Accurate trajectory prediction is critical for safe autonomous navigation, yet the impact of dataset design on model performance remains understudied. This work systematically examines how feature selection, cross-dataset transfer, and geographic diversity influence trajectory prediction accuracy in multi-agent settings. We evaluate a state-of-the-art model using our novel L4 Motion Forecasting dataset based on our own data recordings in Germany and the US. This includes enhanced map and agent features. We compare our dataset to the US-centric Argoverse 2 benchmark. First, we find that incorporating supplementary map and agent features unique to our dataset, yields no measurable improvement over baseline features, demonstrating that modern architectures do not need extensive feature sets for optimal performance. The limited features of public datasets are sufficient to capture convoluted interactions without added complexity. Second, we perform cross-dataset experiments to evaluate how effective domain knowledge can be transferred between datasets. Third, we group our dataset by country and check the knowledge transfer between different driving cultures.

Embedding Based Retrieval (EBR) is a crucial component of the retrieval stage in (Ads) Recommendation System that utilizes Two Tower or Siamese Networks to learn embeddings for both users and items (ads). It then employs an Approximate Nearest Neighbor Search (ANN) to efficiently retrieve the most relevant ads for a specific user. Despite the recent rise to popularity in the industry, they have a couple of limitations. Firstly, Two Tower model architecture uses a single dot product interaction which despite their efficiency fail to capture the data distribution in practice. Secondly, the centroid representation and cluster assignment, which are components of ANN, occur after the training process has been completed. As a result, they do not take into account the optimization criteria used for retrieval model. In this paper, we present Hierarchical Structured Neural Network (HSNN), a deployed jointly optimized hierarchical clustering and neural network model that can take advantage of sophisticated interactions and model architectures that are more common in the ranking stages while maintaining a sub-linear inference cost. We achieve 6.5% improvement in offline evaluation and also demonstrate 1.22% online gains through A/B experiments. HSNN has been successfully deployed into the Ads Recommendation system and is currently handling major portion of the traffic. The paper shares our experience in developing this system, dealing with challenges like freshness, volatility, cold start recommendations, cluster collapse and lessons deploying the model in a large scale retrieval production system.

In customer service technical support, swiftly and accurately retrieving relevant past issues is critical for efficiently resolving customer inquiries. The conventional retrieval methods in retrieval-augmented generation (RAG) for large language models (LLMs) treat a large corpus of past issue tracking tickets as plain text, ignoring the crucial intra-issue structure and inter-issue relations, which limits performance. We introduce a novel customer service question-answering method that amalgamates RAG with a knowledge graph (KG). Our method constructs a KG from historical issues for use in retrieval, retaining the intra-issue structure and inter-issue relations. During the question-answering phase, our method parses consumer queries and retrieves related sub-graphs from the KG to generate answers. This integration of a KG not only improves retrieval accuracy by preserving customer service structure information but also enhances answering quality by mitigating the effects of text segmentation. Empirical assessments on our benchmark datasets, utilizing key retrieval (MRR, Recall@K, NDCG@K) and text generation (BLEU, ROUGE, METEOR) metrics, reveal that our method outperforms the baseline by 77.6% in MRR and by 0.32 in BLEU. Our method has been deployed within LinkedIn's customer service team for approximately six months and has reduced the median per-issue resolution time by 28.6%.

Text-to-image models such as stable diffusion have opened a plethora of opportunities for generating art. Recent literature has surveyed the use of text-to-image models for enhancing the work of many creative artists. Many e-commerce platforms employ a manual process to generate the banners, which is time-consuming and has limitations of scalability. In this work, we demonstrate the use of text-to-image models for generating personalized web banners with dynamic content for online shoppers based on their interactions. The novelty in this approach lies in converting users' interaction data to meaningful prompts without human intervention. To this end, we utilize a large language model (LLM) to systematically extract a tuple of attributes from item meta-information. The attributes are then passed to a text-to-image model via prompt engineering to generate images for the banner. Our results show that the proposed approach can create high-quality personalized banners for users.

What you will be doing: In-car testing execution: Plan, coordinate, and complete testing requirements in your region. Ensure smooth flow of operations, handle schedule, coordinate drivers and test operators. Drive process improvement: Build issue reports, deliver feedback, run execution risks, test new tool features. Own operational processes, build and track critical metrics. Report, track, and improve Fleet efficiency: lead the fleet efficiency across car, garage, people and execution.

The Bosch Group operates in most countries in the world. With over 400,000 associates, a career at Bosch offers a chance to grow an exceptional career in an environment that values diversity, initiative, and a drive for results. If you are interested in working on the cutting-edge of technology, working at Bosch Research is the place for you! We are committed to quality at Bosch. Our environment celebrates diversity and promotes career progression.

Find open roles in Artificial Intelligence (AI), Machine Learning (ML), Natural Language Processing (NLP), Computer Vision (CV), Data Engineering, Data Analytics, Big Data, and Data Science in general, filtered by job title or popular skill, toolset and products used.

The Bosch Research and Technology Center North America with offices in Sunnyvale, California, Pittsburgh, Pennsylvania and Cambridge, Massachusetts is part of the global Bosch Group (www.bosch.com), The Research and Technology Center North America (RTC-NA) is committed to providing technologies and system solutions for various Bosch business fields primarily in the areas of Integrated Human-Machine Intelligence, Robotics, Energy Technologies, Internet Technologies, Circuit Design, Semiconductors and Wireless, and MEMS Advanced Design. The focus of our global research on Integrated Human-Machine Intelligence includes Big Data Visual Analytics, Explainable AI, Audio Analytics, NLP, Conversational AI, Cloud Robotics, Mixed Reality and Smart Wearables, etc. We develop intuitive, interactive, and intelligent solutions to enable inspiring UX for Bosch products and services in application areas such as autonomous driving, car infotainment and driver assistance systems (ADAS), Industry 4.0 and Internet of Things (IoT), security systems, smart home and building solutions, health care, and robotics. As a part of our global research unit, our Conversational AI & Natural Language Processing group is responsible for shaping the future user experience of Bosch products by developing cutting-edge technologies and prototype systems in the fields of natural language processing and understanding, knowledge representation and reasoning, question answering, information retrieval, dialogue management, knowledge-based assistance, speech processing, and etc.

Searching for and making decisions about products is becoming increasingly easier in the e-commerce space, thanks to the evolution of recommender systems. Personalization and recommender systems have gone hand-in-hand to help customers fulfill their shopping needs and improve their experiences in the process. With the growing adoption of conversational platforms for shopping, it has become important to build personalized models at scale to handle the large influx of data and perform inference in real-time. In this work, we present an end-to-end machine learning system for personalized conversational voice commerce. We include components for implicit feedback to the model, model training, evaluation on update, and a real-time inference engine. Our system personalizes voice shopping for Walmart Grocery customers and is currently available via Google Assistant, Siri and Google Home devices.

Responsibilities: • Invent and build solutions to real-world customer problems through close collaborations with design, research and engineering teams • Ability to quickly change and iterate based on the team's needs • Multi-task and change from one task to another without loss of efficiency or composure Skills: • Bachelor's in Computer Science, Electrical Engineering, Statistics or related field • Ability to run experiments and analyze results scientifically • Must have working experience and be expert in building AI Models • Solid understanding in algorithms and data structure • A breadth of technical skills and know how to use the right tool for the job • Have a passion for solving very difficult technology challenges and learning new technologies and domains • Ability to work independently and multi-task effectively • Ability to understand business requirements and translate them into technical requirements • Flexible and willing to accept a change in priorities as necessary • Strong attention to detail • Experience working in a collaborative environment with designers and researchers Desired Skills & Experience: • Experience in data analysis is a plus • Good understanding of ML application design principles • Experienced in exploring a new field