The goal of program synthesis, or code generation, is to generate executable code based on given descriptions. Recently, there has been an increasing number of studies employing reinforcement learning (RL) to improve the performance of large language models (LLMs) for code. However, current representative works either rely solely on offline frameworks, limiting the exploration of new sample spaces, or fall short in the utilization of unit test signals, not accounting for specific error locations within the code. To address these issues, we propose RLTF, i.e., Reinforcement Learning from Unit Test Feedback, a novel online RL framework with unit test feedback of multi-granularity for refining code LLMs. Our approach generates data in real-time during training and simultaneously utilizes fine-grained feedback signals to guide the model towards producing higher-quality code. Extensive experiments show that RLTF achieves state-of-the-art performance on the APPS and the MBPP benchmarks. Our code is available at: //github.com/Zyq-scut/RLTF.
相關內容
Modern deep learning models, growing larger and more complex, have demonstrated exceptional generalization and accuracy due to training on huge datasets. This trend is expected to continue. However, the increasing size of these models poses challenges in training, as traditional centralized methods are limited by memory constraints at such scales. This paper proposes an asynchronous decentralized training paradigm for large modern deep learning models that harnesses the compute power of regular heterogeneous PCs with limited resources connected across the internet to achieve favourable performance metrics. Ravnest facilitates decentralized training by efficiently organizing compute nodes into clusters with similar data transfer rates and compute capabilities, without necessitating that each node hosts the entire model. These clusters engage in $\textit{Zero-Bubble Asynchronous Model Parallel}$ training, and a $\textit{Parallel Multi-Ring All-Reduce}$ method is employed to effectively execute global parameter averaging across all clusters. We have framed our asynchronous SGD loss function as a block structured optimization problem with delayed updates and derived an optimal convergence rate of $O\left(\frac{1}{\sqrt{K}}\right)$. We further discuss linear speedup with respect to the number of participating clusters and the bound on the staleness parameter.
We present Image Sculpting, a new framework for editing 2D images by incorporating tools from 3D geometry and graphics. This approach differs markedly from existing methods, which are confined to 2D spaces and typically rely on textual instructions, leading to ambiguity and limited control. Image Sculpting converts 2D objects into 3D, enabling direct interaction with their 3D geometry. Post-editing, these objects are re-rendered into 2D, merging into the original image to produce high-fidelity results through a coarse-to-fine enhancement process. The framework supports precise, quantifiable, and physically-plausible editing options such as pose editing, rotation, translation, 3D composition, carving, and serial addition. It marks an initial step towards combining the creative freedom of generative models with the precision of graphics pipelines.
The recent development on large language models makes automatically constructing small programs possible. It thus has the potential to free software engineers from low-level coding and allow us to focus on the perhaps more interesting parts of software development, such as requirement engineering and system testing. In this project, we develop a prototype named AISD (AI-aided Software Development), which is capable of taking high-level (potentially vague) user requirements as inputs, generates detailed use cases, prototype system designs, and subsequently system implementation. Different from existing attempts, AISD is designed to keep the user in the loop, i.e., by repeatedly taking user feedback on use cases, high-level system designs, and prototype implementations through system testing. AISD has been evaluated with a novel benchmark of non-trivial software projects. The experimental results suggest that it might be possible to imagine a future where software engineering is reduced to requirement engineering and system testing only.
Large language models (LLMs) such as ChatGPT have demonstrated unprecedented capabilities in multiple AI tasks. However, hardware inefficiencies have become a significant factor limiting the democratization of LLMs. We propose Chiplet Cloud, an ASIC supercomputer architecture that optimizes total cost of ownership (TCO) per token for serving generative LLMs. Chiplet Cloud fits all model parameters inside the on-chip SRAMs to eliminate bandwidth limitations while moderating the die size to improve system costs while leveraging software mappings to overcome data communication overhead. We propose a comprehensive design methodology that accurately explores a spectrum of major design trade-offs in the joint space of hardware-software and generates a detailed performance-cost analysis on all valid design points. We evaluate Chiplet Cloud on four popular LLMs. Compared to GPU and TPU, our architecture can achieve up to 94x and 15x improvement in TCO/Token respectively, significantly reducing the cost for realistically serving modern LLMs.
Automatically detecting or segmenting cracks in images can help in reducing the cost of maintenance or operations. Detecting, measuring and quantifying cracks for distress analysis in challenging background scenarios is a difficult task as there is no clear boundary that separates cracks from the background. Developed algorithms should handle the inherent challenges associated with data. Some of the perceptually noted challenges are color, intensity, depth, blur, motion-blur, orientation, different region of interest (ROI) for the defect, scale, illumination, complex and challenging background, etc. These variations occur across (crack inter class) and within images (crack intra-class variabilities). Overall, there is significant background (inter) and foreground (intra-class) variability. In this work, we have attempted to reduce the effect of these variations in challenging background scenarios. We have proposed a stochastic width (SW) approach to reduce the effect of these variations. Our proposed approach improves detectability and significantly reduces false positives and negatives. We have measured the performance of our algorithm objectively in terms of mean IoU, false positives and negatives and subjectively in terms of perceptual quality.
Recent research has shown that adversarial patches can manipulate outputs from object detection models. However, the conspicuous patterns on these patches may draw more attention and raise suspicions among humans. Moreover, existing works have primarily focused on the attack performance of individual models and have neglected the generation of adversarial patches for ensemble attacks on multiple object detection models. To tackle these concerns, we propose a novel approach referred to as the More Vivid Patch (MVPatch), which aims to improve the transferability and stealthiness of adversarial patches while considering the limitations observed in prior paradigms, such as easy identification and poor transferability. Our approach incorporates an attack algorithm that decreases object confidence scores of multiple object detectors by using the ensemble attack loss function, thereby enhancing the transferability of adversarial patches. Additionally, we propose a lightweight visual similarity measurement algorithm realized by the Compared Specified Image Similarity (CSS) loss function, which allows for the generation of natural and stealthy adversarial patches without the reliance on additional generative models. Extensive experiments demonstrate that the proposed MVPatch algorithm achieves superior attack transferability compared to similar algorithms in both digital and physical domains, while also exhibiting a more natural appearance. These findings emphasize the remarkable stealthiness and transferability of the proposed MVPatch attack algorithm.
This paper proposes a general network fingerprinting framework, Seqnature, that uses packet sequences as its basic data unit and that makes it simple to implement any fingerprinting technique that can be formulated as a problem of identifying packet exchanges that consistently occur when the fingerprinted event is triggered. We demonstrate the versatility of Seqnature by using it to implement five different fingerprinting techniques, as special cases of the framework, which broadly fall into two categories: (i) fingerprinting techniques that consider features of each individual packet in a packet sequence, e.g., size and direction; and (ii) fingerprinting techniques that only consider stream-wide features, specifically what Internet endpoints are contacted. We illustrate how Seqnature facilitates comparisons of the relative performance of different fingerprinting techniques by applying the five fingerprinting techniques to datasets from the literature. The results confirm findings in prior work, for example that endpoint information alone is insufficient to differentiate between individual events on Internet of Things devices, but also show that smart TV app fingerprints based exclusively on endpoint information are not as distinct as previously reported.
Transformer is a promising neural network learner, and has achieved great success in various machine learning tasks. Thanks to the recent prevalence of multimodal applications and big data, Transformer-based multimodal learning has become a hot topic in AI research. This paper presents a comprehensive survey of Transformer techniques oriented at multimodal data. The main contents of this survey include: (1) a background of multimodal learning, Transformer ecosystem, and the multimodal big data era, (2) a theoretical review of Vanilla Transformer, Vision Transformer, and multimodal Transformers, from a geometrically topological perspective, (3) a review of multimodal Transformer applications, via two important paradigms, i.e., for multimodal pretraining and for specific multimodal tasks, (4) a summary of the common challenges and designs shared by the multimodal Transformer models and applications, and (5) a discussion of open problems and potential research directions for the community.
Transformers have achieved superior performances in many tasks in natural language processing and computer vision, which also intrigues great interests in the time series community. Among multiple advantages of transformers, the ability to capture long-range dependencies and interactions is especially attractive for time series modeling, leading to exciting progress in various time series applications. In this paper, we systematically review transformer schemes for time series modeling by highlighting their strengths as well as limitations through a new taxonomy to summarize existing time series transformers in two perspectives. From the perspective of network modifications, we summarize the adaptations of module level and architecture level of the time series transformers. From the perspective of applications, we categorize time series transformers based on common tasks including forecasting, anomaly detection, and classification. Empirically, we perform robust analysis, model size analysis, and seasonal-trend decomposition analysis to study how Transformers perform in time series. Finally, we discuss and suggest future directions to provide useful research guidance. To the best of our knowledge, this paper is the first work to comprehensively and systematically summarize the recent advances of Transformers for modeling time series data. We hope this survey will ignite further research interests in time series Transformers.
As an effective strategy, data augmentation (DA) alleviates data scarcity scenarios where deep learning techniques may fail. It is widely applied in computer vision then introduced to natural language processing and achieves improvements in many tasks. One of the main focuses of the DA methods is to improve the diversity of training data, thereby helping the model to better generalize to unseen testing data. In this survey, we frame DA methods into three categories based on the diversity of augmented data, including paraphrasing, noising, and sampling. Our paper sets out to analyze DA methods in detail according to the above categories. Further, we also introduce their applications in NLP tasks as well as the challenges.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191