scale multi-agent transportation simulations. This work can be useful for surrogate modeling of scenarios with very large populations. 

Computer-Aided Architectural Design (CAAD) finds its historical precedents in technological enthusiasm for generative algorithms and architectural intelligence. Current developments in Artificial Intelligence (AI) and paradigms in Machine Learning (ML) bring new opportunities for creating innovative digital architectural tools, but in practice this is not happening. CAAD enthusiasts revisit generative algorithms, while professional architects and urban designers remain reluctant to use software that automatically generates architecture and cities. This paper looks at the history of CAAD and digital tools for Computer Aided Design (CAD), Building Information Modeling (BIM) and Geographic Information Systems (GIS) in order to reflect on the role of AI in future digital tools and professional practices. Architects and urban designers have diagrammatic knowledge and work with design problems on symbolic level. The digital tools gradually evolved from CAD to BIM software with symbolical architectural elements. The BIM software works like CAAD (CAD systems for Architects) or digital board for drawing and delivers plans, sections and elevations, but without AI. AI has the capability to process data and interact with designers. The AI in future digital tools for CAAD and Computer-Aided Urban Design (CAUD) can link to big data and develop ambient intelligence. Architects and urban designers can harness the benefits of analytical ambient intelligent AIs in creating environmental designs, not only for shaping buildings in isolated virtual cubicles. However there is a need to prepare frameworks for communication between AIs and professional designers. If the cities of the future integrate spatially analytical AI, are to be made smart or even ambient intelligent, AI should be applied to improving the lives of inhabitants and help with their daily living and sustainability.

The new developments in Information and Communication Technologies (ICT) and Artificial Intelligence (AI) bring revelations of emerging smart cities. However, AI has not yet been integrated in Computer Aided Design (CAD), Building Information Modelling (BIM) or Geographic Information Systems (GIS) software. There are experiments with AI in urban modelling and simulations and AI techniques are applied in procedural generation of buildings and cities, but software based on simulations, procedural models and generative algorithms is seldom used in architectural and urbanist practices. In this paper, we look at the history of smart cities and digitization in architecture and urbanism in relation to new potentials brought by AI. We map and juxtapose future urban visions, digital tools and AI techniques to discuss the role of architects and urban designers in an emerging world of smart cities. The purpose is to inspire a debate about the possibility to make a convergence of architectural and urbanist practices with new AI developments.

When we practice a movement, human brains creates a motor memory of it. These memories are formed and stored in the brain as representations which allows us to perform familiar tasks faster than new movements. From a developmental robotics and embodied artificial agent perspective it could be also beneficial to exploit the concept of these motor representations in the form of spatial-temporal motion priors for complex, full-body motion synthesis. Encoding such priors in neural networks in a form of inductive biases inherit essential spatio-temporality aspect of human motion. In our current work we examine and compare recent approaches for capturing spatial and temporal dependencies with machine learning algorithms that are used to model human motion.