相关论文: MFTCoder: Boosting Code LLMs with Multitask Fine-T…

Recent research explores optimization using large language models (LLMs) by either iteratively seeking next-step solutions from LLMs or directly prompting LLMs for an optimizer. However, these approaches exhibit inherent limitations,…

Code synthesis, which requires a deep understanding of complex natural language problem descriptions, generation of code instructions for complex algorithms and data structures, and the successful execution of comprehensive unit tests,…

While large language models demonstrate remarkable capabilities at task-specific applications through fine-tuning, extending these benefits across diverse languages is essential for broad accessibility. However, effective cross-lingual…

Large Language Models (LLMs) are widely adopted for assisting in software development tasks, yet their performance evaluations have narrowly focused on the functional correctness of generated code. Human programmers, however, require…

The pervasive deployment of Large Language Models-LLMs in various sectors often neglects the nuanced requirements of individuals and small organizations, who benefit more from models precisely tailored to their specific business contexts…

Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervised fine-tuning (SFT) approach, which relies on large-scale…

Fine-tuning large language models (LLMs) for domain-specific tasks requires training datasets that comprehensively cover the target capabilities a practitioner needs. Yet identifying which capabilities a dataset fails to support, and doing…

The use of large language models (LLMs) for automated code generation has emerged as a significant focus within AI research. As these pretrained models continue to evolve, their ability to understand and generate complex code structures has…

The recent surge in Large Language Models (LLMs) has garnered significant attention across numerous fields. Fine-tuning is often required to fit general LLMs for a specific domain, like the web-based healthcare system. However, two problems…

The advancement of large language models (LLMs) has significantly propelled the field of code generation. Previous work integrated reinforcement learning (RL) with compiler feedback for exploring the output space of LLMs to enhance code…

Converting webpage designs into code (design-to-code) plays a vital role in User Interface (UI) development for front-end developers, bridging the gap between visual design and functional implementation. While recent Multimodal Large…

Code review is essential for maintaining software quality but often time-consuming and cognitively demanding, especially in industrial environments. Recent advancements in language models (LMs) have opened new avenues for automating core…

Code Sensitivity refers to the ability of Code LLMs to recognize and respond to details changes in problem descriptions. While current code benchmarks and instruction data focus on difficulty and diversity, sensitivity is overlooked. We…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in chart understanding tasks. However, interpreting charts with textual descriptions often leads to information loss, as it fails to fully capture the dense…

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…

The rapid advancement of Large Language Models (LLMs) has significantly improved code generation, yet most models remain text-only, neglecting crucial visual aids like diagrams and flowcharts used in real-world software development. To…

Even though large language models are becoming increasingly capable, it is still unreasonable to expect them to excel at tasks that are under-represented on the Internet. Leveraging LLMs for specialized applications, particularly in niche…

Developing high-performance GPU kernels is critical for AI and scientific computing, but remains challenging due to its reliance on expert crafting and poor portability. While LLMs offer promise for automation, both general-purpose and…

Vision-Language Models (VLMs) have demonstrated remarkable capabilities in cross-modal understanding and generation by integrating visual and textual information. While instruction tuning and parameter-efficient fine-tuning methods have…

Among parameter-efficient fine-tuning methods, freezing has emerged as a popular strategy for speeding up training, reducing catastrophic forgetting, and improving downstream performance. We investigate the impact of freezing the decoder in…