English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large Language Models (LLMs) have shown promise in the autonomous drivingsector, particularly in generalization and interpretability. We introduce aunique object-level multimodal LLM architecture that merges vectorized numericmodalities with a pre-trained LLM to improve context understanding in drivingsituations. We also present a new dataset of 160k QA pairs derived from 10kdriving scenarios, paired with high quality control commands collected with RLagent and question answer pairs generated by teacher LLM (GPT-3.5). A distinctpretraining strategy is devised to align numeric vector modalities with staticLLM representations using vector captioning language data. We also introduce anevaluation metric for Driving QA and demonstrate our LLM-driver's proficiencyin interpreting driving scenarios, answering questions, and decision-making.Our findings highlight the potential of LLM-based driving action generation incomparison to traditional behavioral cloning. We make our benchmark, datasets,and model available for further exploration.

Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving