E-commerce product titles often include redundant information that negatively impacts the user experience. Removing repeated words through restructuring and paraphrasing can make titles more concise and improve readability. While large language models can optimize titles, their computational cost makes them impractical for large-scale applications. In this paper, we first analyze the sources of repetition in multilingual product titles, then present LocRegen, a system that uses smaller language models to efficiently remove redundancies while preserving essential product attributes. Our experiments across five languages show that LocRegen with a 7B model substantially outperforms a 47B mixture-of-experts model: LocRegen achieves a 2.4% redundant title rate compared to 3.5% for the 47B model, and maintains a 3.8% overall error rate across all error categories including key product attribute omission compared to 8.4% for the 47B model. These results demonstrate that LocRegen delivers superior performance on cost-effective hardware with acceptable latency, making it practical for large-scale deployment where much larger models would be computationally prohibitive.

In recent years, the interpretability of Deep Neural Networks (DNNs) has garnered significant attention, particularly due to their widespread deployment in critical domains like healthcare, finance, and autonomous systems. To address the challenge of understanding how DNNs make decisions, Explainable AI (XAI) methods, such as saliency maps, have been developed to provide insights into the inner workings of these models. This paper introduces DiffCAM, a novel XAI method designed to overcome limitations in existing Class Activation Map (CAM)-based techniques, which often rely on decision boundary gradients to estimate feature importance. DiffCAM differentiates itself by considering the actual data distribution of the reference class, identifying feature importance based on how a target example differs from reference examples. This approach captures the most discriminative features without relying on decision boundaries or prediction results, making DiffCAM applicable to a broader range of models, including foundation models. Through extensive experiments, we demonstrate the superior performance and flexibility of DiffCAM in providing meaningful explanations across diverse datasets and scenarios.

Modern engineering, spanning electrical, mechanical, aerospace, civil, and computer disciplines, stands as a cornerstone of human civilization and the foundation of our society. However, engineering design poses a fundamentally different challenge for large language models (LLMs) compared with traditional textbook-style problem solving or factual question answering. Although existing benchmarks have driven progress in areas such as language understanding, code synthesis, and scientific problem solving, real-world engineering design demands the synthesis of domain knowledge, navigation of complex trade-offs, and management of the tedious processes that consume much of practicing engineers' time. Despite these shared challenges across engineering disciplines, no benchmark currently captures the unique demands of engineering design work. In this work, we introduce EngDesign, an Engineering Design benchmark that evaluates LLMs' abilities to perform practical design tasks across nine engineering domains. Unlike existing benchmarks that focus on factual recall or question answering, EngDesign uniquely emphasizes LLMs' ability to synthesize domain knowledge, reason under constraints, and generate functional, objective-oriented engineering designs. Each task in EngDesign represents a real-world engineering design problem, accompanied by a detailed task description specifying design goals, constraints, and performance requirements. EngDesign pioneers a simulation-based evaluation paradigm that moves beyond textbook knowledge to assess genuine engineering design capabilities and shifts evaluation from static answer checking to dynamic, simulation-driven functional verification, marking a crucial step toward realizing the vision of engineering Artificial General Intelligence (AGI).