Paper-Conference

Multitask Multimodal Prompted Training for Interactive Embodied Task Completion

An Analysis of Visually Grounded Instructions in Embodied AI Tasks

'What are you referring to?' Evaluating the Ability of Multi-Modal Dialogue Models to Process Clarificational Exchanges

Demonstrating EMMA: Embodied MultiModal Agent for Language-guided Action Execution in 3D Simulated Environments

Combine to Describe: Evaluating Compositional Generalization in Image Captioning

ACT-Thor: A Controlled Benchmark for Embodied Action Understanding in Simulated Environments

An Empirical Study on the Generalization Power of Neural Representations Learned via Visual Guessing Games

Predicting Perceptual Speed from Search Behaviour

Imagining Grounded Conceptual Representations from Perceptual Information in Situated Guessing Games

CompGuessWhat?!: A Multi-task Evaluation Framework for Grounded Language Learning