Related papers: PIE: A Domain-Specific Language for Interactive So…
The enhancement of Visual Language Models (VLMs) has traditionally relied on knowledge distillation from larger, more capable models. This dependence creates a fundamental bottleneck for improving state-of-the-art systems, particularly when…
Speculative decoding accelerates large language model inference by using smaller draft models to generate candidate tokens for parallel verification. However, current approaches are limited by sequential stage dependencies that prevent full…
Domain-driven design (DDD) is a powerful design technique for architecting complex software systems. This paper introduces a prompting framework that automates core DDD activities through structured large language model (LLM) interactions.…
This paper presents SPIE: a novel approach for semantic and structural post-training of instruction-based image editing diffusion models, addressing key challenges in alignment with user prompts and consistency with input images. We…
Operationalizing AI has become a major endeavor in both research and industry. Automated, operationalized pipelines that manage the AI application lifecycle will form a significant part of tomorrow's infrastructure workloads. To optimize…
An increasing number of models and frameworks for Virtual Assistant (VA) development exist nowadays, following the progress in the Natural Language Processing (NLP) and Natural Language Understanding (NLU) fields. Regardless of their…
Quick interaction between a human teacher and a learning machine presents numerous benefits and challenges when working with web-scale data. The human teacher guides the machine towards accomplishing the task of interest. The learning…
IoT and edge-based inference systems require unique solutions to overcome resource limitations and unpredictable environments. In this paper, we propose an environment-aware dynamic pruning system that handles the unpredictability of edge…
Automated machine learning makes it easier for data scientists to develop pipelines by searching over possible choices for hyperparameters, algorithms, and even pipeline topologies. Unfortunately, the syntax for automated machine learning…
Artificial Intelligence (AI) applications in automation systems are usually distributed systems whose development and integration involve several experts. Each expert uses its own domain-specific modeling language and tools to model the…
Continuous Software Engineering (CSE) is widely adopted in the industry, integrating practices such as Continuous Integration and Continuous Deployment (CI/CD). Beyond technical aspects, CSE also encompasses business activities like…
With the growing popularity of Large Reasoning Models and their results in solving mathematical problems, it becomes crucial to measure their capabilities. We introduce a pipeline for both automatic and interactive verification as a more…
As the integration of web services into web applications becomes more and more common, it is necessary to find a solution for low-code or no-code environments. This thesis is the first attempt to allow for the easy integration of web…
The ability to independently deploy parts of a software system is one of the cornerstones of modern software development, and allows for these parts to evolve independently and at different speeds. A major challenge of such independent…
Irregular codes are bottlenecked by memory and communication latency. Decoupled access/execute (DAE) is a common technique to tackle this problem. It relies on the compiler to separate memory address generation from the rest of the program,…
Large multimodal models (LMMs) have demonstrated excellent capabilities in both understanding and generation tasks with various modalities. While these models can accept flexible combinations of input data, their training efficiency suffers…
The increasing demand for programmers has led to a surge in participants in programming courses, making it increasingly challenging for instructors to assess student code manually. As a result, automated programming assessment systems…
Typically, information extraction (IE) requires a pipeline approach: first, a sequence labeling model is trained on manually annotated documents to extract relevant spans; then, when a new document arrives, a model predicts spans which are…
We introduce a domain-specific language (DSL) for creating sets of tile types for simulations of the abstract Tile Assembly Model. The language defines objects known as tile templates, which represent related groups of tiles, and a small…
Unstructured text has long been difficult to automatically analyze at scale. Large language models (LLMs) now offer a way forward by enabling {\em semantic data processing}, where familiar data processing operators (e.g., map, reduce,…