Related papers: ChartMaster: Advancing Chart-to-Code Generation wi…

Despite significant evolution of CUDA programming and domain-specific libraries, effectively utilizing GPUs with massively parallel engines remains difficult. Large language models (LLMs) show strong potential in generating optimized CUDA…

Generative models have received a lot of attention in many areas of academia and the industry. Their capabilities span many areas, from the invention of images given a prompt to the generation of concrete code to solve a certain programming…

Despite significant advancements in Large Language Models (LLMs), developing advanced reasoning capabilities in LLMs remains a key challenge. Process Reward Models (PRMs) have demonstrated exceptional promise in enhancing reasoning by…

Testing plays a pivotal role in ensuring software quality, yet conventional Search Based Software Testing (SBST) methods often struggle with complex software units, achieving suboptimal test coverage. Recent works using large language…

Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent advances in large language models (LLMs) have made it possible…

Solving complex chart Q&A tasks requires advanced visual reasoning abilities in multimodal large language models (MLLMs), including recognizing key information from visual inputs and conducting reasoning over it. While fine-tuning MLLMs for…

Chart question-answering (QA) benchmarks aim to pose questions that require visual reasoning to correctly answer, but models can often reach solutions through shortcuts or prior familiarity with a chart based on their own background…

Given a graph with textual attributes, we enable users to `chat with their graph': that is, to ask questions about the graph using a conversational interface. In response to a user's questions, our method provides textual replies and…

Current Large Language Models (LLMs) often undergo supervised fine-tuning (SFT) to acquire tool use capabilities. However, SFT struggles to generalize to unfamiliar or complex tool use scenarios. Recent advancements in reinforcement…

Generating structured, editable diagrams remains a significant challenge for contemporary large language models, despite their proficiency in general-purpose vector code generation. The primary difficulty lies in the structural fragility of…

With respect to improving the reasoning accuracy of LLMs, the representative reinforcement learning (RL) method GRPO faces failure due to insignificant reward variance, while verification methods based on process reward models (PRMs) suffer…

Large language model (LLM) coding agents can generate working code, but their solutions often accumulate complexity, duplication, and architectural debt. Human developers address such issues through refactoring: behavior-preserving program…

Graphs have become an important modeling tool for web applications, and Graph Neural Networks (GNNs) have achieved great success in graph representation learning. However, the performance of traditional GNNs heavily relies on a large amount…

Large Language Models (LLMs) have shown significant potential in designing reward functions for Reinforcement Learning (RL) tasks. However, obtaining high-quality reward code often involves human intervention, numerous LLM queries, or…

Multimodal Large Language Models (MLLMs) have emerged as powerful tools for chart comprehension. However, they heavily rely on extracted content via OCR, which leads to numerical hallucinations when chart textual annotations are sparse.…

Graph Data Prompt (GDP), which introduces specific prompts in graph data for efficiently adapting pre-trained GNNs, has become a mainstream approach to graph fine-tuning learning problem. However, existing GDPs have been respectively…

Large Language Models (LLMs) have demonstrated strong capabilities in transforming text descriptions or tables to data visualizations via instruction-tuning methods. However, it is not straightforward to apply these methods directly for a…

The Design2Code problem, which involves converting digital designs into functional source code, is a significant challenge in software development due to its complexity and time-consuming nature. Traditional approaches often struggle with…

Existing methods fail to effectively steer Large Language Models (LLMs) between textual reasoning and code generation, leaving symbolic computing capabilities underutilized. We introduce CodeSteer, an effective method for guiding LLM…

Rubric-based Reinforcement Learning (RL) has emerged as a promising approach for aligning Large Language Models (LLMs) with complex, open-domain instruction following tasks. However, existing methods predominantly rely on response-level…