Since time immemorial an old adage has always seemed to ring true: you cannot use a high-level productive programming language like Python or R for real-time control and embedded-systems programming, you must rewrite your program in C. We present a counterexample to this mantra by demonstrating how recent compiler developments in the Julia programming language allow users of Julia and the equation-based modeling language ModelingToolkit to compile and deploy binaries for real-time model-based estimation and control. Contrary to the approach taken by a majority of modeling and simulation tools, we do not generate C code, and instead demonstrate how we may use the native Julia code-generation pipeline through LLVM to compile architecture-specific binaries from high-level code. This approach avoids many of the restrictions typically placed on high-level languages to enable C-code generation. As case studies, we include a nonlinear state estimator derived from an equation-based model which is compiled into a program that performs state estimation for deployment onto a Raspberry Pi, as well as a PID controller library implemented in Julia and compiled into a shared library callable from a C program.
Lately, Large Language Models have been widely used in code generation. GPT4 is considered the most potent Large Language Model from Openai. In this paper, we examine GPT3.5 and GPT4 as coding assistants. More specifically, we have constructed appropriate tests to check whether the two systems can a) answer typical questions that can arise during the code development, b) produce reliable code, and c) contribute to code debugging. The test results are impressive. The performance of GPT4 is outstanding and signals an increase in the productivity of programmers and the reorganization of software development procedures based on these new tools.
Despite Large Language Models (LLMs) like GPT-4 achieving impressive results in function-level code generation, they struggle with repository-scale code understanding (e.g., coming up with the right arguments for calling routines), requiring a deeper comprehension of complex file interactions. Also, recently, people have developed LLM agents that attempt to interact with repository code (e.g., compiling and evaluating its execution), prompting the need to evaluate their performance. These gaps have motivated our development of ML-Bench, a benchmark rooted in real-world programming applications that leverage existing code repositories to perform tasks. Addressing the need for LLMs to interpret long code contexts and translate instructions into precise, executable scripts, ML-Bench encompasses annotated 9,641 examples across 18 GitHub repositories, challenging LLMs to accommodate user-specified arguments and documentation intricacies effectively. To evaluate both LLMs and AI agents, two setups are employed: ML-LLM-Bench for assessing LLMs' text-to-code conversion within a predefined deployment environment, and ML-Agent-Bench for testing autonomous agents in an end-to-end task execution within a Linux sandbox environment. Our findings indicate that while GPT-4o leads with a Pass@5 rate surpassing 50%, there remains significant scope for improvement, highlighted by issues such as hallucinated outputs and difficulties with bash script generation. Notably, in the more demanding ML-Agent-Bench, GPT-4o achieves a 76.47% success rate, reflecting the efficacy of iterative action and feedback in complex task resolution. Our code, dataset, and models are available at https://github.com/gersteinlab/ML-bench.
The impressive performance of proprietary LLMs like GPT4 in code generation has led to a trend to replicate these capabilities in open-source models through knowledge distillation (e.g. Code Evol-Instruct). However, these efforts often neglect the crucial aspect of response quality, relying heavily on teacher models for direct response distillation. This paradigm, especially for complex instructions, can degrade the quality of synthesized data, compromising the knowledge distillation process. To this end, our study introduces the Adaptive Modular Response Evolution (AMR-Evol) framework, which employs a two-stage process to refine response distillation. The first stage, modular decomposition, breaks down the direct response into more manageable sub-modules. The second stage, adaptive response evolution, automatically evolves the response with the related function modules. Our experiments with three popular code benchmarks (HumanEval, MBPP, and EvalPlus) attest to the superiority of the AMR-Evol framework over baseline response distillation methods. By comparing with the open-source Code LLMs trained on a similar scale of data, we observed performance enhancements: more than +3.0 points on HumanEval-Plus and +1.0 points on MBPP-Plus, which underscores the effectiveness of our framework. Our codes are available at https://github.com/ChiYeungLaw/AMR-Evol.
Data labeling is a time intensive process. As such, many data scientists use various tools to aid in the data generation and labeling process. While these tools help automate labeling, many still require user interaction throughout the process. Additionally, most target only a few network frameworks. Any researchers exploring multiple frameworks must find additional tools orwrite conversion scripts. This paper presents an automated tool for generating synthetic data in arbitrary network formats. It uses Robot Operating System (ROS) and Gazebo, which are common tools in the robotics community. Through ROS paradigms, it allows extensive user customization of the simulation environment and data generation process. Additionally, a plugin-like framework allows the development of arbitrary data format writers without the need to change the main body of code. Using this tool, the authors were able to generate an arbitrarily large image dataset for three unique training formats using approximately 15 min of user setup time and a variable amount of hands-off run time, depending on the dataset size. The source code for this data generation tool is available at https://github.com/Navy-RISE-Lab/nn_data_collection
Next-generation wireless networks require higher spectral efficiency and lower latency to meet the demands of various upcoming applications. Recently, non-orthogonal multiple access (NOMA) schemes are introduced in the literature for 5G and beyond. Various forms of NOMA are considered like power domain, code domain, pattern division multiple access, etc. to enhance the spectral efficiency of wireless networks. In this chapter, we introduce the code domain-based sparse code multiple access (SCMA) NOMA scheme to enhance the spectral efficiency of a wireless network. The design and detection of an SCMA system are analyzed in this chapter. Also, the method for codebooks design and its impact on system performance are highlighted. A hybrid multiple access scheme is also introduced using both code-domain and power-domain NOMA. Furthermore, simulation results are included to show the impact of various SCMA system parameters.ext-generation wireless networks require higher spectral efficiency and lower latency to meet the demands of various upcoming applications. Recently, non-orthogonal multiple access (NOMA) schemes are introduced in the literature for 5G and beyond. Various forms of NOMA are considered like power domain, code domain, pattern division multiple access, etc. to enhance the spectral efficiency of wireless networks. In this chapter, we introduce the code domainbased sparse code multiple access (SCMA) NOMA scheme to enhance the spectral efficiency of a wireless network. The design and detection of an SCMA system are analyzed in this chapter. Also, the method for codebooks design and its impact on system performance are highlighted. A hybrid multiple access scheme is also introduced using both code-domain and power-domain NOMA. Furthermore, simulation results are included to show the impact of various SCMA system parameters.
Waveform generation is essential for studying signal propagation and channel characteristics, particularly for objects that are conceptualized but still need to be operational. We introduce a comprehensive guide on creating synthetic signals using channel and delay coefficients derived from the Quasi-Deterministic Radio Channel Generator (QuaDRiGa), which is recognized as a 3GPP-3D and 3GPP 38.901 reference implementation. The effectiveness of the proposed synthetic waveform generation method is validated through accurate estimation of code delay and Doppler shift. This validation is achieved using both the parallel code phase search technique and the conventional tracking method applied to satellites. As the method of integrating channel and delay coefficients to create synthetic waveforms is the same for satellite, HAPS, and gNB PRS, validating this method on synthetic satellite signals could potentially be extended to HAPS and gNB PRS as well. This study could significantly contribute to the field of heterogeneous navigation systems.
As LLM-generated code grows in popularity, more evaluation is needed to assess the risks of using such tools, especially for safety-critical applications such as path planning. Existing coding benchmarks are insufficient as they do not reflect the context and complexity of safety-critical applications. To this end, we assessed six LLMs' abilities to generate the code for three different path-planning algorithms and tested them on three maps of various difficulties. Our results suggest that LLM-generated code presents serious hazards for path planning applications and should not be applied in safety-critical contexts without rigorous testing.
Building Management System (BMS) through a data-driven method always faces data and model scalability issues. We propose a methodology to tackle the scalability challenges associated with the development of data-driven models for BMS by using Large Language Models (LLMs). LLMs' code generation adaptability can enable broader adoption of BMS by "automating the automation," particularly the data handling and data-driven modeling processes. In this paper, we use LLMs to generate code that processes structured data from BMS and build data-driven models for BMS's specific requirements. This eliminates the need for manual data and model development, reducing the time, effort, and cost associated with this process. Our hypothesis is that LLMs can incorporate domain knowledge about data science and BMS into data processing and modeling, ensuring that the data-driven modeling is automated for specific requirements of different building types and control objectives, which also improves accuracy and scalability. We generate a prompt template following the framework of Machine Learning Operations so that the prompts are designed to systematically generate Python code for data-driven modeling. Our case study indicates that bi-sequential prompting under the prompt template can achieve a high success rate of code generation and code accuracy, and significantly reduce human labor costs.
Large language models (LLMs) such as ChatGPT are increasingly proficient in understanding and generating a mixture of code and text. Evaluation based on such $\textit{mixture}$ can lead to a more comprehensive understanding of the models' abilities in solving coding problems. However, in this context, current evaluation methods are either limited in task coverage or lack standardization. To address this issue, we propose using category theory as a framework for evaluation. Specifically, morphisms within a code category can represent code debugging and transformation, functors between two categories represent code translation, and functors between a code category and a natural language category represent code generation, explanation, and reproduction. We present an automatic evaluation framework called $\textbf{CatCode}$ ($\textbf{Cat}$egory $\textbf{Code}$) that can comprehensively assess the coding abilities of LLMs, including ChatGPT, Text-Davinci, and CodeGeeX.
This paper explores the use of Large Language Models (LLMs) and in particular ChatGPT in programming, source code analysis, and code generation. LLMs and ChatGPT are built using machine learning and artificial intelligence techniques, and they offer several benefits to developers and programmers. While these models can save time and provide highly accurate results, they are not yet advanced enough to replace human programmers entirely. The paper investigates the potential applications of LLMs and ChatGPT in various areas, such as code creation, code documentation, bug detection, refactoring, and more. The paper also suggests that the usage of LLMs and ChatGPT is expected to increase in the future as they offer unparalleled benefits to the programming community.
Large Language Models (LLMs) have become increasingly integral to enhancing developer productivity, particularly in code generation, comprehension, and repair tasks. However, fine-tuning these models with high-quality, real-world data is challenging due to privacy concerns and the lack of accessible, labeled datasets. In this paper, we present DialogAgent, an automated tool for generating synthetic training data that closely mimics real developer interactions within Integrated Development Environments (IDEs). DialogAgent enables the production of diverse, high-fidelity query-response pairs by simulating multi-turn dialogues and contextual behaviors observed in real-world programming scenarios. The tool significantly reduces the reliance on manual data generation, increasing efficiency by 4.8 times compared to traditional methods. Our experiments and online deployment demonstrate substantial improvements in model performance for code-related question-answering tasks: the acceptance rate of responses generated by our in-house model is improved by 33%, after training on synthesized data generated by DialogAgent.
Video generation has achieved rapid progress benefiting from high-quality renderings provided by powerful image generators. We regard the video synthesis task as generating a sequence of images sharing the same contents but varying in motions. However, most previous video synthesis frameworks based on pre-trained image generators treat content and motion generation separately, leading to unrealistic generated videos. Therefore, we design a novel framework to build the motion space, aiming to achieve content consistency and fast convergence for video generation. We present MotionVideoGAN, a novel video generator synthesizing videos based on the motion space learned by pre-trained image pair generators. Firstly, we propose an image pair generator named MotionStyleGAN to generate image pairs sharing the same contents and producing various motions. Then we manage to acquire motion codes to edit one image in the generated image pairs and keep the other unchanged. The motion codes help us edit images within the motion space since the edited image shares the same contents with the other unchanged one in image pairs. Finally, we introduce a latent code generator to produce latent code sequences using motion codes for video generation. Our approach achieves state-of-the-art performance on the most complex video dataset ever used for unconditional video generation evaluation, UCF101.
The emergence of ChatGPT has once again sparked research in generative artificial intelligence (GAI). While people have been amazed by the generated results, they have also noticed the reasoning potential reflected in the generated textual content. However, this current ability for causal reasoning is primarily limited to the domain of language generation, such as in models like GPT-3. In visual modality, there is currently no equivalent research. Considering causal reasoning in visual content generation is significant. This is because visual information contains infinite granularity. Particularly, images can provide more intuitive and specific demonstrations for certain reasoning tasks, especially when compared to coarse-grained text. Hence, we propose a new image generation task called visual question answering with image (VQAI) and establish a dataset of the same name based on the classic \textit{Tom and Jerry} animated series. Additionally, we develop a new paradigm for image generation to tackle the challenges of this task. Finally, we perform extensive experiments and analyses, including visualizations of the generated content and discussions on the potentials and limitations. The code and data are publicly available under the license of CC BY-NC-SA 4.0 for academic and non-commercial usage. The code and dataset are publicly available at: https://github.com/IEIT-AGI/MIX-Shannon/blob/main/projects/VQAI/lgd_vqai.md.
Deliberation is a common and natural behavior in human daily life. For example, when writing papers or articles, we usually first write drafts, and then iteratively polish them until satisfied. In light of such a human cognitive process, we propose DECOM, which is a multi-pass deliberation framework for automatic comment generation. DECOM consists of multiple Deliberation Models and one Evaluation Model. Given a code snippet, we first extract keywords from the code and retrieve a similar code fragment from a pre-defined corpus. Then, we treat the comment of the retrieved code as the initial draft and input it with the code and keywords into DECOM to start the iterative deliberation process. At each deliberation, the deliberation model polishes the draft and generates a new comment. The evaluation model measures the quality of the newly generated comment to determine whether to end the iterative process or not. When the iterative process is terminated, the best-generated comment will be selected as the target comment. Our approach is evaluated on two real-world datasets in Java (87K) and Python (108K), and experiment results show that our approach outperforms the state-of-the-art baselines. A human evaluation study also confirms the comments generated by DECOM tend to be more readable, informative, and useful.
Generative recommendation (GR) has emerged as a promising paradigm that predicts target items by autoregressively generating their semantic identifiers (SID). Most GR methods follow a quantization-representation-generation pipeline. While most research focuses on quantization and generation, the representation that bridges the two remains underexplored. Existing representation constructions mainly take two forms: either directly flattening the SID code embeddings into a sequence or merging them into a compact vector via external networks. While effective, they still expose two practical challenges: \textbf{1) Loss of item semantics:} Information lost by quantization or compression needs to be recovered during the representation stage. \textbf{2) Insufficient modeling of structured SID relations:} Intra-item code composition patterns and inter-item prefix-transition patterns are not explicitly preserved for representation and subsequent SID generation. To overcome these challenges, we propose \textbf{ComeIR}, a \textbf{\uline{Co}}nditional \textbf{\uline{me}}mory Enhanced \textbf{\uline{I}}tem \textbf{\uline{R}}epresentation framework that reconstructs SID code embeddings into item-aware inputs and preserves structured SID evidence for prediction. Item-guided Token Scoring estimates the contribution of each SID code using the item embedding employed by the quantizer. Dual-level Conditional Memory captures intra-item prefix composition and inter-item prefix transitions, while Memory Merge integrates these signals into each historical item representation. The Memory-restoring Prediction Head further conditions SID-level prediction on the generated prefix and historical transition evidence. Extensive experiments demonstrate the effectiveness and flexibility of ComeIR, and further reveal scalable gains from enlarging conditional memory.
Recent advancements in the field of natural language generation have facilitated the use of large language models to assess the quality of generated text. Although these models have shown promising results in tasks such as machine translation and summarization, their applicability in code intelligence tasks remains limited without human involvement. The complexity of programming concepts required for such tasks makes it difficult to develop evaluation metrics that align with human judgment. Token-matching-based metrics, such as BLEU, have demonstrated weak correlations with human practitioners in code intelligence tasks. Moreover, utilizing human-written test suites to evaluate functional correctness can be challenging in domains with low resources. To overcome these obstacles, we propose \texttt{ICE-Score}, a new evaluation metric via instructing large language models (LLMs) for code assessments. Our metric addresses the limitations of existing approaches by achieving superior correlations with functional correctness and human preferences, without the need for test oracles or references. We evaluate the efficacy of our metric on two different aspects (\textit{human preference} and \textit{execution success}) and four programming languages. Our results demonstrate that our metric surpasses state-of-the-art metrics for code generation, delivering high levels of accuracy and consistency across various programming languages and tasks. We also make our evaluation metric and datasets available to the public\footnote{\url{https://github.com/terryyz/ice-score}}, encouraging further research in evaluating code intelligence tasks.
Code-mixing is a phenomenon of mixing words and phrases from two or more languages in a single utterance of speech and text. Due to the high linguistic diversity, code-mixing presents several challenges in evaluating standard natural language generation (NLG) tasks. Various widely popular metrics perform poorly with the code-mixed NLG tasks. To address this challenge, we present a metric independent evaluation pipeline MIPE that significantly improves the correlation between evaluation metrics and human judgments on the generated code-mixed text. As a use case, we demonstrate the performance of MIPE on the machine-generated Hinglish (code-mixing of Hindi and English languages) sentences from the HinGE corpus. We can extend the proposed evaluation strategy to other code-mixed language pairs, NLG tasks, and evaluation metrics with minimal to no effort.
We present EasyGen, an efficient model designed to enhance multimodal understanding and generation by harnessing the capabilities of diffusion models and large language models (LLMs), Unlike existing multimodal models that predominately depend on encoders like CLIP or ImageBind and need ample amounts of training data to bridge modalities,EasyGen leverages BiDiffuser,a bidirectional conditional diffusion model, to foster more efficient modality interactions. Easygen achieves text generation by training a projection layer linking BiDiffuser and an LLM, and facilities image generation by training an adapter to align the LLM's text space with the BiDiffuser's image space, Comprehensive quantitative and qualitative experiments show that EasyGen excels in data-efficient training, high-quality image generation, and extendibility, effectively addressing the challenges in multimodal generation. The source code is available at https://github.com/zxy556677/EasyGen.
The emergence of advanced neural networks has opened up new ways in automated code generation from conceptual models, promising to enhance software development processes. This paper presents a preliminary evaluation of GPT-4-Vision, a state-of-the-art deep learning model, and its capabilities in transforming Unified Modeling Language (UML) class diagrams into fully operating Java class files. In our study, we used exported images of 18 class diagrams comprising 10 single-class and 8 multi-class diagrams. We used 3 different prompts for each input, and we manually evaluated the results. We created a scoring system in which we scored the occurrence of elements found in the diagram within the source code. On average, the model was able to generate source code for 88% of the elements shown in the diagrams. Our results indicate that GPT-4-Vision exhibits proficiency in handling single-class UML diagrams, successfully transforming them into syntactically correct class files. However, for multi-class UML diagrams, the model's performance is weaker compared to single-class diagrams. In summary, further investigations are necessary to exploit the model's potential completely.