As autonomous driving technology matures, safety and robustness of its k...
A holistic understanding of object properties across diverse sensory
mod...
Intelligent Traffic Monitoring (ITMo) technologies hold the potential fo...
Communication via natural language is a crucial aspect of intelligence, ...
Self-training based on pseudo-labels has emerged as a dominant approach ...
Humans learn about objects via interaction and using multiple perception...
Generalisation to unseen contexts remains a challenge for embodied navig...
The feasibility of collecting a large amount of expert demonstrations ha...
Understanding novel situations in the traffic domain requires an intrica...
Humans leverage multiple sensor modalities when interacting with objects...
Procedural text understanding is a challenging language reasoning task t...
Self-supervision based on the information extracted from large knowledge...
We present the results of our autonomous racing virtual challenge, based...
This chapter illustrates how suitable neuro-symbolic models for language...
To be viable for safety-critical applications, such as autonomous drivin...
Commonsense reasoning benchmarks have been largely solved by fine-tuning...
Recent advances in the areas of multimodal machine learning and artifici...
Conditional text generation has been a challenging task that is yet to s...
Effective feature-extraction is critical to models' contextual understan...
Recent developments in pre-trained neural language modeling have led to ...
Understanding the models that characterize the thermal dynamics in a sma...
Computational context understanding refers to an agent's ability to fuse...
Multi-agent trajectory forecasting in autonomous driving requires an age...
Non-extractive commonsense QA remains a challenging AI task, as it requi...