Related papers: MM-ReCoder: Advancing Chart-to-Code Generation wit…

Large Language Models (LLMs) have achieved remarkable performance across diverse tasks, yet their susceptibility to generating incorrect content during inference remains a critical unsolved challenge. While self-correction methods offer…

Existing reinforcement learning strategies based on outcome supervision have proven effective in enhancing the performance of large language models(LLMs) for code generation. While reinforcement learning based on process supervision has…

Recent studies customizing Multimodal Large Language Models (MLLMs) for domain-specific tasks have yielded promising results, especially in the field of scientific chart comprehension. These studies generally utilize visual instruction…

Large Language Models (LLMs) for code generation evolve rapidly through fine-tuning, merging, or new model releases. However, such updates can introduce regressions, not only in correctness but also in code quality and performance. To…

Code-generating Large Language Models (LLMs) have become essential tools in modern software development, enhancing productivity and accelerating development. This paper aims to investigate the fine-tuning of code-generating LLMs using…

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) has demonstrated strong capabilities in…

Recent advancements in large language models (LLMs) have shown very impressive capabilities in code generation across many programming languages. However, even state-of-the-art LLMs generate programs that contains syntactic errors and fail…

Large Language Models (LLMs) generate functionally correct solutions but often fall short in code efficiency, a critical bottleneck for real-world deployment. In this paper, we introduce a novel test-time iterative optimization framework to…

Automating the transformation of user interface (UI) designs into front-end code holds significant promise for accelerating software development and democratizing design workflows. While multimodal large language models (MLLMs) can…

Large Language Models (LLMs) are changing the coding paradigm, known as vibe coding, yet synthesizing algorithmically sophisticated and robust code still remains a critical challenge. Incentivizing the deep reasoning capabilities of LLMs is…

This paper introduces a novel code-to-code search technique that enhances the performance of Large Language Models (LLMs) by including both static and dynamic features as well as utilizing both similar and dissimilar examples during…

Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains. However, their ability to replicate complex, multi-panel visualizations from real-world data remains largely unassessed. To…

With the widespread adoption of Large Language Models (LLMs) such as GitHub Copilot and ChatGPT, developers increasingly rely on AI-assisted tools to support code generation. While LLMs can generate syntactically correct solutions for…

Multi-modal large language models have demonstrated impressive performances on most vision-language tasks. However, the model generally lacks the understanding capabilities for specific domain data, particularly when it comes to…

Large language models (LLMs) have demonstrated strong code generation capabilities, yet the runtime performance of generated code is not guaranteed, and there have been few attempts to train LLMs using runtime performance as a reward in the…

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…

Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing…

Time-series reasoning remains a significant challenge in multimodal large language models (MLLMs) due to the dynamic temporal patterns, ambiguous semantics, and lack of temporal priors. In this work, we introduce TimeMaster, a reinforcement…

A dominant assumption in Multimodal Language Model (MLLM) research is that its performance is largely inherited from the LLM backbone, given its immense parameter scale and remarkable capabilities. This has created a void in the…

Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, the most general and…