activity
20232026
collaborators
Showing cs.AIShow all

5 papers · 1 filter

cs.AI2026

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…

cs.AI2026

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…

cs.AI2026

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.…

cs.AI2025

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…

cs.AI2024

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…