arXiv subjects

Jinjun Xiong

Publications and source records attributed to Jinjun Xiong.

At least 55 records · Page 3Linked to original sources

arXiv2024

Towards Precision Characterization of Communication Disorders using Models of Perceived Pragmatic Similarity

The diagnosis and treatment of individuals with communication disorders offers many opportunities for the application of speech technology, but research so far has not adequately considered: the diversity of conditions, the role of pragmatic deficits, and the challenges of limited data. This paper explores how a general-purpose model of perceived pragmatic similarity may overcome these limitations. It explains how it might support several use cases for clinicians and clients, and presents evidence that a simple model can provide value, and in particular can capture utterance aspects that are relevant to diagnoses of autism and specific language impairment.

cs.CL↗

arXiv2024

LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning

Multimodal large language models (LLMs) have achieved notable success across various domains, while research in the medical field has largely focused on unimodal images. Meanwhile, current general-domain multimodal models for videos still lack the capabilities to understand and engage in conversations about surgical videos. One major contributing factor is the absence of datasets in the surgical field. In this paper, we create a new dataset, Surg-QA, consisting of 102,000 surgical video-instruction pairs, the largest of its kind so far. To build such a dataset, we propose a novel two-stage question-answer generation pipeline with LLM to learn surgical knowledge in a structured manner from the publicly available surgical lecture videos. The pipeline breaks down the generation process into two stages to significantly reduce the task complexity, allowing us to use a more affordable, locally deployed open-source LLM than the premium paid LLM services. It also mitigates the risk of LLM hallucinations during question-answer generation, thereby enhancing the overall quality of the generated data. We further train LLaVA-Surg, a novel vision-language conversational assistant capable of answering open-ended questions about surgical videos, on this Surg-QA dataset, and conduct comprehensive evaluations on zero-shot surgical video question-answering tasks. We show that LLaVA-Surg significantly outperforms all previous general-domain models, demonstrating exceptional multimodal conversational skills in answering open-ended questions about surgical videos. We will release our code, model, and the instruction-tuning dataset.

cs.CV↗

arXiv2024

FASA: a Flexible and Automatic Speech Aligner for Extracting High-quality Aligned Children Speech Data

Automatic Speech Recognition (ASR) for adults' speeches has made significant progress by employing deep neural network (DNN) models recently, but improvement in children's speech is still unsatisfactory due to children's speech's distinct characteristics. DNN models pre-trained on adult data often struggle in generalizing children's speeches with fine tuning because of the lack of high-quality aligned children's speeches. When generating datasets, human annotations are not scalable, and existing forced-alignment tools are not usable as they make impractical assumptions about the quality of the input transcriptions. To address these challenges, we propose a new forced-alignment tool, FASA, as a flexible and automatic speech aligner to extract high-quality aligned children's speech data from many of the existing noisy children's speech data. We demonstrate its usage on the CHILDES dataset and show that FASA can improve data quality by 13.6$\times$ over human annotations.

cs.CL↗

arXiv2024

HiKonv: Maximizing the Throughput of Quantized Convolution With Novel Bit-wise Management and Computation

Quantization for CNN has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data representations. There are, however, no systematic studies on how an existing full-bitwidth processing unit, such as ALU in CPUs and DSP in FPGAs, can be better utilized to deliver significantly higher computation throughput for convolution under various quantized bitwidths. In this study, we propose HiKonv, a unified solution that maximizes the throughput of convolution on a given underlying processing unit with low-bitwidth quantized data inputs through novel bit-wise management and parallel computation. We establish theoretical framework and performance models using a full-bitwidth multiplier for highly parallelized low-bitwidth convolution, and demonstrate new breakthroughs for high-performance computing in this critical domain. For example, a single 32-bit processing unit in CPU can deliver 128 binarized convolution operations (multiplications and additions) and 13 4-bit convolution operations with a single multiplication instruction, and a single 27x18 multiplier in the FPGA DSP can deliver 60, 8 or 2 convolution operations with 1, 4 or 8-bit inputs in one clock cycle. We demonstrate the effectiveness of HiKonv on both CPU and FPGA. On CPU, HiKonv outperforms the baseline implementation with 1 to 8-bit inputs and provides up to 7.6x and 1.4x performance improvements for 1-D convolution, and performs 2.74x and 3.19x over the baseline implementation for 4-bit signed and unsigned data inputs for 2-D convolution. On FPGA, HiKonv solution enables a single DSP to process multiple convolutions with a shorter processing latency. For binarized input, each DSP with HiKonv is equivalent up to 76.6 LUTs. Compared to the DAC-SDC 2020 champion model, HiKonv achieves a 2.37x throughput improvement and 2.61x DSP efficiency improvement, respectively.

cs.AR↗

arXiv2024

QuadraNet V2: Efficient and Sustainable Training of High-Order Neural Networks with Quadratic Adaptation

Machine learning is evolving towards high-order models that necessitate pre-training on extensive datasets, a process associated with significant overheads. Traditional models, despite having pre-trained weights, are becoming obsolete due to architectural differences that obstruct the effective transfer and initialization of these weights. To address these challenges, we introduce a novel framework, QuadraNet V2, which leverages quadratic neural networks to create efficient and sustainable high-order learning models. Our method initializes the primary term of the quadratic neuron using a standard neural network, while the quadratic term is employed to adaptively enhance the learning of data non-linearity or shifts. This integration of pre-trained primary terms with quadratic terms, which possess advanced modeling capabilities, significantly augments the information characterization capacity of the high-order network. By utilizing existing pre-trained weights, QuadraNet V2 reduces the required GPU hours for training by 90\% to 98.4\% compared to training from scratch, demonstrating both efficiency and effectiveness.

cs.LG↗

arXiv2024

Robust Implementation of Retrieval-Augmented Generation on Edge-based Computing-in-Memory Architectures

Large Language Models (LLMs) deployed on edge devices learn through fine-tuning and updating a certain portion of their parameters. Although such learning methods can be optimized to reduce resource utilization, the overall required resources remain a heavy burden on edge devices. Instead, Retrieval-Augmented Generation (RAG), a resource-efficient LLM learning method, can improve the quality of the LLM-generated content without updating model parameters. However, the RAG-based LLM may involve repetitive searches on the profile data in every user-LLM interaction. This search can lead to significant latency along with the accumulation of user data. Conventional efforts to decrease latency result in restricting the size of saved user data, thus reducing the scalability of RAG as user data continuously grows. It remains an open question: how to free RAG from the constraints of latency and scalability on edge devices? In this paper, we propose a novel framework to accelerate RAG via Computing-in-Memory (CiM) architectures. It accelerates matrix multiplications by performing in-situ computation inside the memory while avoiding the expensive data transfer between the computing unit and memory. Our framework, Robust CiM-backed RAG (RoCR), utilizing a novel contrastive learning-based training method and noise-aware training, can enable RAG to efficiently search profile data with CiM. To the best of our knowledge, this is the first work utilizing CiM to accelerate RAG.

cs.LG↗

arXiv2024

From Keyboard to Chatbot: An AI-powered Integration Platform with Large-Language Models for Teaching Computational Thinking for Young Children

Teaching programming in early childhood (4-9) to enhance computational thinking has gained popularity in the recent movement of computer science for all. However, current practices ignore some fundamental issues resulting from young children's developmental readiness, such as the sustained capability to keyboarding, the decomposition of complex tasks to small tasks, the need for intuitive mapping from abstract programming to tangible outcomes, and the limited amount of screen time exposure. To address these issues in this paper, we present a novel methodology with an AI-powered integration platform to effectively teach computational thinking for young children. The system features a hybrid pedagogy that supports both the top-down and bottom-up approach for teaching computational thinking. Young children can describe their desired task in natural language, while the system can respond with an easy-to-understand program consisting of the right level of decomposed sub-tasks. A tangible robot can immediately execute the decomposed program and demonstrate the program's outcomes to young children. The system is equipped with an intelligent chatbot that can interact with young children through natural languages, and children can speak to the chatbot to complete all the needed programming tasks, while the chatbot orchestrates the execution of the program onto the robot. This would completely eliminates the need of keyboards for young children to program. By developing such a system, we aim to make the concept of computational thinking more accessible to young children, fostering a natural understanding of programming concepts without the need of explicit programming skills. Through the interactive experience provided by the robotic agent, our system seeks to engage children in an effective manner, contributing to the field of educational technology for early childhood computer science education.

cs.HC↗

arXiv2024

xMLP: Revolutionizing Private Inference with Exclusive Square Activation

Private Inference (PI) enables deep neural networks (DNNs) to work on private data without leaking sensitive information by exploiting cryptographic primitives such as multi-party computation (MPC) and homomorphic encryption (HE). However, the use of non-linear activations such as ReLU in DNNs can lead to impractically high PI latency in existing PI systems, as ReLU requires the use of costly MPC computations, such as Garbled Circuits. Since square activations can be processed by Beaver's triples hundreds of times faster compared to ReLU, they are more friendly to PI tasks, but using them leads to a notable drop in model accuracy. This paper starts by exploring the reason for such an accuracy drop after using square activations, and concludes that this is due to an "information compounding" effect. Leveraging this insight, we propose xMLP, a novel DNN architecture that uses square activations exclusively while maintaining parity in both accuracy and efficiency with ReLU-based DNNs. Our experiments on CIFAR-100 and ImageNet show that xMLP models consistently achieve better performance than ResNet models with fewer activation layers and parameters while maintaining consistent performance with its ReLU-based variants. Remarkably, when compared to state-of-the-art PI Models, xMLP demonstrates superior performance, achieving a 0.58% increase in accuracy with 7x faster PI speed. Moreover, it delivers a significant accuracy improvement of 4.96% while maintaining the same PI latency. When offloading PI to the GPU, xMLP is up to 700x faster than the previous state-of-the-art PI model with comparable accuracy.

cs.LG↗

arXiv2024

FL-NAS: Towards Fairness of NAS for Resource Constrained Devices via Large Language Models

Neural Architecture Search (NAS) has become the de fecto tools in the industry in automating the design of deep neural networks for various applications, especially those driven by mobile and edge devices with limited computing resources. The emerging large language models (LLMs), due to their prowess, have also been incorporated into NAS recently and show some promising results. This paper conducts further exploration in this direction by considering three important design metrics simultaneously, i.e., model accuracy, fairness, and hardware deployment efficiency. We propose a novel LLM-based NAS framework, FL-NAS, in this paper, and show experimentally that FL-NAS can indeed find high-performing DNNs, beating state-of-the-art DNN models by orders-of-magnitude across almost all design considerations.

cs.LG↗

arXiv2024

"The teachers are confused as well": A Multiple-Stakeholder Ethics Discussion on Large Language Models in Computing Education

Large Language Models (LLMs) are advancing quickly and impacting people's lives for better or worse. In higher education, concerns have emerged such as students' misuse of LLMs and degraded education outcomes. To unpack the ethical concerns of LLMs for higher education, we conducted a case study consisting of stakeholder interviews (n=20) in higher education computer science. We found that students use several distinct mental models to interact with LLMs - LLMs serve as a tool for (a) writing, (b) coding, and (c) information retrieval, which differ somewhat in ethical considerations. Students and teachers brought up ethical issues that directly impact them, such as inaccurate LLM responses, hallucinations, biases, privacy leakage, and academic integrity issues. Participants emphasized the necessity of guidance and rules for the use of LLMs in higher education, including teaching digital literacy, rethinking education, and having cautious and contextual policies. We reflect on the ethical challenges and propose solutions.

cs.CY↗

arXiv2023

Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling

Graph convolutional networks (GCNs) have recently achieved great empirical success in learning graph-structured data. To address its scalability issue due to the recursive embedding of neighboring features, graph topology sampling has been proposed to reduce the memory and computational cost of training GCNs, and it has achieved comparable test performance to those without topology sampling in many empirical studies. To the best of our knowledge, this paper provides the first theoretical justification of graph topology sampling in training (up to) three-layer GCNs for semi-supervised node classification. We formally characterize some sufficient conditions on graph topology sampling such that GCN training leads to a diminishing generalization error. Moreover, our method tackles the nonconvex interaction of weights across layers, which is under-explored in the existing theoretical analyses of GCNs. This paper characterizes the impact of graph structures and topology sampling on the generalization performance and sample complexity explicitly, and the theoretical findings are also justified through numerical experiments.

cs.LG↗

arXiv2023

QuadraNet: Improving High-Order Neural Interaction Efficiency with Hardware-Aware Quadratic Neural Networks

Recent progress in computer vision-oriented neural network designs is mostly driven by capturing high-order neural interactions among inputs and features. And there emerged a variety of approaches to accomplish this, such as Transformers and its variants. However, these interactions generate a large amount of intermediate state and/or strong data dependency, leading to considerable memory consumption and computing cost, and therefore compromising the overall runtime performance. To address this challenge, we rethink the high-order interactive neural network design with a quadratic computing approach. Specifically, we propose QuadraNet -- a comprehensive model design methodology from neuron reconstruction to structural block and eventually to the overall neural network implementation. Leveraging quadratic neurons' intrinsic high-order advantages and dedicated computation optimization schemes, QuadraNet could effectively achieve optimal cognition and computation performance. Incorporating state-of-the-art hardware-aware neural architecture search and system integration techniques, QuadraNet could also be well generalized in different hardware constraint settings and deployment scenarios. The experiment shows thatQuadraNet achieves up to 1.5$\times$ throughput, 30% less memory footprint, and similar cognition performance, compared with the state-of-the-art high-order approaches.

cs.LG↗

arXiv2023

Parallelizing Maximal Clique Enumeration on GPUs

We present a GPU solution for exact maximal clique enumeration (MCE) that performs a search tree traversal following the Bron-Kerbosch algorithm. Prior works on parallelizing MCE on GPUs perform a breadth-first traversal of the tree, which has limited scalability because of the explosion in the number of tree nodes at deep levels. We propose to parallelize MCE on GPUs by performing depth-first traversal of independent subtrees in parallel. Since MCE suffers from high load imbalance and memory capacity requirements, we propose a worker list for dynamic load balancing, as well as partial induced subgraphs and a compact representation of excluded vertex sets to regulate memory consumption. Our evaluation shows that our GPU implementation on a single GPU outperforms the state-of-the-art parallel CPU implementation by a geometric mean of 4.9x (up to 16.7x), and scales efficiently to multiple GPUs. Our code has been open-sourced to enable further research on accelerating MCE.

cs.DC↗

arXiv2023

CODAG: Characterizing and Optimizing Decompression Algorithms for GPUs

Data compression and decompression have become vital components of big-data applications to manage the exponential growth in the amount of data collected and stored. Furthermore, big-data applications have increasingly adopted GPUs due to their high compute throughput and memory bandwidth. Prior works presume that decompression is memory-bound and have dedicated most of the GPU's threads to data movement and adopted complex software techniques to hide memory latency for reading compressed data and writing uncompressed data. This paper shows that these techniques lead to poor GPU resource utilization as most threads end up waiting for the few decoding threads, exposing compute and synchronization latencies. Based on this observation, we propose CODAG, a novel and simple kernel architecture for high throughput decompression on GPUs. CODAG eliminates the use of specialized groups of threads, frees up compute resources to increase the number of parallel decompression streams, and leverages the ample compute activities and the GPU's hardware scheduler to tolerate synchronization, compute, and memory latencies. Furthermore, CODAG provides a framework for users to easily incorporate new decompression algorithms without being burdened with implementing complex optimizations to hide memory latency. We validate our proposed architecture with three different encoding techniques, RLE v1, RLE v2, and Deflate, and a wide range of large datasets from different domains. We show that CODAG provides 13.46x, 5.69x, and 1.18x speed up for RLE v1, RLE v2, and Deflate, respectively, when compared to the state-of-the-art decompressors from NVIDIA RAPIDS.

cs.DC↗

arXiv2023

Image Harmonization with Diffusion Model

Image composition in image editing involves merging a foreground image with a background image to create a composite. Inconsistent lighting conditions between the foreground and background often result in unrealistic composites. Image harmonization addresses this challenge by adjusting illumination and color to achieve visually appealing and consistent outputs. In this paper, we present a novel approach for image harmonization by leveraging diffusion models. We conduct a comparative analysis of two conditional diffusion models, namely Classifier-Guidance and Classifier-Free. Our focus is on addressing the challenge of adjusting illumination and color in foreground images to create visually appealing outputs that seamlessly blend with the background. Through this research, we establish a solid groundwork for future investigations in the realm of diffusion model-based image harmonization.

cs.CV↗

arXiv2023

Can Language Models Be Specific? How?

"He is a person", "Paris is located on the earth". Both statements are correct but meaningless - due to lack of specificity. In this paper, we propose to measure how specific the language of pre-trained language models (PLMs) is. To achieve this, we introduce a novel approach to build a benchmark for specificity testing by forming masked token prediction tasks with prompts. For instance, given "Toronto is located in [MASK].", we want to test whether a more specific answer will be better filled in by PLMs, e.g., Ontario instead of Canada. From our evaluations, we show that existing PLMs have only a slight preference for more specific answers. We identify underlying factors affecting the specificity and design two prompt-based methods to improve the specificity. Results show that the specificity of the models can be improved by the proposed methods without additional training. We hope this work can bring to awareness the notion of specificity of language models and encourage the research community to further explore this important but understudied problem.

cs.CL↗

arXiv2023

GPU-Initiated On-Demand High-Throughput Storage Access in the BaM System Architecture

Graphics Processing Units (GPUs) have traditionally relied on the host CPU to initiate access to the data storage. This approach is well-suited for GPU applications with known data access patterns that enable partitioning of their dataset to be processed in a pipelined fashion in the GPU. However, emerging applications such as graph and data analytics, recommender systems, or graph neural networks, require fine-grained, data-dependent access to storage. CPU initiation of storage access is unsuitable for these applications due to high CPU-GPU synchronization overheads, I/O traffic amplification, and long CPU processing latencies. GPU-initiated storage removes these overheads from the storage control path and, thus, can potentially support these applications at much higher speed. However, there is a lack of systems architecture and software stack that enable efficient GPU-initiated storage access. This work presents a novel system architecture, BaM, that fills this gap. BaM features a fine-grained software cache to coalesce data storage requests while minimizing I/O traffic amplification. This software cache communicates with the storage system via high-throughput queues that enable the massive number of concurrent threads in modern GPUs to make I/O requests at a high rate to fully utilize the storage devices and the system interconnect. Experimental results show that BaM delivers 1.0x and 1.49x end-to-end speed up for BFS and CC graph analytics benchmarks while reducing hardware costs by up to 21.7x over accessing the graph data from the host memory. Furthermore, BaM speeds up data-analytics workloads by 5.3x over CPU-initiated storage access on the same hardware.

cs.DC↗

arXiv2022

A Moral- and Event- Centric Inspection of Gender Bias in Fairy Tales at A Large Scale

Fairy tales are a common resource for young children to learn a language or understand how a society works. However, gender bias, e.g., stereotypical gender roles, in this literature may cause harm and skew children's world view. Instead of decades of qualitative and manual analysis of gender bias in fairy tales, we computationally analyze gender bias in a fairy tale dataset containing 624 fairy tales from 7 different cultures. We specifically examine gender difference in terms of moral foundations, which are measures of human morality, and events, which reveal human activities associated with each character. We find that the number of male characters is two times that of female characters, showing a disproportionate gender representation. Our analysis further reveal stereotypical portrayals of both male and female characters in terms of moral foundations and events. Female characters turn out more associated with care-, loyalty- and sanctity- related moral words, while male characters are more associated with fairness- and authority- related moral words. Female characters' events are often about emotion (e.g., weep), appearance (e.g., comb), household (e.g., bake), etc.; while male characters' events are more about profession (e.g., hunt), violence (e.g., destroy), justice (e.g., judge), etc. Gender bias in terms of moral foundations shows an obvious difference across cultures. For example, female characters are more associated with care and sanctity in high uncertainty-avoidance cultures which are less open to changes and unpredictability. Based on the results, we propose implications for children's literature and early literacy research.

cs.CL↗