9 papers
PRISM: A Category-Theoretic Framework for Measuring and Refining Multimodal Analogies
Mirella Zeisler, Ojas Shirekar, Mircea Licǎ +1
Analogical reasoning involves identifying and preserving relational structures across domains. However, existing approaches to AI-driven multimodal analogy generation lack an inter…
OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation
Oana Madalina Fron, Ojas Shirekar, Chirag Raman
Cooperative language-model agents must coordinate over long horizons and adapt to changing environments and to partners with unfamiliar conventions, yet existing agents map observa…
Generative Interactions: Weaving Multiparty Human Motion with Bilevel Latent Dynamics
Ojas Shirekar, Yash Surange, Agustinas Jučas +1
Human social behaviour is not a collection of independent motions, but a jointly organised process in which group dynamics and individual variation continuously shape one another.…
Controlled Face Manipulation and Synthesis for Data Augmentation
Joris Kirchner, Amogh Gudi, Marian Bittner +1
Deep learning vision models excel with abundant supervision, but many applications face label scarcity and class imbalance. Controllable image editing can augment scarce labeled da…
Multimodal Quantitative Measures for Multiparty Behaviour Evaluation
Ojas Shirekar, Wim Pouw, Chenxu Hao +3
Digital humans are emerging as autonomous agents in multiparty interactions, yet existing evaluation metrics largely ignore contextual coordination dynamics. We introduce a unified…
Indeterminacy in Affective Computing: Considering Meaning and Context in Data Collection Practices
Bernd Dudzik, Tiffany Matej Hrkalovic, Chenxu Hao +2
Automatic Affect Prediction (AAP) uses computational analysis of input data such as text, speech, images, and physiological signals to predict various affective phenomena (e.g., em…
MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning
Mircea Lică, Ojas Shirekar, Baptiste Colle +1
Embodied agents powered by large language models (LLMs), such as Voyager, promise open-ended competence in worlds such as Minecraft. However, when powered by open-weight LLMs they…
A Comparative Study of Garment Draping Techniques
Prerana Achar, Mayank Patel, Anushka Mulik +3
We present a comparison review that evaluates popular techniques for garment draping for 3D fashion design, virtual try-ons, and animations. A comparative study is performed betwee…
Ensemble Learning to Assess Dynamics of Affective Experience Ratings and Physiological Change
Felix Dollack, Kiyoshi Kiyokawa, Huakun Liu +4
The congruence between affective experiences and physiological changes has been a debated topic for centuries. Recent technological advances in measurement and data analysis provid…