相关论文: o1-Coder: an o1 Replication for Coding

One-class Classification (OCC) is an area of machine learning which addresses prediction based on unbalanced datasets. Basically, OCC algorithms achieve training by means of a single class sample, with potentially some additional…

Large Language Models (LLMs) have emerged as powerful tools for software development tasks such as code completion, translation, and optimization. However, their ability to generate efficient and correct code, particularly in complex…

Programming is a powerful and ubiquitous problem-solving tool. Developing systems that can assist programmers or even generate programs independently could make programming more productive and accessible, yet so far incorporating…

Recent reasoning models, such as OpenAI's O1 series, have demonstrated exceptional performance on complex reasoning tasks and revealed new test-time scaling laws. Inspired by this, many people have been studying how to train models to…

We describe the implementation of output code optimization in the open source computer algebra system FORM. This implementation is based on recently discovered techniques of Monte Carlo tree search to find efficient multivariate Horner…

Morphological reinflection is the task of generating a target form given a source form, a source tag and a target tag. We propose a new way of modeling this task with neural encoder-decoder models. Our approach reduces the amount of…

Chart reasoning presents unique challenges due to its inherent complexity -- requiring precise numerical comprehension, multi-level visual understanding, and logical inference across interconnected data elements. Existing vision-language…

We introduce our first reflective generative model MetaStone-S1, which obtains OpenAI o3-mini's performance via the new Reflective Generative Form. The new form focuses on high-quality reasoning trajectory selection and contains two…

Existing leading code comment generation approaches with the structure-to-sequence framework ignores the type information of the interpretation of the code, e.g., operator, string, etc. However, introducing the type information into the…

Repository-level code generation remains challenging due to complex code dependencies and the limitations of large language models (LLMs) in processing long contexts. While retrieval-augmented generation (RAG) frameworks are widely adopted,…

Intermediate reasoning or acting steps have successfully improved large language models (LLMs) for handling various downstream natural language processing (NLP) tasks. When applying LLMs for code generation, recent works mainly focus on…

While reasoning models (e.g., DeepSeek R1) trained with reinforcement learning (RL), excel in textual reasoning, they struggle in scenarios requiring structured problem-solving, such as geometric reasoning, concise computation, or complex…

This Innovative Practice full paper explores how Large Language Models (LLMs) can enhance the teaching of code refactoring in software engineering courses through real-time, context-aware feedback. Refactoring improves code quality but is…

With the rapid evolution of large language models (LLM), reinforcement learning (RL) has emerged as a pivotal technique for code generation and optimization in various domains. This paper presents a systematic survey of the application of…

We present Owlgorithm, an educational platform that supports Self-Regulated Learning (SRL) in competitive programming (CP) through AI-generated reflective questions. Leveraging GPT-4o, Owlgorithm produces context-aware, metacognitive…

Large Language Models (LLMs) have shown remarkable performance on complex reasoning tasks, especially when equipped with long chain-of-thought (CoT) reasoning. However, eliciting long CoT typically requires large-scale reinforcement…

Text-based retrieval of Computer-Aided Design (CAD) models is a critical yet underexplored task for the reuse of legacy industrial designs. Existing CAD repositories are typically searched using filenames or directories, which limits the…

Long-horizon video-audio reasoning and fine-grained pixel understanding impose conflicting requirements on omnimodal models: dense temporal coverage demands many low-resolution frames, whereas precise grounding calls for high-resolution…

Modern reasoning models, such as OpenAI's o1 and DeepSeek-R1, exhibit impressive problem-solving capabilities but suffer from critical inefficiencies: high inference latency, excessive computational resource consumption, and a tendency…

Despite the rapid growth of machine learning research, corresponding code implementations are often unavailable, making it slow and labor-intensive for researchers to reproduce results and build upon prior work. In the meantime, recent…