相关论文: SketchFill: Sketch-Guided Code Generation for Impu…
For decades, corporations and governments have relied on scanned documents to record vast amounts of information. However, extracting this information is a slow and tedious process due to the sheer volume and complexity of these records.…
Scripting interfaces enable users to automate tasks and customize software workflows, but creating scripts traditionally requires programming expertise and familiarity with specific APIs, posing barriers for many users. While Large Language…
Recent studies have raised significant concerns regarding the reliability of current mathematics benchmarks, highlighting issues such as simplistic design and potential data contamination. Consequently, developing a reliable benchmark that…
In order to compute fast approximations to the singular value decompositions (SVD) of very large matrices, randomized sketching algorithms have become a leading approach. However, a key practical difficulty of sketching an SVD is that the…
Visual reasoning is crucial for multimodal large language models (MLLMs) to address complex chart queries, yet high-quality rationale data remains scarce. Existing methods leveraged (M)LLMs for data generation, but direct prompting often…
In science education, students frequently construct hand-drawn visual models of scientific phenomena. These drawings rely on a visual structure where information is encoded through visual objects, their attributes, and relationships.…
Large language models (LLMs) are increasingly deployed in settings where the available context is incomplete or degraded. We argue that an LLM generating answers under incomplete context can be viewed as an implicit imputer, and evaluated…
While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven…
Sketch-Based Image Retrieval (SBIR) is a crucial task in multimedia retrieval, where the goal is to retrieve a set of images that match a given sketch query. Researchers have already proposed several well-performing solutions for this task,…
Mathematical problem-solving is a key field in artificial intelligence (AI) and a critical benchmark for evaluating the capabilities of large language models (LLMs). While extensive research has focused on mathematical problem-solving, most…
Current multimodal large language models (MLLMs), while effective in natural image understanding, struggle with visualization understanding due to their inability to decode the data-to-visual mapping and extract structured information. To…
Within the evolving landscape of deep learning, the dilemma of data quantity and quality has been a long-standing problem. The recent advent of Large Language Models (LLMs) offers a data-centric solution to alleviate the limitations of…
As large language models (LLMs) become increasingly capable and widely adopted, benchmarks play a central role in assessing their practical utility. For example, SWE-Bench Verified has emerged as a critical benchmark for evaluating LLMs'…
Fully comprehending scientific papers by machines reflects a high level of Artificial General Intelligence, requiring the ability to reason across fragmented and heterogeneous sources of information, presenting a complex and practically…
Automated data extraction from research texts has been steadily improving, with the emergence of large language models (LLMs) accelerating progress even further. Extracting data from plots in research papers, however, has been such a…
(Renyi Qu's Master's Thesis) Recent advancements in interpretable models for vision-language tasks have achieved competitive performance; however, their interpretability often suffers due to the reliance on unstructured text outputs from…
Workflows are a fundamental component of automation in enterprise platforms, enabling the orchestration of tasks, data processing, and system integrations. Despite being widely used, building workflows can be complex, often requiring manual…
The "thinking with images" paradigm represents a pivotal shift in the reasoning of Vision Language Models (VLMs), moving from text-dominant chain-of-thought to image-interactive reasoning. By invoking visual tools or generating intermediate…
The automatic generation of visualizations is an old task that, through the years, has shown more and more interest from the research and practitioner communities. Recently, large language models (LLM) have become an interesting option for…
Large Language Models (LLMs) have recently made significant advances in code generation through the 'Chain-of-Thought' prompting technique. This technique empowers the model to autonomously devise "solution plans" to tackle intricate…