Showing 1–50 of 94 results for author: Bulling, A

Ontology-Guided Diffusion for Zero-Shot Visual Sim2Real Transfer

Authors: Mohamed Youssef, Mayar Elfares, Anna-Maria Meer, Matteo Bortoletto, Andreas Bulling

Abstract: Bridging the simulation-to-reality (sim2real) gap remains challenging as labelled real-world data is scarce. Existing diffusion-based approaches rely on unstructured prompts or statistical alignment, which do not capture the structured factors that make images look real. We introduce Ontology- Guided Diffusion (OGD), a neuro-symbolic zero-shot sim2real image translation framework that represents r… ▽ More Bridging the simulation-to-reality (sim2real) gap remains challenging as labelled real-world data is scarce. Existing diffusion-based approaches rely on unstructured prompts or statistical alignment, which do not capture the structured factors that make images look real. We introduce Ontology- Guided Diffusion (OGD), a neuro-symbolic zero-shot sim2real image translation framework that represents realism as structured knowledge. OGD decomposes realism into an ontology of interpretable traits -- such as lighting and material properties -- and encodes their relationships in a knowledge graph. From a synthetic image, OGD infers trait activations and uses a graph neural network to produce a global embedding. In parallel, a symbolic planner uses the ontology traits to compute a consistent sequence of visual edits needed to narrow the realism gap. The graph embedding conditions a pretrained instruction-guided diffusion model via cross-attention, while the planned edits are converted into a structured instruction prompt. Across benchmarks, our graph-based embeddings better distinguish real from synthetic imagery than baselines, and OGD outperforms state-of-the-art diffusion methods in sim2real image translations. Overall, OGD shows that explicitly encoding realism structure enables interpretable, data-efficient, and generalisable zero-shot sim2real transfer. △ Less

Submitted 25 March, 2026; v1 submitted 19 March, 2026; originally announced March 2026.

ObjectVisA-120: Object-based Visual Attention Prediction in Interactive Street-crossing Environments

Authors: Igor Vozniak, Philipp Mueller, Nils Lipp, Janis Sprenger, Konstantin Poddubnyy, Davit Hovhannisyan, Christian Mueller, Andreas Bulling, Philipp Slusallek

Abstract: The object-based nature of human visual attention is well-known in cognitive science, but has only played a minor role in computational visual attention models so far. This is mainly due to a lack of suitable datasets and evaluation metrics for object-based attention. To address these limitations, we present ObjectVisA-120 -- a novel 120-participant dataset of spatial street-crossing navigation in… ▽ More The object-based nature of human visual attention is well-known in cognitive science, but has only played a minor role in computational visual attention models so far. This is mainly due to a lack of suitable datasets and evaluation metrics for object-based attention. To address these limitations, we present ObjectVisA-120 -- a novel 120-participant dataset of spatial street-crossing navigation in virtual reality specifically geared to object-based attention evaluations. The uniqueness of the presented dataset lies in the ethical and safety affiliated challenges that make collecting comparable data in real-world environments highly difficult. ObjectVisA-120 not only features accurate gaze data and a complete state-space representation of objects in the virtual environment, but it also offers variable scenario complexities and rich annotations, including panoptic segmentation, depth information, and vehicle keypoints. We further propose object-based similarity (oSIM) as a novel metric to evaluate the performance of object-based visual attention models, a previously unexplored performance characteristic. Our evaluations show that explicitly optimising for object-based attention not only improves oSIM performance but also leads to an improved model performance on common metrics. In addition, we present SUMGraph, a Mamba U-Net-based model, which explicitly encodes critical scene objects (vehicles) in a graph representation, leading to further performance improvements over several state-of-the-art visual attention prediction methods. The dataset, code and models will be publicly released. △ Less

Submitted 30 January, 2026; v1 submitted 19 January, 2026; originally announced January 2026.

Comments: Accepted for publication at the IEEE Intelligent Vehicles Symposium (IV), 2026

CryptoQA: A Large-scale Question-answering Dataset for AI-assisted Cryptography

Authors: Mayar Elfares, Pascal Reisert, Tilman Dietz, Manpa Barman, Ahmed Zaki, Ralf Küsters, Andreas Bulling

Abstract: Large language models (LLMs) excel at many general-purpose natural language processing tasks. However, their ability to perform deep reasoning and mathematical analysis, particularly for complex tasks as required in cryptography, remains poorly understood, largely due to the lack of suitable data for evaluation and training. To address this gap, we present CryptoQA, the first large-scale question-… ▽ More Large language models (LLMs) excel at many general-purpose natural language processing tasks. However, their ability to perform deep reasoning and mathematical analysis, particularly for complex tasks as required in cryptography, remains poorly understood, largely due to the lack of suitable data for evaluation and training. To address this gap, we present CryptoQA, the first large-scale question-answering (QA) dataset specifically designed for cryptography. CryptoQA contains over two million QA pairs drawn from curated academic sources, along with contextual metadata that can be used to test the cryptographic capabilities of LLMs and to train new LLMs on cryptographic tasks. We benchmark 15 state-of-the-art LLMs on CryptoQA, evaluating their factual accuracy, mathematical reasoning, consistency, referencing, backward reasoning, and robustness to adversarial samples. In addition to quantitative metrics, we provide expert reviews that qualitatively assess model outputs and establish a gold-standard baseline. Our results reveal significant performance deficits of LLMs, particularly on tasks that require formal reasoning and precise mathematical knowledge. This shows the urgent need for LLM assistants tailored to cryptography research and development. We demonstrate that, by using CryptoQA, LLMs can be fine-tuned to exhibit better performance on cryptographic tasks. △ Less

Submitted 2 December, 2025; originally announced December 2025.

High entropy leads to symmetry-equivariant policies in Dec-POMDPs

Authors: Johannes Forkel, Constantin Ruhdorfer, Michael Beukman, Andreas Bulling, Jakob Foerster

Abstract: We prove that in any Dec-POMDP, sufficiently high entropy regularization ensures that the policy gradient flow with tabular softmax parametrization always converges, for any initialization, to the same joint policy, and that this joint policy is equivariant w.r.t. all symmetries of the Dec-POMDP. In particular, policies coming from different initializations will be fully compatible, in that their… ▽ More We prove that in any Dec-POMDP, sufficiently high entropy regularization ensures that the policy gradient flow with tabular softmax parametrization always converges, for any initialization, to the same joint policy, and that this joint policy is equivariant w.r.t. all symmetries of the Dec-POMDP. In particular, policies coming from different initializations will be fully compatible, in that their cross-play returns are equal to their self-play returns. Through extensive evaluation of independent PPO, arguably the standard baseline deep multi-agent policy gradient algorithm, in the Hanabi, Overcooked and Yokai environments, we find that the entropy coefficient has a massive influence on the cross-play returns between independently trained policies, and that the decrease in self-play returns coming from increased entropy regularization can often be counteracted by greedifying the learned policies after training. In Hanabi in particular we achieve a new SOTA in inter-seed cross-play this way. While we give examples of Dec-POMDPs in which one cannot learn the optimal symmetry-equivariant policy this way, both our theoretical and empirical results suggest that one should consider far higher entropy coefficients during hyperparameter sweeps in Dec-POMDPs than is typically done. Code for our experiments can be found at https://github.com/jforkel/JAX-OBL △ Less

Submitted 4 June, 2026; v1 submitted 27 November, 2025; originally announced November 2025.

REFLECTing SPERET: Measuring and Promoting Ethics and Privacy Reflexivity in Eye-Tracking Research

Authors: Susanne Hindennach, Mayar Elfares, Céline Gressel, Andreas Bulling

Abstract: The proliferation of eye tracking in high-stakes domains - such as healthcare, marketing and surveillance - underscores the need for researchers to be ethically aware when employing this technology. Although privacy and ethical guidelines have emerged in recent years, empirical research on how scholars reflect on their own work remains scarce. To address this gap, we present two complementary inst… ▽ More The proliferation of eye tracking in high-stakes domains - such as healthcare, marketing and surveillance - underscores the need for researchers to be ethically aware when employing this technology. Although privacy and ethical guidelines have emerged in recent years, empirical research on how scholars reflect on their own work remains scarce. To address this gap, we present two complementary instruments developed with input from more than 70 researchers: REFLECT, a qualitative questionnaire, and SPERET (Latin for "hope"), a quantitative psychometric scale that measures privacy and ethics reflexivity in eye tracking. Our findings reveal a research community that is concerned about user privacy, cognisant of methodological constraints, such as sample bias, and that possesses a nuanced sense of ethical responsibility evolving with project maturity. Together, these tools and our analyses offer a systematic examination and a hopeful outlook on reflexivity in eye-tracking research, promoting more privacy and ethics-conscious practice. △ Less

Submitted 24 November, 2025; originally announced November 2025.

Comments: 15 pages

HAGI++: Head-Assisted Gaze Imputation and Generation

Authors: Chuhan Jiao, Zhiming Hu, Andreas Bulling

Abstract: Mobile eye tracking plays a vital role in capturing human visual attention across both real-world and extended reality (XR) environments, making it an essential tool for applications ranging from behavioural research to human-computer interaction. However, missing values due to blinks, pupil detection errors, or illumination changes pose significant challenges for further gaze data analysis. To ad… ▽ More Mobile eye tracking plays a vital role in capturing human visual attention across both real-world and extended reality (XR) environments, making it an essential tool for applications ranging from behavioural research to human-computer interaction. However, missing values due to blinks, pupil detection errors, or illumination changes pose significant challenges for further gaze data analysis. To address this challenge, we introduce HAGI++ - a multi-modal diffusion-based approach for gaze data imputation that, for the first time, uses the integrated head orientation sensors to exploit the inherent correlation between head and eye movements. HAGI++ employs a transformer-based diffusion model to learn cross-modal dependencies between eye and head representations and can be readily extended to incorporate additional body movements. Extensive evaluations on the large-scale Nymeria, Ego-Exo4D, and HOT3D datasets demonstrate that HAGI++ consistently outperforms conventional interpolation methods and deep learning-based time-series imputation baselines in gaze imputation. Furthermore, statistical analyses confirm that HAGI++ produces gaze velocity distributions that closely match actual human gaze behaviour, ensuring more realistic gaze imputations. Moreover, by incorporating wrist motion captured from commercial wearable devices, HAGI++ surpasses prior methods that rely on full-body motion capture in the extreme case of 100% missing gaze data (pure gaze generation). Our method paves the way for more complete and accurate eye gaze recordings in real-world settings and has significant potential for enhancing gaze-based analysis and interaction across various application domains. △ Less

Submitted 4 November, 2025; originally announced November 2025.

Comments: Extended version of our UIST'25 paper "HAGI: Head-Assisted Gaze Imputation for Mobile Eye Trackers"

ProToM: Promoting Prosocial Behaviour via Theory of Mind-Informed Feedback

Authors: Matteo Bortoletto, Yichao Zhou, Lance Ying, Tianmin Shu, Andreas Bulling

Abstract: While humans are inherently social creatures, the challenge of identifying when and how to assist and collaborate with others - particularly when pursuing independent goals - can hinder cooperation. To address this challenge, we aim to develop an AI system that provides useful feedback to promote prosocial behaviour - actions that benefit others, even when not directly aligned with one's own goals… ▽ More While humans are inherently social creatures, the challenge of identifying when and how to assist and collaborate with others - particularly when pursuing independent goals - can hinder cooperation. To address this challenge, we aim to develop an AI system that provides useful feedback to promote prosocial behaviour - actions that benefit others, even when not directly aligned with one's own goals. We introduce ProToM, a Theory of Mind-informed facilitator that promotes prosocial actions in multi-agent systems by providing targeted, context-sensitive feedback to individual agents. ProToM first infers agents' goals using Bayesian inverse planning, then selects feedback to communicate by maximising expected utility, conditioned on the inferred goal distribution. We evaluate our approach against baselines in two multi-agent environments: Doors, Keys, and Gems, as well as Overcooked. Our results suggest that state-of-the-art large language and reasoning models fall short of communicating feedback that is both contextually grounded and well-timed - leading to higher communication overhead and task speedup. In contrast, ProToM provides targeted and helpful feedback, achieving a higher success rate, shorter task completion times, and is consistently preferred by human users. △ Less

Submitted 5 September, 2025; originally announced September 2025.

Comments: Website at https://www.matteobortoletto.org/protom/

ToM-SSI: Evaluating Theory of Mind in Situated Social Interactions

Authors: Matteo Bortoletto, Constantin Ruhdorfer, Andreas Bulling

Abstract: Most existing Theory of Mind (ToM) benchmarks for foundation models rely on variations of the Sally-Anne test, offering only a very limited perspective on ToM and neglecting the complexity of human social interactions. To address this gap, we propose ToM-SSI: a new benchmark specifically designed to test ToM capabilities in environments rich with social interactions and spatial dynamics. While cur… ▽ More Most existing Theory of Mind (ToM) benchmarks for foundation models rely on variations of the Sally-Anne test, offering only a very limited perspective on ToM and neglecting the complexity of human social interactions. To address this gap, we propose ToM-SSI: a new benchmark specifically designed to test ToM capabilities in environments rich with social interactions and spatial dynamics. While current ToM benchmarks are limited to text-only or dyadic interactions, ToM-SSI is multimodal and includes group interactions of up to four agents that communicate and move in situated environments. This unique design allows us to study, for the first time, mixed cooperative-obstructive settings and reasoning about multiple agents' mental state in parallel, thus capturing a wider range of social cognition than existing benchmarks. Our evaluations reveal that the current models' performance is still severely limited, especially in these new tasks, highlighting critical gaps for future research. △ Less

Submitted 16 September, 2025; v1 submitted 5 September, 2025; originally announced September 2025.

Comments: EMNLP 2025 (Main)

The Yokai Learning Environment: Tracking Beliefs Over Space and Time

Authors: Constantin Ruhdorfer, Matteo Bortoletto, Johannes Forkel, Jakob Foerster, Andreas Bulling

Abstract: The ability to cooperate with unknown partners is a central challenge in cooperative AI and widely studied in the form of zero-shot coordination (ZSC), which evaluates an algorithm by measuring the performance of independently trained agents when paired. The Hanabi Learning Environment (HLE) has become the dominant benchmark for ZSC, but recent work has achieved near-perfect inter-seed cross-play… ▽ More The ability to cooperate with unknown partners is a central challenge in cooperative AI and widely studied in the form of zero-shot coordination (ZSC), which evaluates an algorithm by measuring the performance of independently trained agents when paired. The Hanabi Learning Environment (HLE) has become the dominant benchmark for ZSC, but recent work has achieved near-perfect inter-seed cross-play performance, limiting its ability to track algorithmic progress. We introduce the Yokai Learning Environment (YLE) - an open-source multi-agent RL benchmark in which effective collaboration requires building common ground by tracking and updating beliefs over moving cards, reasoning under ambiguous hints, and deciding when to terminate the game based on inferred shared knowledge - features absent in the HLE, where beliefs are tied to hand slots and hints are truthful by rule. We evaluate the leading ZSC methods, including High-Entropy IPPO, Other-Play, and Off-Belief Learning, which achieve near-perfect inter-seed cross-play in the HLE, and show that in the YLE they exhibit persistent SP-XP gaps, degraded early-ending calibration, and weaker belief representations in cross-play, indicating failure to maintain consistent internal models with unseen partners. Methods that perform best in the HLE do not perform best in the YLE, indicating that progress measured on a single benchmark may not generalise. Together, these results establish YLE as a challenging new ZSC benchmark. △ Less

Submitted 5 August, 2026; v1 submitted 17 August, 2025; originally announced August 2025.

Comments: RLC 2026

Unsupervised Partner Design Enables Robust Ad-hoc Teamwork

Authors: Constantin Ruhdorfer, Matteo Bortoletto, Victor Oei, Anna Penzkofer, Andreas Bulling

Abstract: We introduce Unsupervised Partner Design (UPD), a population-free multi-agent reinforcement learning method for robust ad-hoc teamwork. UPD generates training partners on-the-fly and selects them adaptively based on a learnability criterion, removing the need for pre-trained partner populations or manual parameter tuning. We show that this simple mechanism enables effective partner diversity and c… ▽ More We introduce Unsupervised Partner Design (UPD), a population-free multi-agent reinforcement learning method for robust ad-hoc teamwork. UPD generates training partners on-the-fly and selects them adaptively based on a learnability criterion, removing the need for pre-trained partner populations or manual parameter tuning. We show that this simple mechanism enables effective partner diversity and can be extended to joint partner-environment selection when a procedural level generator is available. Across Level-Based Foraging, Overcooked-AI, and the Overcooked Generalisation Challenge, UPD consistently achieves strong performance compared to both population-based and population-free baselines. In a human-AI user study, agents trained with UPD achieve higher returns and are rated as more adaptive, more human-like, and less frustrating than all evaluated baseline methods. △ Less

Submitted 7 June, 2026; v1 submitted 8 August, 2025; originally announced August 2025.

Comments: 27 pages

Tell Me Without Telling Me: Two-Way Prediction of Visualization Literacy and Visual Attention

Authors: Minsuk Chang, Yao Wang, Huichen Will Wang, Yuanhong Zhou, Andreas Bulling, Cindy Xiong Bearfield

Abstract: Accounting for individual differences can improve the effectiveness of visualization design. While the role of visual attention in visualization interpretation is well recognized, existing work often overlooks how this behavior varies based on visual literacy levels. Based on data from a 235-participant user study covering three visualization tests (mini-VLAT, CALVI, and SGL), we show that distinc… ▽ More Accounting for individual differences can improve the effectiveness of visualization design. While the role of visual attention in visualization interpretation is well recognized, existing work often overlooks how this behavior varies based on visual literacy levels. Based on data from a 235-participant user study covering three visualization tests (mini-VLAT, CALVI, and SGL), we show that distinct attention patterns in visual data exploration can correlate with participants' literacy levels: While experts (high-scorers) generally show a strong attentional focus, novices (low-scorers) focus less and explore more. We then propose two computational models leveraging these insights: Lit2Sal -- a novel visual saliency model that predicts observer attention given their visualization literacy level, and Sal2Lit -- a model to predict visual literacy from human visual attention data. Our quantitative and qualitative evaluation demonstrates that Lit2Sal outperforms state-of-the-art saliency models with literacy-aware considerations. Sal2Lit predicts literacy with 86% accuracy using a single attention map, providing a time-efficient supplement to literacy assessment that only takes less than a minute. Taken together, our unique approach to consider individual differences in salience models and visual attention in literacy assessments paves the way for new directions in personalized visual data communication to enhance understanding. △ Less

Submitted 22 July, 2025; originally announced August 2025.

Comments: 11 pages, 9 figures, Accepted to 2025 IEEE VIS (Visualization and Visual Analytics)

Gaze3P: Gaze-Based Prediction of User-Perceived Privacy

Authors: Mayar Elfares, Pascal Reisert, Ralf Küsters, Andreas Bulling

Abstract: Privacy is a highly subjective concept and perceived variably by different individuals. Previous research on quantifying user-perceived privacy has primarily relied on questionnaires. Furthermore, applying user-perceived privacy to optimise the parameters of privacy-preserving techniques (PPT) remains insufficiently explored. To address these limitations, we introduce Gaze3P -- the first dataset s… ▽ More Privacy is a highly subjective concept and perceived variably by different individuals. Previous research on quantifying user-perceived privacy has primarily relied on questionnaires. Furthermore, applying user-perceived privacy to optimise the parameters of privacy-preserving techniques (PPT) remains insufficiently explored. To address these limitations, we introduce Gaze3P -- the first dataset specifically designed to facilitate systematic investigations into user-perceived privacy. Our dataset comprises gaze data from 100 participants and 1,000 stimuli, encompassing a range of private and safe attributes. With Gaze3P, we train a machine learning model to implicitly and dynamically predict perceived privacy from human eye gaze. Through comprehensive experiments, we show that the resulting models achieve high accuracy. Finally, we illustrate how predicted privacy can be used to optimise the parameters of differentially private mechanisms, thereby enhancing their alignment with user expectations. △ Less

Submitted 10 September, 2025; v1 submitted 1 July, 2025; originally announced July 2025.

Journal ref: Proc. Privacy Enhancing Technologies Symposium (PETS), 2026

MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning

Authors: Tristan Tomilin, Luka van den Boogaard, Samuel Garcin, Constantin Ruhdorfer, Bram Grooten, Fabrice Kusters, Yali Du, Andreas Bulling, Mykola Pechenizkiy, Meng Fang

Abstract: Benchmarks play a central role in reinforcement learning (RL) research, yet their computational constraints often shape what is studied. Despite the motivation of lifelong learning, most continual RL papers consider only 3-10 sequential tasks, as CPU-bound environments make longer sequences impractical. Meanwhile, continual learning in cooperative multi-agent settings remains largely unexplored. T… ▽ More Benchmarks play a central role in reinforcement learning (RL) research, yet their computational constraints often shape what is studied. Despite the motivation of lifelong learning, most continual RL papers consider only 3-10 sequential tasks, as CPU-bound environments make longer sequences impractical. Meanwhile, continual learning in cooperative multi-agent settings remains largely unexplored. To address these gaps, we introduce MEAL (Multi-agent Environments for Adaptive Learning), the first benchmark for continual multi-agent RL. By leveraging JAX and GPU acceleration, MEAL enables training on sequences of 100 tasks in a few hours on a single GPU. We find that long task sequences reveal failure modes that do not appear at smaller scales. △ Less

Submitted 18 June, 2026; v1 submitted 17 June, 2025; originally announced June 2025.

Comments: To be published in the International Conference on Machine Learning (ICML) 2026

Guidelines for Gaze-based Neural Preliminary Diagnosis

Authors: Mayar Elfares, Salma Younis, Pascal Reisert, Ralf Küsters, Tobias Renner, Andreas Bulling

Abstract: Neural disorders refer to any condition affecting the nervous system and that influence how individuals perceive and interact with the world. Traditional neural diagnoses rely on cumbersome, time-consuming, or subjective methods, such as clinical interviews, behavioural observations, or medical imaging. Eye tracking is an attractive alternative because analysing eye movements, such as fixations an… ▽ More Neural disorders refer to any condition affecting the nervous system and that influence how individuals perceive and interact with the world. Traditional neural diagnoses rely on cumbersome, time-consuming, or subjective methods, such as clinical interviews, behavioural observations, or medical imaging. Eye tracking is an attractive alternative because analysing eye movements, such as fixations and saccades, can provide more objective insights into brain function and cognitive processing by capturing non-verbal and unconscious responses. Despite its potential, existing gaze-based studies presented seemingly contradictory findings. They are dispersed across diverse fields, requiring further research to standardise protocols and expand their application, particularly as a preliminary indicator of neural processes for differential diagnosis. Therefore, this paper outlines the main agreed-upon findings and provides a systematisation of knowledge and key guidelines towards advancing gaze-based neural preliminary diagnosis. △ Less

Submitted 10 June, 2025; originally announced June 2025.

QualitEye: Public and Privacy-preserving Gaze Data Quality Verification

Authors: Mayar Elfares, Pascal Reisert, Ralf Küsters, Andreas Bulling

Abstract: Gaze-based applications are increasingly advancing with the availability of large datasets but ensuring data quality presents a substantial challenge when collecting data at scale. It further requires different parties to collaborate, therefore, privacy concerns arise. We propose QualitEye--the first method for verifying image-based gaze data quality. QualitEye employs a new semantic representatio… ▽ More Gaze-based applications are increasingly advancing with the availability of large datasets but ensuring data quality presents a substantial challenge when collecting data at scale. It further requires different parties to collaborate, therefore, privacy concerns arise. We propose QualitEye--the first method for verifying image-based gaze data quality. QualitEye employs a new semantic representation of eye images that contains the information required for verification while excluding irrelevant information for better domain adaptation. QualitEye covers a public setting where parties can freely exchange data and a privacy-preserving setting where parties cannot reveal their raw data nor derive gaze features/labels of others with adapted private set intersection protocols. We evaluate QualitEye on the MPIIFaceGaze and GazeCapture datasets and achieve a high verification performance (with a small overhead in runtime for privacy-preserving versions). Hence, QualitEye paves the way for new gaze analysis methods at the intersection of machine learning, human-computer interaction, and cryptography. △ Less

Submitted 19 March, 2026; v1 submitted 6 June, 2025; originally announced June 2025.

RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo

Authors: Victor Oei, Jenny Schmalfuss, Lukas Mehl, Madlen Bartsch, Shashank Agnihotri, Margret Keuper, Andreas Bulling, Andrés Bruhn

Abstract: Standard benchmarks for optical flow, scene flow, and stereo vision algorithms generally focus on model accuracy rather than robustness to image corruptions like noise or rain. Hence, the resilience of models to such real-world perturbations is largely unquantified. To address this, we present RobustSpring, a comprehensive dataset and benchmark for evaluating robustness to image corruptions for op… ▽ More Standard benchmarks for optical flow, scene flow, and stereo vision algorithms generally focus on model accuracy rather than robustness to image corruptions like noise or rain. Hence, the resilience of models to such real-world perturbations is largely unquantified. To address this, we present RobustSpring, a comprehensive dataset and benchmark for evaluating robustness to image corruptions for optical flow, scene flow, and stereo models. RobustSpring applies 20 different image corruptions, including noise, blur, color changes, quality degradations, and weather distortions, in a time-, stereo-, and depth-consistent manner to the high-resolution Spring dataset, creating a suite of 20,000 corrupted images that reflect challenging conditions. RobustSpring enables comparisons of model robustness via a new corruption robustness metric. Integration with the Spring benchmark enables two-axis evaluations of both accuracy and robustness. We benchmark a curated selection of initial models, observing that robustness varies widely by corruption type, and experimentally show that evaluations on RobustSpring indicate real-world robustness. RobustSpring is a new computer vision benchmark to treat robustness as a first-class citizen, fostering models that are accurate and resilient. It is available at https://spring-benchmark.org. △ Less

Submitted 13 April, 2026; v1 submitted 14 May, 2025; originally announced May 2025.

HOIGaze: Gaze Estimation During Hand-Object Interactions in Extended Reality Exploiting Eye-Hand-Head Coordination

Authors: Zhiming Hu, Daniel Haeufle, Syn Schmitt, Andreas Bulling

Abstract: We present HOIGaze - a novel learning-based approach for gaze estimation during hand-object interactions (HOI) in extended reality (XR). HOIGaze addresses the challenging HOI setting by building on one key insight: The eye, hand, and head movements are closely coordinated during HOIs and this coordination can be exploited to identify samples that are most useful for gaze estimator training - as su… ▽ More We present HOIGaze - a novel learning-based approach for gaze estimation during hand-object interactions (HOI) in extended reality (XR). HOIGaze addresses the challenging HOI setting by building on one key insight: The eye, hand, and head movements are closely coordinated during HOIs and this coordination can be exploited to identify samples that are most useful for gaze estimator training - as such, effectively denoising the training data. This denoising approach is in stark contrast to previous gaze estimation methods that treated all training samples as equal. Specifically, we propose: 1) a novel hierarchical framework that first recognises the hand currently visually attended to and then estimates gaze direction based on the attended hand; 2) a new gaze estimator that uses cross-modal Transformers to fuse head and hand-object features extracted using a convolutional neural network and a spatio-temporal graph convolutional network; and 3) a novel eye-head coordination loss that upgrades training samples belonging to the coordinated eye-head movements. We evaluate HOIGaze on the HOT3D and Aria digital twin (ADT) datasets and show that it significantly outperforms state-of-the-art methods, achieving an average improvement of 15.6% on HOT3D and 6.0% on ADT in mean angular error. To demonstrate the potential of our method, we further report significant performance improvements for the sample downstream task of eye-based activity recognition on ADT. Taken together, our results underline the significant information content available in eye-hand-head coordination and, as such, open up an exciting new direction for learning-based gaze estimation. △ Less

Submitted 28 April, 2025; originally announced April 2025.

Comments: Accepted at SIGGRAPH 2025, link: https://zhiminghu.net/hu25_hoigaze.html

ChartOptimiser: Task-driven Optimisation of Chart Designs

Authors: Yao Wang, Jiarong Pan, Danqing Shi, Zhiming Hu, Antti Oulasvirta, Andreas Bulling

Abstract: Automated chart design has seen significant advancements with the emergence of Large-Language Models (LLMs), which offer a practical solution for generating charts. However, LLMs frequently introduce possibly critical design failures, such as data manipulation and confabulation. While expert users can potentially mitigate these issues through iterative prompt engineering, this process requires sub… ▽ More Automated chart design has seen significant advancements with the emergence of Large-Language Models (LLMs), which offer a practical solution for generating charts. However, LLMs frequently introduce possibly critical design failures, such as data manipulation and confabulation. While expert users can potentially mitigate these issues through iterative prompt engineering, this process requires substantial design knowledge and significant effort, remaining a massive barrier for the general public. In this paper, we present ChartOptimiser, an automated method for generating chart designs with fidelity, efficiency, and effectiveness. Given the inter-dependencies between individual design parameters, ChartOptimiser employs Bayesian optimisation to effectively search the chart design space for a novel objective function grounded in four perceptual metrics. Our empirical evaluations in bar and pie charts demonstrate that ChartOptimiser eliminates iterative design loops, providing non-expert users with high-quality charts that outperform LLM-generated designs in chart clarity, task-solving ease, and visual aesthetics. △ Less

Submitted 7 January, 2026; v1 submitted 14 April, 2025; originally announced April 2025.

Interactive Expressive Motion Generation Using Dynamic Movement Primitives

Authors: Till Hielscher, Andreas Bulling, Kai O. Arras

Abstract: Our goal is to enable social robots to interact autonomously with humans in a realistic, engaging, and expressive manner. The 12 Principles of Animation are a well-established framework animators use to create movements that make characters appear convincing, dynamic, and emotionally expressive. This paper proposes a novel approach that leverages Dynamic Movement Primitives (DMPs) to implement key… ▽ More Our goal is to enable social robots to interact autonomously with humans in a realistic, engaging, and expressive manner. The 12 Principles of Animation are a well-established framework animators use to create movements that make characters appear convincing, dynamic, and emotionally expressive. This paper proposes a novel approach that leverages Dynamic Movement Primitives (DMPs) to implement key animation principles, providing a learnable, explainable, modulable, online adaptable and composable model for automatic expressive motion generation. DMPs, originally developed for general imitation learning in robotics and grounded in a spring-damper system design, offer mathematical properties that make them particularly suitable for this task. Specifically, they enable modulation of the intensities of individual principles and facilitate the decomposition of complex, expressive motion sequences into learnable and parametrizable primitives. We present the mathematical formulation of the parameterized animation principles and demonstrate the effectiveness of our framework through experiments and application on three robotic platforms with different kinematic configurations, in simulation, on actual robots and in a user study. Our results show that the approach allows for creating diverse and nuanced expressions using a single base model. △ Less

Submitted 2 October, 2025; v1 submitted 9 April, 2025; originally announced April 2025.

Comments: This paper has been accepted for publication at the 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

CLAD: Constrained Latent Action Diffusion for Vision-Language Procedure Planning

Authors: Lei Shi, Andreas Bulling

Abstract: We propose CLAD, a Constrained Latent Action Diffusion model for vision-language procedure planning in instructional videos. Procedure planning is the challenging task of predicting intermediate actions given a visual observation of a start and a goal state. However, future interactive AI systems must also be able to plan procedures using multi-modal input, e.g., where visual observations are augm… ▽ More We propose CLAD, a Constrained Latent Action Diffusion model for vision-language procedure planning in instructional videos. Procedure planning is the challenging task of predicting intermediate actions given a visual observation of a start and a goal state. However, future interactive AI systems must also be able to plan procedures using multi-modal input, e.g., where visual observations are augmented with language descriptions. To tackle this vision-language procedure planning task, our method uses a Variational Autoencoder (VAE) to learn the latent representation of actions and observations as constraints and integrate them into the diffusion process. This approach exploits that the latent space of diffusion models already has semantics that can be used. We use the latent constraints to steer the diffusion model to better generate actions. We report extensive experiments on the popular CrossTask, Coin, and NIV datasets and show that our method outperforms state-of-the-art methods by a large margin. By evaluating ablated versions of our method, we further show that the proposed integration of the action and observation representations learnt in the VAE latent space is key to these performance improvements. △ Less

Submitted 15 June, 2026; v1 submitted 9 March, 2025; originally announced March 2025.

Comments: Accepted at RO-MAN 2026

V$^2$Dial: Unification of Video and Visual Dialog via Multimodal Experts

Authors: Adnen Abdessaied, Anna Rohrbach, Marcus Rohrbach, Andreas Bulling

Abstract: We present V$^2$Dial - a novel expert-based model specifically geared towards simultaneously handling image and video input data for multimodal conversational tasks. Current multimodal models primarily focus on simpler tasks (e.g., VQA, VideoQA, video-text retrieval) and often neglect the more challenging conversational counterparts, such as video and visual/image dialog. Moreover, works on both c… ▽ More We present V$^2$Dial - a novel expert-based model specifically geared towards simultaneously handling image and video input data for multimodal conversational tasks. Current multimodal models primarily focus on simpler tasks (e.g., VQA, VideoQA, video-text retrieval) and often neglect the more challenging conversational counterparts, such as video and visual/image dialog. Moreover, works on both conversational tasks evolved separately from each other despite their apparent similarities limiting their applicability potential. To this end, we propose to unify both tasks using a single model that for the first time jointly learns the spatial and temporal features of images and videos by routing them through dedicated experts and aligns them using matching and contrastive learning techniques. Furthermore, we systemically study the domain shift between the two tasks by investigating whether and to what extent these seemingly related tasks can mutually benefit from their respective training data. Extensive evaluations on the widely used video and visual dialog datasets of AVSD and VisDial show that our model achieves new state-of-the-art results across four benchmarks both in zero-shot and fine-tuning settings. △ Less

Submitted 14 March, 2025; v1 submitted 3 March, 2025; originally announced March 2025.

Comments: CVPR 2025

Grid Labeling: Crowdsourcing Task-Specific Importance from Visualizations

Authors: Minsuk Chang, Yao Wang, Huichen Will Wang, Andreas Bulling, Cindy Xiong Bearfield

Abstract: Knowing where people look in visualizations is key to effective design. Yet, existing research primarily focuses on free-viewing-based saliency models - although visual attention is inherently task-dependent. Collecting task-relevant importance data remains a resource-intensive challenge. To address this, we introduce Grid Labeling - a novel annotation method for collecting task-specific importanc… ▽ More Knowing where people look in visualizations is key to effective design. Yet, existing research primarily focuses on free-viewing-based saliency models - although visual attention is inherently task-dependent. Collecting task-relevant importance data remains a resource-intensive challenge. To address this, we introduce Grid Labeling - a novel annotation method for collecting task-specific importance data to enhance saliency prediction models. Grid Labeling dynamically segments visualizations into Adaptive Grids, enabling efficient, low-effort annotation while adapting to visualization structure. We conducted a human subject study comparing Grid Labeling with existing annotation methods, ImportAnnots, and BubbleView across multiple metrics. Results show that Grid Labeling produces the least noisy data and the highest inter-participant agreement with fewer participants while requiring less physical (e.g., clicks/mouse movements) and cognitive effort. An interactive demo is available at https://jangsus1.github.io/Grid-Labeling. △ Less

Submitted 28 April, 2025; v1 submitted 19 February, 2025; originally announced February 2025.

Comments: 6 pages, 4 figures, Accepted to EuroVis 2025 (Short Paper Track)

Chartist: Task-driven Eye Movement Control for Chart Reading

Authors: Danqing Shi, Yao Wang, Yunpeng Bai, Andreas Bulling, Antti Oulasvirta

Abstract: To design data visualizations that are easy to comprehend, we need to understand how people with different interests read them. Computational models of predicting scanpaths on charts could complement empirical studies by offering estimates of user performance inexpensively; however, previous models have been limited to gaze patterns and overlooked the effects of tasks. Here, we contribute Chartist… ▽ More To design data visualizations that are easy to comprehend, we need to understand how people with different interests read them. Computational models of predicting scanpaths on charts could complement empirical studies by offering estimates of user performance inexpensively; however, previous models have been limited to gaze patterns and overlooked the effects of tasks. Here, we contribute Chartist, a computational model that simulates how users move their eyes to extract information from the chart in order to perform analysis tasks, including value retrieval, filtering, and finding extremes. The novel contribution lies in a two-level hierarchical control architecture. At the high level, the model uses LLMs to comprehend the information gained so far and applies this representation to select a goal for the lower-level controllers, which, in turn, move the eyes in accordance with a sampling policy learned via reinforcement learning. The model is capable of predicting human-like task-driven scanpaths across various tasks. It can be applied in fields such as explainable AI, visualization design evaluation, and optimization. While it displays limitations in terms of generalizability and accuracy, it takes modeling in a promising direction, toward understanding human behaviors in interacting with charts. △ Less

Submitted 5 February, 2025; originally announced February 2025.

HAIFAI: Human-AI Interaction for Mental Face Reconstruction

Authors: Florian Strohm, Mihai Bâce, Andreas Bulling

Abstract: We present HAIFAI - a novel two-stage system where humans and AI interact to tackle the challenging task of reconstructing a visual representation of a face that exists only in a person's mind. In the first stage, users iteratively rank images our reconstruction system presents based on their resemblance to a mental image. These rankings, in turn, allow the system to extract relevant image feature… ▽ More We present HAIFAI - a novel two-stage system where humans and AI interact to tackle the challenging task of reconstructing a visual representation of a face that exists only in a person's mind. In the first stage, users iteratively rank images our reconstruction system presents based on their resemblance to a mental image. These rankings, in turn, allow the system to extract relevant image features, fuse them into a unified feature vector, and use a generative model to produce an initial reconstruction of the mental image. The second stage leverages an existing face editing method, allowing users to manually refine and further improve this reconstruction using an easy-to-use slider interface for face shape manipulation. To avoid the need for tedious human data collection for training the reconstruction system, we introduce a computational user model of human ranking behaviour. For this, we collected a small face ranking dataset through an online crowd-sourcing study containing data from 275 participants. We evaluate HAIFAI and an ablated version in a 12-participant user study and demonstrate that our approach outperforms the previous state of the art regarding reconstruction quality, usability, perceived workload, and reconstruction speed. We further validate the reconstructions in a subsequent face ranking study with 18 participants and show that HAIFAI achieves a new state-of-the-art identification rate of 60.6%. These findings represent a significant advancement towards developing new interactive intelligent systems capable of reliably and effortlessly reconstructing a user's mental image. △ Less

Submitted 25 February, 2025; v1 submitted 9 December, 2024; originally announced December 2024.

HaHeAE: Learning Generalisable Joint Representations of Human Hand and Head Movements in Extended Reality

Authors: Zhiming Hu, Guanhua Zhang, Zheming Yin, Daniel Haeufle, Syn Schmitt, Andreas Bulling

Abstract: Human hand and head movements are the most pervasive input modalities in extended reality (XR) and are significant for a wide range of applications. However, prior works on hand and head modelling in XR only explored a single modality or focused on specific applications. We present HaHeAE - a novel self-supervised method for learning generalisable joint representations of hand and head movements i… ▽ More Human hand and head movements are the most pervasive input modalities in extended reality (XR) and are significant for a wide range of applications. However, prior works on hand and head modelling in XR only explored a single modality or focused on specific applications. We present HaHeAE - a novel self-supervised method for learning generalisable joint representations of hand and head movements in XR. At the core of our method is an autoencoder (AE) that uses a graph convolutional network-based semantic encoder and a diffusion-based stochastic encoder to learn the joint semantic and stochastic representations of hand-head movements. It also features a diffusion-based decoder to reconstruct the original signals. Through extensive evaluations on three public XR datasets, we show that our method 1) significantly outperforms commonly used self-supervised methods by up to 74.0% in terms of reconstruction quality and is generalisable across users, activities, and XR environments, 2) enables new applications, including interpretable hand-head cluster identification and variable hand-head movement generation, and 3) can serve as an effective feature extractor for downstream tasks. Together, these results demonstrate the effectiveness of our method and underline the potential of self-supervised methods for jointly modelling hand-head behaviours in extended reality. △ Less

Submitted 16 May, 2025; v1 submitted 21 October, 2024; originally announced October 2024.

Comments: Link: https://zhiminghu.net/hu25_haheae

SummAct: Uncovering User Intentions Through Interactive Behaviour Summarisation

Authors: Guanhua Zhang, Mohamed Ahmed, Zhiming Hu, Andreas Bulling

Abstract: Recent work has highlighted the potential of modelling interactive behaviour analogously to natural language. We propose interactive behaviour summarisation as a novel computational task and demonstrate its usefulness for automatically uncovering latent user intentions while interacting with graphical user interfaces. To tackle this task, we introduce SummAct, a novel hierarchical method to summar… ▽ More Recent work has highlighted the potential of modelling interactive behaviour analogously to natural language. We propose interactive behaviour summarisation as a novel computational task and demonstrate its usefulness for automatically uncovering latent user intentions while interacting with graphical user interfaces. To tackle this task, we introduce SummAct, a novel hierarchical method to summarise low-level input actions into high-level intentions. SummAct first identifies sub-goals from user actions using a large language model and in-context learning. High-level intentions are then obtained by fine-tuning the model using a novel UI element attention to preserve detailed context information embedded within UI elements during summarisation. Through a series of evaluations, we demonstrate that SummAct significantly outperforms baselines across desktop and mobile interfaces as well as interactive tasks by up to 21.9%. We further show three exciting interactive applications benefited from SummAct: interactive behaviour forecasting, automatic behaviour synonym identification, and language-based behaviour retrieval. △ Less

Submitted 10 October, 2024; originally announced October 2024.

DiffEyeSyn: Diffusion-based User-specific Eye Movement Synthesis

Authors: Chuhan Jiao, Guanhua Zhang, Yeonjoo Cho, Zhiming Hu, Andreas Bulling

Abstract: High-frequency gaze data contains more user-specific information than low-frequency data, promising for various applications. However, existing gaze modelling methods focus on low-frequency data, ignoring user-specific subtle eye movements in high-frequency eye movements. We present DiffEyeSyn -- the first computational method to synthesise eye movements specific to individual users. The key idea… ▽ More High-frequency gaze data contains more user-specific information than low-frequency data, promising for various applications. However, existing gaze modelling methods focus on low-frequency data, ignoring user-specific subtle eye movements in high-frequency eye movements. We present DiffEyeSyn -- the first computational method to synthesise eye movements specific to individual users. The key idea is to consider the user-specific information as a special type of noise in eye movement data. This perspective reshapes eye movement synthesis into the task of injecting this user-specific noise into any given eye movement sequence. We formulate this injection task as a conditional diffusion process in which the synthesis is conditioned on user-specific embeddings extracted from the gaze data using pre-trained models for user authentication. We propose user identity guidance -- a novel loss function that allows our model to preserve user identity while generating human-like eye movements in the spatial domain. Experiments on two public datasets show that our synthetic eye movements preserve user-specific characteristics and are more realistic than baseline approaches. Furthermore, we demonstrate that DiffEyeSyn can synthesise large-scale gaze data and support various downstream tasks, such as gaze-based user identification. As such, our work lays the methodological foundations for personalised eye movement synthesis that has significant application potential, such as for character animation, eye movement biometrics, and gaze data imputation. △ Less

Submitted 20 May, 2025; v1 submitted 2 September, 2024; originally announced September 2024.

Comments: Corrected bugs in creating visualisations

MultiMediate'24: Multi-Domain Engagement Estimation

Authors: Philipp Müller, Michal Balazia, Tobias Baur, Michael Dietz, Alexander Heimerl, Anna Penzkofer, Dominik Schiller, François Brémond, Jan Alexandersson, Elisabeth André, Andreas Bulling

Abstract: Estimating the momentary level of participant's engagement is an important prerequisite for assistive systems that support human interactions. Previous work has addressed this task in within-domain evaluation scenarios, i.e. training and testing on the same dataset. This is in contrast to real-life scenarios where domain shifts between training and testing data frequently occur. With MultiMediate'… ▽ More Estimating the momentary level of participant's engagement is an important prerequisite for assistive systems that support human interactions. Previous work has addressed this task in within-domain evaluation scenarios, i.e. training and testing on the same dataset. This is in contrast to real-life scenarios where domain shifts between training and testing data frequently occur. With MultiMediate'24, we present the first challenge addressing multi-domain engagement estimation. As training data, we utilise the NOXI database of dyadic novice-expert interactions. In addition to within-domain test data, we add two new test domains. First, we introduce recordings following the NOXI protocol but covering languages that are not present in the NOXI training data. Second, we collected novel engagement annotations on the MPIIGroupInteraction dataset which consists of group discussions between three to four people. In this way, MultiMediate'24 evaluates the ability of approaches to generalise across factors such as language and cultural background, group size, task, and screen-mediated vs. face-to-face interaction. This paper describes the MultiMediate'24 challenge and presents baseline results. In addition, we discuss selected challenge solutions. △ Less

Submitted 29 August, 2024; originally announced August 2024.

Comments: arXiv admin note: text overlap with arXiv:2308.08256

Amortized Bayesian Multilevel Models

Authors: Daniel Habermann, Marvin Schmitt, Lars Kühmichel, Andreas Bulling, Stefan T. Radev, Paul-Christian Bürkner

Abstract: Multilevel models (MLMs) are a central building block of the Bayesian workflow. They enable joint, interpretable modeling of data across hierarchical levels and provide a fully probabilistic quantification of uncertainty. Despite their well-recognized advantages, MLMs pose significant computational challenges, often rendering their estimation and evaluation intractable within reasonable time const… ▽ More Multilevel models (MLMs) are a central building block of the Bayesian workflow. They enable joint, interpretable modeling of data across hierarchical levels and provide a fully probabilistic quantification of uncertainty. Despite their well-recognized advantages, MLMs pose significant computational challenges, often rendering their estimation and evaluation intractable within reasonable time constraints. Recent advances in simulation-based inference offer promising solutions for addressing complex probabilistic models using deep generative networks. However, the utility and reliability of deep learning methods for estimating Bayesian MLMs remains largely unexplored, especially when compared with gold-standard samplers. To this end, we explore a family of neural network architectures that leverage the probabilistic factorization of multilevel models to facilitate efficient neural network training and subsequent near-instant posterior inference on unseen datasets. We test our method on several real-world case studies and provide comprehensive comparisons to Stan's gold standard sampler, where possible. Finally, we provide an open-source implementation of our methods to stimulate further research in the nascent field of amortized Bayesian inference. △ Less

Submitted 16 June, 2025; v1 submitted 23 August, 2024; originally announced August 2024.

Comments: 24 pages, 13 figures

Explicit Modelling of Theory of Mind for Belief Prediction in Nonverbal Social Interactions

Authors: Matteo Bortoletto, Constantin Ruhdorfer, Lei Shi, Andreas Bulling

Abstract: We propose MToMnet - a Theory of Mind (ToM) neural network for predicting beliefs and their dynamics during human social interactions from multimodal input. ToM is key for effective nonverbal human communication and collaboration, yet, existing methods for belief modelling have not included explicit ToM modelling or have typically been limited to one or two modalities. MToMnet encodes contextual c… ▽ More We propose MToMnet - a Theory of Mind (ToM) neural network for predicting beliefs and their dynamics during human social interactions from multimodal input. ToM is key for effective nonverbal human communication and collaboration, yet, existing methods for belief modelling have not included explicit ToM modelling or have typically been limited to one or two modalities. MToMnet encodes contextual cues (scene videos and object locations) and integrates them with person-specific cues (human gaze and body language) in a separate MindNet for each person. Inspired by prior research on social cognition and computational ToM, we propose three different MToMnet variants: two involving fusion of latent representations and one involving re-ranking of classification scores. We evaluate our approach on two challenging real-world datasets, one focusing on belief prediction, while the other examining belief dynamics prediction. Our results demonstrate that MToMnet surpasses existing methods by a large margin while at the same time requiring a significantly smaller number of parameters. Taken together, our method opens up a highly promising direction for future work on artificial intelligent systems that can robustly predict human beliefs from their non-verbal behaviour and, as such, more effectively collaborate with humans. △ Less

Submitted 28 August, 2024; v1 submitted 9 July, 2024; originally announced July 2024.

Comments: ECAI 2024

HOIMotion: Forecasting Human Motion During Human-Object Interactions Using Egocentric 3D Object Bounding Boxes

Authors: Zhiming Hu, Zheming Yin, Daniel Haeufle, Syn Schmitt, Andreas Bulling

Abstract: We present HOIMotion - a novel approach for human motion forecasting during human-object interactions that integrates information about past body poses and egocentric 3D object bounding boxes. Human motion forecasting is important in many augmented reality applications but most existing methods have only used past body poses to predict future motion. HOIMotion first uses an encoder-residual graph… ▽ More We present HOIMotion - a novel approach for human motion forecasting during human-object interactions that integrates information about past body poses and egocentric 3D object bounding boxes. Human motion forecasting is important in many augmented reality applications but most existing methods have only used past body poses to predict future motion. HOIMotion first uses an encoder-residual graph convolutional network (GCN) and multi-layer perceptrons to extract features from body poses and egocentric 3D object bounding boxes, respectively. Our method then fuses pose and object features into a novel pose-object graph and uses a residual-decoder GCN to forecast future body motion. We extensively evaluate our method on the Aria digital twin (ADT) and MoGaze datasets and show that HOIMotion consistently outperforms state-of-the-art methods by a large margin of up to 8.7% on ADT and 7.2% on MoGaze in terms of mean per joint position error. Complementing these evaluations, we report a human study (N=20) that shows that the improvements achieved by our method result in forecasted poses being perceived as both more precise and more realistic than those of existing methods. Taken together, these results reveal the significant information content available in egocentric 3D object bounding boxes for human motion forecasting and the effectiveness of our method in exploiting this information. △ Less

Submitted 2 July, 2024; originally announced July 2024.

Comments: Accepted at ISMAR 2024 TVCG-track, zhiminghu.net/hu24_hoimotion.html. arXiv admin note: text overlap with arXiv:2403.09885

Multi-Modal Video Dialog State Tracking in the Wild

Authors: Adnen Abdessaied, Lei Shi, Andreas Bulling

Abstract: We present MST-MIXER - a novel video dialog model operating over a generic multi-modal state tracking scheme. Current models that claim to perform multi-modal state tracking fall short of two major aspects: (1) They either track only one modality (mostly the visual input) or (2) they target synthetic datasets that do not reflect the complexity of real-world in the wild scenarios. Our model address… ▽ More We present MST-MIXER - a novel video dialog model operating over a generic multi-modal state tracking scheme. Current models that claim to perform multi-modal state tracking fall short of two major aspects: (1) They either track only one modality (mostly the visual input) or (2) they target synthetic datasets that do not reflect the complexity of real-world in the wild scenarios. Our model addresses these two limitations in an attempt to close this crucial research gap. Specifically, MST-MIXER first tracks the most important constituents of each input modality. Then, it predicts the missing underlying structure of the selected constituents of each modality by learning local latent graphs using a novel multi-modal graph structure learning method. Subsequently, the learned local graphs and features are parsed together to form a global graph operating on the mix of all modalities which further refines its structure and node embeddings. Finally, the fine-grained graph node features are used to enhance the hidden states of the backbone Vision-Language Model (VLM). MST-MIXER achieves new state-of-the-art results on five challenging benchmarks. △ Less

Submitted 5 July, 2024; v1 submitted 2 July, 2024; originally announced July 2024.

Comments: ECCV 2024

The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design

Authors: Constantin Ruhdorfer, Matteo Bortoletto, Anna Penzkofer, Andreas Bulling

Abstract: We introduce the Overcooked Generalisation Challenge (OGC) - a new benchmark for evaluating reinforcement learning (RL) agents on their ability to cooperate with unknown partners in unfamiliar environments. Existing work typically evaluated cooperative RL only in their training environment or with their training partners, thus seriously limiting our ability to understand agents' generalisation cap… ▽ More We introduce the Overcooked Generalisation Challenge (OGC) - a new benchmark for evaluating reinforcement learning (RL) agents on their ability to cooperate with unknown partners in unfamiliar environments. Existing work typically evaluated cooperative RL only in their training environment or with their training partners, thus seriously limiting our ability to understand agents' generalisation capacity - an essential requirement for future collaboration with humans. The OGC extends Overcooked-AI to support dual curriculum design (DCD). It is fully GPU-accelerated, open-source, and integrated into the minimax DCD benchmark suite. Compared to prior DCD benchmarks, where designers manipulate only minimal elements of the environment, OGC introduces a significantly richer design space: full kitchen layouts with multiple objects that require the designer to account for interaction dynamics between agents. We evaluate state-of-the-art DCD algorithms alongside scalable neural architectures and find that current methods fail to produce agents that generalise effectively to novel layouts and unfamiliar partners. Our results indicate that both agents and curriculum designers struggle with the joint challenge of partner and environment generalisation. These findings establish OGC as a demanding testbed for cooperative generalisation and highlight key directions for future research. We open-source our code. △ Less

Submitted 12 September, 2025; v1 submitted 25 June, 2024; originally announced June 2024.

Comments: TMLR, 31 pages

Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Models

Authors: Matteo Bortoletto, Constantin Ruhdorfer, Lei Shi, Andreas Bulling

Abstract: Despite growing interest in Theory of Mind (ToM) tasks for evaluating language models (LMs), little is known about how LMs internally represent mental states of self and others. Understanding these internal mechanisms is critical - not only to move beyond surface-level performance, but also for model alignment and safety, where subtle misattributions of mental states may go undetected in generated… ▽ More Despite growing interest in Theory of Mind (ToM) tasks for evaluating language models (LMs), little is known about how LMs internally represent mental states of self and others. Understanding these internal mechanisms is critical - not only to move beyond surface-level performance, but also for model alignment and safety, where subtle misattributions of mental states may go undetected in generated outputs. In this work, we present the first systematic investigation of belief representations in LMs by probing models across different scales, training regimens, and prompts - using control tasks to rule out confounds. Our experiments provide evidence that both model size and fine-tuning substantially improve LMs' internal representations of others' beliefs, which are structured - not mere by-products of spurious correlations - yet brittle to prompt variations. Crucially, we show that these representations can be strengthened: targeted edits to model activations can correct wrong ToM inferences. △ Less

Submitted 19 May, 2025; v1 submitted 25 June, 2024; originally announced June 2024.

Comments: ICML 2024 Workshop on Mechanistic Interpretability version: https://openreview.net/forum?id=yEwEVoH9Be

Limits of Theory of Mind Modelling in Dialogue-Based Collaborative Plan Acquisition

Authors: Matteo Bortoletto, Constantin Ruhdorfer, Adnen Abdessaied, Lei Shi, Andreas Bulling

Abstract: Recent work on dialogue-based collaborative plan acquisition (CPA) has suggested that Theory of Mind (ToM) modelling can improve missing knowledge prediction in settings with asymmetric skill-sets and knowledge. Although ToM was claimed to be important for effective collaboration, its real impact on this novel task remains under-explored. By representing plans as graphs and by exploiting task-spec… ▽ More Recent work on dialogue-based collaborative plan acquisition (CPA) has suggested that Theory of Mind (ToM) modelling can improve missing knowledge prediction in settings with asymmetric skill-sets and knowledge. Although ToM was claimed to be important for effective collaboration, its real impact on this novel task remains under-explored. By representing plans as graphs and by exploiting task-specific constraints we show that, as performance on CPA nearly doubles when predicting one's own missing knowledge, the improvements due to ToM modelling diminish. This phenomenon persists even when evaluating existing baseline methods. To better understand the relevance of ToM for CPA, we report a principled performance comparison of models with and without ToM features. Results across different models and ablations consistently suggest that learned ToM features are indeed more likely to reflect latent patterns in the data with no perceivable link to ToM. This finding calls for a deeper understanding of the role of ToM in CPA and beyond, as well as new methods for modelling and evaluating mental states in computational collaborative agents. △ Less

Submitted 28 May, 2024; v1 submitted 21 May, 2024; originally announced May 2024.

Comments: ACL 2024

VSA4VQA: Scaling a Vector Symbolic Architecture to Visual Question Answering on Natural Images

Authors: Anna Penzkofer, Lei Shi, Andreas Bulling

Abstract: While Vector Symbolic Architectures (VSAs) are promising for modelling spatial cognition, their application is currently limited to artificially generated images and simple spatial queries. We propose VSA4VQA - a novel 4D implementation of VSAs that implements a mental representation of natural images for the challenging task of Visual Question Answering (VQA). VSA4VQA is the first model to scale… ▽ More While Vector Symbolic Architectures (VSAs) are promising for modelling spatial cognition, their application is currently limited to artificially generated images and simple spatial queries. We propose VSA4VQA - a novel 4D implementation of VSAs that implements a mental representation of natural images for the challenging task of Visual Question Answering (VQA). VSA4VQA is the first model to scale a VSA to complex spatial queries. Our method is based on the Semantic Pointer Architecture (SPA) to encode objects in a hyperdimensional vector space. To encode natural images, we extend the SPA to include dimensions for object's width and height in addition to their spatial location. To perform spatial queries we further introduce learned spatial query masks and integrate a pre-trained vision-language model for answering attribute-related questions. We evaluate our method on the GQA benchmark dataset and show that it can effectively encode natural images, achieving competitive performance to state-of-the-art deep learning methods for zero-shot VQA. △ Less

Submitted 6 May, 2024; originally announced May 2024.

Comments: To be published in the Proceedings of the Annual Meeting of the Cognitive Science Society (CogSci'24)

DiffGaze: A Diffusion Model for Continuous Gaze Sequence Generation on 360° Images

Authors: Chuhan Jiao, Yao Wang, Guanhua Zhang, Mihai Bâce, Zhiming Hu, Andreas Bulling

Abstract: We present DiffGaze, a novel method for generating realistic and diverse continuous human gaze sequences on 360° images based on a conditional score-based denoising diffusion model. Generating human gaze on 360° images is important for various human-computer interaction and computer graphics applications, e.g. for creating large-scale eye tracking datasets or for realistic animation of virtual hum… ▽ More We present DiffGaze, a novel method for generating realistic and diverse continuous human gaze sequences on 360° images based on a conditional score-based denoising diffusion model. Generating human gaze on 360° images is important for various human-computer interaction and computer graphics applications, e.g. for creating large-scale eye tracking datasets or for realistic animation of virtual humans. However, existing methods are limited to predicting discrete fixation sequences or aggregated saliency maps, thereby neglecting crucial parts of natural gaze behaviour. Our method uses features extracted from 360° images as condition and uses two transformers to model the temporal and spatial dependencies of continuous human gaze. We evaluate DiffGaze on two 360° image benchmarks for gaze sequence generation as well as scanpath prediction and saliency prediction. Our evaluations show that DiffGaze outperforms state-of-the-art methods on all tasks on both benchmarks. We also report a 21-participant user study showing that our method generates gaze sequences that are indistinguishable from real human sequences. △ Less

Submitted 26 March, 2024; originally announced March 2024.

UP-FacE: User-predictable Fine-grained Face Shape Editing

Authors: Florian Strohm, Mihai Bâce, Andreas Bulling

Abstract: We present User-predictable Face Editing (UP-FacE) -- a novel method for predictable face shape editing. In stark contrast to existing methods for face editing using trial and error, edits with UP-FacE are predictable by the human user. That is, users can control the desired degree of change precisely and deterministically and know upfront the amount of change required to achieve a certain editing… ▽ More We present User-predictable Face Editing (UP-FacE) -- a novel method for predictable face shape editing. In stark contrast to existing methods for face editing using trial and error, edits with UP-FacE are predictable by the human user. That is, users can control the desired degree of change precisely and deterministically and know upfront the amount of change required to achieve a certain editing result. Our method leverages facial landmarks to precisely measure facial feature values, facilitating the training of UP-FacE without manually annotated attribute labels. At the core of UP-FacE is a transformer-based network that takes as input a latent vector from a pre-trained generative model and a facial feature embedding, and predicts a suitable manipulation vector. To enable user-predictable editing, a scaling layer adjusts the manipulation vector to achieve the precise desired degree of change. To ensure that the desired feature is manipulated towards the target value without altering uncorrelated features, we further introduce a novel semantic face feature loss. Qualitative and quantitative results demonstrate that UP-FacE enables precise and fine-grained control over 23 face shape features. △ Less

Submitted 11 July, 2024; v1 submitted 20 March, 2024; originally announced March 2024.

Learning User Embeddings from Human Gaze for Personalised Saliency Prediction

Authors: Florian Strohm, Mihai Bâce, Andreas Bulling

Abstract: Reusable embeddings of user behaviour have shown significant performance improvements for the personalised saliency prediction task. However, prior works require explicit user characteristics and preferences as input, which are often difficult to obtain. We present a novel method to extract user embeddings from pairs of natural images and corresponding saliency maps generated from a small amount o… ▽ More Reusable embeddings of user behaviour have shown significant performance improvements for the personalised saliency prediction task. However, prior works require explicit user characteristics and preferences as input, which are often difficult to obtain. We present a novel method to extract user embeddings from pairs of natural images and corresponding saliency maps generated from a small amount of user-specific eye tracking data. At the core of our method is a Siamese convolutional neural encoder that learns the user embeddings by contrasting the image and personal saliency map pairs of different users. Evaluations on two public saliency datasets show that the generated embeddings have high discriminative power, are effective at refining universal saliency maps to the individual users, and generalise well across users and images. Finally, based on our model's ability to encode individual user characteristics, our work points towards other applications that can benefit from reusable embeddings of gaze behaviour. △ Less

Submitted 26 March, 2024; v1 submitted 20 March, 2024; originally announced March 2024.

GazeMotion: Gaze-guided Human Motion Forecasting

Authors: Zhiming Hu, Syn Schmitt, Daniel Haeufle, Andreas Bulling

Abstract: We present GazeMotion, a novel method for human motion forecasting that combines information on past human poses with human eye gaze. Inspired by evidence from behavioural sciences showing that human eye and body movements are closely coordinated, GazeMotion first predicts future eye gaze from past gaze, then fuses predicted future gaze and past poses into a gaze-pose graph, and finally uses a res… ▽ More We present GazeMotion, a novel method for human motion forecasting that combines information on past human poses with human eye gaze. Inspired by evidence from behavioural sciences showing that human eye and body movements are closely coordinated, GazeMotion first predicts future eye gaze from past gaze, then fuses predicted future gaze and past poses into a gaze-pose graph, and finally uses a residual graph convolutional network to forecast body motion. We extensively evaluate our method on the MoGaze, ADT, and GIMO benchmark datasets and show that it outperforms state-of-the-art methods by up to 7.4% improvement in mean per joint position error. Using head direction as a proxy to gaze, our method still achieves an average improvement of 5.5%. We finally report an online user study showing that our method also outperforms prior methods in terms of perceived realism. These results show the significant information content available in eye gaze for human motion forecasting as well as the effectiveness of our method in exploiting this information. △ Less

Submitted 11 July, 2024; v1 submitted 14 March, 2024; originally announced March 2024.

Comments: Accepted at IROS 2024 as Oral Presentation. Code available at https://zhiminghu.net/hu24_gazemotion.html

ActionDiffusion: An Action-aware Diffusion Model for Procedure Planning in Instructional Videos

Authors: Lei Shi, Paul Bürkner, Andreas Bulling

Abstract: We present ActionDiffusion -- a novel diffusion model for procedure planning in instructional videos that is the first to take temporal inter-dependencies between actions into account in a diffusion model for procedure planning. This approach is in stark contrast to existing methods that fail to exploit the rich information content available in the particular order in which actions are performed.… ▽ More We present ActionDiffusion -- a novel diffusion model for procedure planning in instructional videos that is the first to take temporal inter-dependencies between actions into account in a diffusion model for procedure planning. This approach is in stark contrast to existing methods that fail to exploit the rich information content available in the particular order in which actions are performed. Our method unifies the learning of temporal dependencies between actions and denoising of the action plan in the diffusion process by projecting the action information into the noise space. This is achieved 1) by adding action embeddings in the noise masks in the noise-adding phase and 2) by introducing an attention mechanism in the noise prediction network to learn the correlations between different action steps. We report extensive experiments on three instructional video benchmark datasets (CrossTask, Coin, and NIV) and show that our method outperforms previous state-of-the-art methods on all metrics on CrossTask and NIV and all metrics except accuracy on Coin dataset. We show that by adding action embeddings into the noise mask the diffusion model can better learn action temporal dependencies and increase the performances on procedure planning. △ Less

Submitted 20 July, 2024; v1 submitted 13 March, 2024; originally announced March 2024.

PrivatEyes: Appearance-based Gaze Estimation Using Federated Secure Multi-Party Computation

Authors: Mayar Elfares, Pascal Reisert, Zhiming Hu, Wenwu Tang, Ralf Küsters, Andreas Bulling

Abstract: Latest gaze estimation methods require large-scale training data but their collection and exchange pose significant privacy risks. We propose PrivatEyes - the first privacy-enhancing training approach for appearance-based gaze estimation based on federated learning (FL) and secure multi-party computation (MPC). PrivatEyes enables training gaze estimators on multiple local datasets across different… ▽ More Latest gaze estimation methods require large-scale training data but their collection and exchange pose significant privacy risks. We propose PrivatEyes - the first privacy-enhancing training approach for appearance-based gaze estimation based on federated learning (FL) and secure multi-party computation (MPC). PrivatEyes enables training gaze estimators on multiple local datasets across different users and server-based secure aggregation of the individual estimators' updates. PrivatEyes guarantees that individual gaze data remains private even if a majority of the aggregating servers is malicious. We also introduce a new data leakage attack DualView that shows that PrivatEyes limits the leakage of private training data more effectively than previous approaches. Evaluations on the MPIIGaze, MPIIFaceGaze, GazeCapture, and NVGaze datasets further show that the improved privacy does not lead to a lower gaze estimation accuracy or substantially higher computational costs - both of which are on par with its non-secure counterparts. △ Less

Submitted 29 February, 2024; originally announced February 2024.

Generating Realistic Arm Movements in Reinforcement Learning: A Quantitative Comparison of Reward Terms and Task Requirements

Authors: Jhon P. F. Charaja, Isabell Wochner, Pierre Schumacher, Winfried Ilg, Martin Giese, Christophe Maufroy, Andreas Bulling, Syn Schmitt, Georg Martius, Daniel F. B. Haeufle

Abstract: The mimicking of human-like arm movement characteristics involves the consideration of three factors during control policy synthesis: (a) chosen task requirements, (b) inclusion of noise during movement execution and (c) chosen optimality principles. Previous studies showed that when considering these factors (a-c) individually, it is possible to synthesize arm movements that either kinematically… ▽ More The mimicking of human-like arm movement characteristics involves the consideration of three factors during control policy synthesis: (a) chosen task requirements, (b) inclusion of noise during movement execution and (c) chosen optimality principles. Previous studies showed that when considering these factors (a-c) individually, it is possible to synthesize arm movements that either kinematically match the experimental data or reproduce the stereotypical triphasic muscle activation pattern. However, to date no quantitative comparison has been made on how realistic the arm movement generated by each factor is; as well as whether a partial or total combination of all factors results in arm movements with human-like kinematic characteristics and a triphasic muscle pattern. To investigate this, we used reinforcement learning to learn a control policy for a musculoskeletal arm model, aiming to discern which combination of factors (a-c) results in realistic arm movements according to four frequently reported stereotypical characteristics. Our findings indicate that incorporating velocity and acceleration requirements into the reaching task, employing reward terms that encourage minimization of mechanical work, hand jerk, and control effort, along with the inclusion of noise during movement, leads to the emergence of realistic human arm movements in reinforcement learning. We expect that the gained insights will help in the future to better predict desired arm movements and corrective forces in wearable assistive devices. △ Less

Submitted 27 November, 2024; v1 submitted 21 February, 2024; originally announced February 2024.

OLViT: Multi-Modal State Tracking via Attention-Based Embeddings for Video-Grounded Dialog

Authors: Adnen Abdessaied, Manuel von Hochmeister, Andreas Bulling

Abstract: We present the Object Language Video Transformer (OLViT) - a novel model for video dialog operating over a multi-modal attention-based dialog state tracker. Existing video dialog models struggle with questions requiring both spatial and temporal localization within videos, long-term temporal reasoning, and accurate object tracking across multiple dialog turns. OLViT addresses these challenges by m… ▽ More We present the Object Language Video Transformer (OLViT) - a novel model for video dialog operating over a multi-modal attention-based dialog state tracker. Existing video dialog models struggle with questions requiring both spatial and temporal localization within videos, long-term temporal reasoning, and accurate object tracking across multiple dialog turns. OLViT addresses these challenges by maintaining a global dialog state based on the output of an Object State Tracker (OST) and a Language State Tracker (LST): while the OST attends to the most important objects within the video, the LST keeps track of the most important linguistic co-references to previous dialog turns. In stark contrast to previous works, our approach is generic by nature and is therefore capable of learning continuous multi-modal dialog state representations of the most relevant objects and rounds. As a result, they can be seamlessly integrated into Large Language Models (LLMs) and offer high flexibility in dealing with different datasets and tasks. Evaluations on the challenging DVD (response classification) and SIMMC 2.1 (response generation) datasets show that OLViT achieves new state-of-the-art performance across both datasets. △ Less

Submitted 20 February, 2024; originally announced February 2024.

Comments: COLING 2024

Mindful Explanations: Prevalence and Impact of Mind Attribution in XAI Research

Authors: Susanne Hindennach, Lei Shi, Filip Miletić, Andreas Bulling

Abstract: When users perceive AI systems as mindful, independent agents, they hold them responsible instead of the AI experts who created and designed these systems. So far, it has not been studied whether explanations support this shift in responsibility through the use of mind-attributing verbs like "to think". To better understand the prevalence of mind-attributing explanations we analyse AI explanations… ▽ More When users perceive AI systems as mindful, independent agents, they hold them responsible instead of the AI experts who created and designed these systems. So far, it has not been studied whether explanations support this shift in responsibility through the use of mind-attributing verbs like "to think". To better understand the prevalence of mind-attributing explanations we analyse AI explanations in 3,533 explainable AI (XAI) research articles from the Semantic Scholar Open Research Corpus (S2ORC). Using methods from semantic shift detection, we identify three dominant types of mind attribution: (1) metaphorical (e.g. "to learn" or "to predict"), (2) awareness (e.g. "to consider"), and (3) agency (e.g. "to make decisions"). We then analyse the impact of mind-attributing explanations on awareness and responsibility in a vignette-based experiment with 199 participants. We find that participants who were given a mind-attributing explanation were more likely to rate the AI system as aware of the harm it caused. Moreover, the mind-attributing explanation had a responsibility-concealing effect: Considering the AI experts' involvement lead to reduced ratings of AI responsibility for participants who were given a non-mind-attributing or no explanation. In contrast, participants who read the mind-attributing explanation still held the AI system responsible despite considering the AI experts' involvement. Taken together, our work underlines the need to carefully phrase explanations about AI systems in scientific writing to reduce mind attribution and clearly communicate human responsibility. △ Less

Submitted 19 December, 2023; originally announced December 2023.

Comments: 21 pages, 6 figures, to be published in PACM HCI (CSCW '24)

GazeMoDiff: Gaze-guided Diffusion Model for Stochastic Human Motion Prediction

Authors: Haodong Yan, Zhiming Hu, Syn Schmitt, Andreas Bulling

Abstract: Human motion prediction is important for many virtual and augmented reality (VR/AR) applications such as collision avoidance and realistic avatar generation. Existing methods have synthesised body motion only from observed past motion, despite the fact that human eye gaze is known to correlate strongly with body movements and is readily available in recent VR/AR headsets. We present GazeMoDiff - a… ▽ More Human motion prediction is important for many virtual and augmented reality (VR/AR) applications such as collision avoidance and realistic avatar generation. Existing methods have synthesised body motion only from observed past motion, despite the fact that human eye gaze is known to correlate strongly with body movements and is readily available in recent VR/AR headsets. We present GazeMoDiff - a novel gaze-guided denoising diffusion model to generate stochastic human motions. Our method first uses a gaze encoder and a motion encoder to extract the gaze and motion features respectively, then employs a graph attention network to fuse these features, and finally injects the gaze-motion features into a noise prediction network via a cross-attention mechanism to progressively generate multiple reasonable human motions in the future. Extensive experiments on the MoGaze and GIMO datasets demonstrate that our method outperforms the state-of-the-art methods by a large margin in terms of multi-modal final displacement error (17.3% on MoGaze and 13.3% on GIMO). We further conducted a human study (N=21) and validated that the motions generated by our method were perceived as both more precise and more realistic than those of prior methods. Taken together, these results reveal the significant information content available in eye gaze for stochastic human motion prediction as well as the effectiveness of our method in exploiting this information. △ Less

Submitted 21 October, 2024; v1 submitted 19 December, 2023; originally announced December 2023.

Comments: Accepted at PG 2024. Link: https://zhiminghu.net/yan24_gazemodiff.html

Pose2Gaze: Eye-body Coordination during Daily Activities for Gaze Prediction from Full-body Poses

Authors: Zhiming Hu, Jiahui Xu, Syn Schmitt, Andreas Bulling

Abstract: Human eye gaze plays a significant role in many virtual and augmented reality (VR/AR) applications, such as gaze-contingent rendering, gaze-based interaction, or eye-based activity recognition. However, prior works on gaze analysis and prediction have only explored eye-head coordination and were limited to human-object interactions. We first report a comprehensive analysis of eye-body coordination… ▽ More Human eye gaze plays a significant role in many virtual and augmented reality (VR/AR) applications, such as gaze-contingent rendering, gaze-based interaction, or eye-based activity recognition. However, prior works on gaze analysis and prediction have only explored eye-head coordination and were limited to human-object interactions. We first report a comprehensive analysis of eye-body coordination in various human-object and human-human interaction activities based on four public datasets collected in real-world (MoGaze), VR (ADT), as well as AR (GIMO and EgoBody) environments. We show that in human-object interactions, e.g. pick and place, eye gaze exhibits strong correlations with full-body motion while in human-human interactions, e.g. chat and teach, a person's gaze direction is correlated with the body orientation towards the interaction partner. Informed by these analyses we then present Pose2Gaze, a novel eye-body coordination model that uses a convolutional neural network and a spatio-temporal graph convolutional neural network to extract features from head direction and full-body poses, respectively, and then uses a convolutional neural network to predict eye gaze. We compare our method with state-of-the-art methods that predict eye gaze only from head movements and show that Pose2Gaze outperforms these baselines with an average improvement of 24.0% on MoGaze, 10.1% on ADT, 21.3% on GIMO, and 28.6% on EgoBody in mean angular error, respectively. We also show that our method significantly outperforms prior methods in the sample downstream task of eye-based activity recognition. These results underline the significant information content available in eye-body coordination during daily activities and open up a new direction for gaze prediction. △ Less

Submitted 10 June, 2024; v1 submitted 19 December, 2023; originally announced December 2023.

Comments: Accepted at TVCG 2024, code available at https://zhiminghu.net/hu24_pose2gaze.html

Neural Reasoning About Agents' Goals, Preferences, and Actions

Authors: Matteo Bortoletto, Lei Shi, Andreas Bulling

Abstract: We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph neural network for learning agent and world state representations with a transformer to encode the task context. When evaluated on the challenging Baby Intuiti… ▽ More We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph neural network for learning agent and world state representations with a transformer to encode the task context. When evaluated on the challenging Baby Intuitions Benchmark, IRENE achieves new state-of-the-art performance on three out of its five tasks - with up to 48.9% improvement. In contrast to existing methods, IRENE is able to bind preferences to specific agents, to better distinguish between rational and irrational agents, and to better understand the role of blocking obstacles. We also investigate, for the first time, the influence of the training tasks on test performance. Our analyses demonstrate the effectiveness of IRENE in combining prior knowledge gained during training for unseen evaluation tasks. △ Less

Submitted 12 December, 2023; originally announced December 2023.

Comments: The 38th Annual AAAI Conference on Artificial Intelligence (AAAI-24)

$\mathbb{VD}$-$\mathbb{GR}$: Boosting $\mathbb{V}$isual $\mathbb{D}$ialog with Cascaded Spatial-Temporal Multi-Modal $\mathbb{GR}$aphs

Authors: Adnen Abdessaied, Lei Shi, Andreas Bulling

Abstract: We propose $\mathbb{VD}$-$\mathbb{GR}$ - a novel visual dialog model that combines pre-trained language models (LMs) with graph neural networks (GNNs). Prior works mainly focused on one class of models at the expense of the other, thus missing out on the opportunity of combining their respective benefits. At the core of $\mathbb{VD}$-$\mathbb{GR}$ is a novel integration mechanism that alternates b… ▽ More We propose $\mathbb{VD}$-$\mathbb{GR}$ - a novel visual dialog model that combines pre-trained language models (LMs) with graph neural networks (GNNs). Prior works mainly focused on one class of models at the expense of the other, thus missing out on the opportunity of combining their respective benefits. At the core of $\mathbb{VD}$-$\mathbb{GR}$ is a novel integration mechanism that alternates between spatial-temporal multi-modal GNNs and BERT layers, and that covers three distinct contributions: First, we use multi-modal GNNs to process the features of each modality (image, question, and dialog history) and exploit their local structures before performing BERT global attention. Second, we propose hub-nodes that link to all other nodes within one modality graph, allowing the model to propagate information from one GNN (modality) to the other in a cascaded manner. Third, we augment the BERT hidden states with fine-grained multi-modal GNN features before passing them to the next $\mathbb{VD}$-$\mathbb{GR}$ layer. Evaluations on VisDial v1.0, VisDial v0.9, VisDialConv, and VisPro show that $\mathbb{VD}$-$\mathbb{GR}$ achieves new state-of-the-art results across all four datasets. △ Less

Submitted 25 October, 2023; originally announced October 2023.

Comments: WACV 2024

Inferring Human Intentions from Predicted Action Probabilities

Authors: Lei Shi, Paul-Christian Bürkner, Andreas Bulling

Abstract: Predicting the next action that a human is most likely to perform is key to human-AI collaboration and has consequently attracted increasing research interests in recent years. An important factor for next action prediction are human intentions: If the AI agent knows the intention it can predict future actions and plan collaboration more effectively. Existing Bayesian methods for this task struggl… ▽ More Predicting the next action that a human is most likely to perform is key to human-AI collaboration and has consequently attracted increasing research interests in recent years. An important factor for next action prediction are human intentions: If the AI agent knows the intention it can predict future actions and plan collaboration more effectively. Existing Bayesian methods for this task struggle with complex visual input while deep neural network (DNN) based methods do not provide uncertainty quantifications. In this work we combine both approaches for the first time and show that the predicted next action probabilities contain information that can be used to infer the underlying intention. We propose a two-step approach to human intention prediction: While a DNN predicts the probabilities of the next action, MCMC-based Bayesian inference is used to infer the underlying intention from these predictions. This approach not only allows for independent design of the DNN architecture but also the subsequently fast, design-independent inference of human intentions. We evaluate our method using a series of experiments on the Watch-And-Help (WAH) and a keyboard and mouse interaction dataset. Our results show that our approach can accurately predict human intentions from observed actions and the implicit information contained in next action probabilities. Furthermore, we show that our approach can predict the correct intention even if only few actions have been observed. △ Less

Submitted 25 March, 2024; v1 submitted 23 August, 2023; originally announced August 2023.

Comments: Accepted by Workshop on Theory of Mind in Human-AI Interaction at CHI 2024