Follow this author to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. A year ago, during his rookie Formula One campaign, Kimi Antonelli, the 19-year-old Italian driving prodigy tapped to replace seven-time champion Lewis Hamilton in the Mercedes lineup, spent the days after his first podium finish completing his final high school exams. This season, schoolwork in the rearview mirror, Antonelli can't stop winning and setting new records.

Interpretable communication is essential for safe and trustworthy autonomous driving, yet current vision-language models (VLMs) often operate under idealized assumptions and struggle to capture user intent in real-world scenarios. Existing driving-oriented VQA datasets are limited to full-scene descriptions or waypoint prediction, preventing the assessment of whether VLMs can respond to localized user-driven queries. We introduce Box-QAymo, a box-referring dataset and benchmark designed to both evaluate and finetune VLMs on spatial and temporal reasoning over user-specified objects. Users express intent by drawing bounding boxes, offering a fast and intuitive interface for focused queries in complex scenes. Specifically, we propose a hierarchical evaluation protocol that begins with binary sanity-check questions to assess basic model capacities, and progresses to (1) attribute prediction for box-referred objects, (2) motion understanding of target instances, and (3) spatiotemporal motion reasoning over inter-object dynamics across frames. To support this, we crowd-sourced fine-grained object classes and visual attributes that reflect the complexity drivers encounter, and extract object trajectories to construct temporally grounded QA pairs. Rigorous quality control through negative sampling, temporal consistency checks, and difficulty-aware balancing guarantee dataset robustness and diversity. Our comprehensive evaluation reveals significant limitations in current VLMs when queried about perception questions, highlighting the gap in achieving real-world performance. This work provides a foundation for developing more robust and interpretable autonomous driving systems that can communicate effectively with users under real-world conditions. Project page and dataset are available at https://djamahl99.github.io/qaymo-pages/.

End-to-end autonomous driving demonstrates strong planning capabilities with large-scale data but still struggles in complex, rare scenarios due to limited commonsense. In contrast, Large Vision-Language Models (LVLMs) excel in scene understanding and reasoning. The path forward lies in merging the strengths of both approaches. Previous methods using LVLMs to predict trajectories or control signals yield suboptimal results, as LVLMs are not well-suited for precise numerical predictions. This paper presents Senna, an autonomous driving system combining an LVLM (Senna-VLM) with an end-to-end model (Senna-E2E). Senna decouples high-level planning from low-level trajectory prediction. Senna-VLM generates planning decisions in natural language, while Senna-E2E predicts precise trajectories. Senna-VLM utilizes a multi-image encoding approach and multi-view prompts for efficient scene understanding. Besides, we introduce planning-oriented QAs alongside a three-stage training strategy, which enhances Senna-VLM's planning performance while preserving commonsense. Extensive experiments on two datasets show that Senna achieves state-of-the-art planning performance. Notably, with pre-training on a large-scale dataset DriveX and fine-tuning on nuScenes, Senna significantly reduces average planning error by 27.12% and collision rate by 33.33% over model without pre-training. We believe Senna's cross-scenario generalization and transferability are essential for achieving fully autonomous driving. Code and models will be released at https://github.com/hustvl/Senna.

'The greatest track on Earth' finally finishes up at the Interlagos Circuit of the São Paulo Grand Prix. It features the Senna'S', an S-shaped part of the track named after the legendary Brazilian racing driver Ayrton Senna. Look closely and you'll see a statue of Senna, who was tragically killed at the 1994 San Marino Grand Prix when his car crashed into a concrete barrier. Bringing the AI track to an end in Brazil, the last section runs from Turn 14, known as Junção, and into Interlagos' final sector. Sky Sports, which has exclusive broadcast rights to live F1 races, is trying to entice fans to subscriptions before the Grand Prix season starts next month. The 2024 calendar comprises a record 24 Grands Prix, starting with the Bahrain Grand Prix on March 2. The Senna'S', named after the legendary Ayrton Senna, is renowned as one of Formula 1's most iconic overtaking spots Bringing the race to an end in Brazil, the thirteenth section of'The Greatest Track On Earth' runs from Turn 14, known as Junção, and into Interlagos' final sector Not content with winning trophies in real life, McLaren is now competing in the virtual world for F1 glory. The legendary British automobile company entered the world of eSports in 2017 and won its first tournament in December last year. With two Brits on the team, McLaren saw off fierce competitors including Mercedes-Benz, Aston Martin, Red Bull Racing and Haas. MailOnline has taken a trip to the global headwaters of McLaren in Woking, Surrey, to see what it takes to become a professional eSports driver.

Twenty-three years after his death, former Formula 1 world champion Ayrton Senna's name is almost as valuable as when he was alive - and it is making a difference in his home country of Brazil. It is Friday afternoon and children around the age of 12 are gathered in the computer lab of a public school in Itatiba, a small town an hour away from Sao Paulo. Class time is already over for the week, but these students have chosen to stay in school for extracurricular activities. They are learning Scratch, a piece of software developed by MIT experts that aims to teach kids how to code. Most public schools in Brazil don't have computer coding in their curriculum.

We seek to better understand the difference in quality of the several publicly released embeddings. We propose several tasks that help to distinguish the characteristics of different embeddings. Our evaluation of sentiment polarity and synonym/antonym relations shows that embeddings are able to capture surprisingly nuanced semantics even in the absence of sentence structure. Moreover, benchmarking the embeddings shows great variance in quality and characteristics of the semantics captured by the tested embeddings. Finally, we show the impact of varying the number of dimensions and the resolution of each dimension on the effective useful features captured by the embedding space. Our contributions highlight the importance of embeddings for NLP tasks and the effect of their quality on the final results.