V-LoRA: An Efficient and Flexible System Boosts Vision Applications with LoRA LMM

Large Multimodal Models (LMMs) have shown significant progress in various complex vision tasks with the solid linguistic and reasoning capacity inherited from large language models (LMMs). Low-rank adaptation (LoRA) offers a promising method to integrate external knowledge into LMMs, compensating for their limitations on domain-specific tasks. However, the existing LoRA model serving is excessively computationally expensive and causes extremely high latency. In this paper, we present an end-to-end solution that empowers diverse vision tasks and enriches vision applications with LoRA LMMs. Our system, VaLoRA, enables accurate and efficient vision tasks by 1) an accuracy-aware LoRA adapter generation approach that generates LoRA adapters rich in domain-specific knowledge to meet application-specific accuracy requirements, 2) an adaptive-tiling LoRA adapters batching operator that efficiently computes concurrent heterogeneous LoRA adapters, and 3) a flexible LoRA adapter orchestration mechanism that manages application requests and LoRA adapters to achieve the lowest average response latency. We prototype VaLoRA on five popular vision tasks on three LMMs. Experiment results reveal that VaLoRA improves 24-62% of the accuracy compared to the original LMMs and reduces 20-89% of the latency compared to the state-of-the-art LoRA model serving systems.

MCUBERT: Memory-Efficient BERT Inference on Commodity Microcontrollers

In this paper, we propose MCUBERT to enable language models like BERT on tiny microcontroller units (MCUs) through network and scheduling co-optimization. We observe the embedding table contributes to the major storage bottleneck for tiny BERT models. Hence, at the network level, we propose an MCU-aware two-stage neural architecture search algorithm based on clustered low-rank approximation for embedding compression. To reduce the inference memory requirements, we further propose a novel fine-grained MCU-friendly scheduling strategy. Through careful computation tiling and re-ordering as well as kernel design, we drastically increase the input sequence lengths supported on MCUs without any latency or accuracy penalty. MCUBERT reduces the parameter size of BERT-tiny and BERT-mini by 5.7$\times$ and 3.0$\times$ and the execution memory by 3.5$\times$ and 4.3$\times$, respectively. MCUBERT also achieves 1.5$\times$ latency reduction. For the first time, MCUBERT enables lightweight BERT models on commodity MCUs and processing more than 512 tokens with less than 256KB of memory.

Ab initio nonparametric variable selection for scalable Symbolic Regression with large $p$

Symbolic regression (SR) is a powerful technique for discovering symbolic expressions that characterize nonlinear relationships in data, gaining increasing attention for its interpretability, compactness, and robustness. However, existing SR methods do not scale to datasets with a large number of input variables (referred to as extreme-scale SR), which are common in modern scientific applications. This ``large $p$'' setting, often accompanied by measurement error, leads to slow performance of SR methods and overly complex expressions that are difficult to interpret. To address this scalability challenge, we propose a method called PAN+SR, which combines a key idea of ab initio nonparametric variable selection with SR to efficiently pre-screen large input spaces and reduce search complexity while maintaining accuracy. The use of nonparametric methods eliminates model misspecification, supporting a strategy called parametric-assisted nonparametric (PAN). We also extend SRBench, an open-source benchmarking platform, by incorporating high-dimensional regression problems with various signal-to-noise ratios. Our results demonstrate that PAN+SR consistently enhances the performance of 17 contemporary SR methods, enabling several to achieve state-of-the-art performance on these challenging datasets.

Leveraging Fine-Tuned Language Models for Efficient and Accurate Smart Contract Auditing

The rise of blockchain technologies has greatly accelerated the development and deployment of smart contracts. However, their inherent vulnerabilities and susceptibility to bugs have led to significant financial losses, underscoring the challenges in securing smart contracts. While traditional auditing methods are crucial, they often fall short in addressing the increasing complexity and volume of smart contracts. Recent advancements in Large Language Models (LLMs) offer promising solutions for enhancing software auditing by automatically identifying security vulnerabilities. Despite their potential, the practical application of these models is hindered by substantial computational demands. This paper investigates the feasibility of using smaller, fine-tuned models to achieve comparable or even superior results in smart contract auditing. We introduce the FTSmartAudit framework, which is designed to develop cost-effective, specialized models for smart contract auditing through the fine-tuning of LLMs. Our contributions include: (1) a single-task learning framework that streamlines data preparation, training, evaluation, and continuous learning; (2) a robust dataset generation method utilizing domain-special knowledge distillation to produce high-quality datasets from advanced models like GPT-4o; (3) an adaptive learning strategy to maintain model accuracy and robustness; (4) the proven effectiveness of fine-tuned models in detecting specific vulnerabilities and complex logical errors; and (5) a framework that can be extended to other domains requiring LLM solutions. Our experimental results demonstrate that smaller models can surpass state-of-the-art commercial models and tools in detecting vulnerabilities in smart contracts.

PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization

Private deep neural network (DNN) inference based on secure two-party computation (2PC) enables secure privacy protection for both the server and the client. However, existing secure 2PC frameworks suffer from a high inference latency due to enormous communication. As the communication of both linear and non-linear DNN layers reduces with the bit widths of weight and activation, in this paper, we propose PrivQuant, a framework that jointly optimizes the 2PC-based quantized inference protocols and the network quantization algorithm, enabling communication-efficient private inference. PrivQuant proposes DNN architecture-aware optimizations for the 2PC protocols for communication-intensive quantized operators and conducts graph-level operator fusion for communication reduction. Moreover, PrivQuant also develops a communication-aware mixed precision quantization algorithm to improve inference efficiency while maintaining high accuracy. The network/protocol co-optimization enables PrivQuant to outperform prior-art 2PC frameworks. With extensive experiments, we demonstrate PrivQuant reduces communication by $11\times, 2.5\times \mathrm{and}~ 2.8\times$, which results in $8.7\times, 1.8\times ~ \mathrm{and}~ 2.4\times$ latency reduction compared with SiRNN, COINN, and CoPriv, respectively.

CopyLens: Dynamically Flagging Copyrighted Sub-Dataset Contributions to LLM Outputs

Large Language Models (LLMs) have become pervasive due to their knowledge absorption and text-generation capabilities. Concurrently, the copyright issue for pretraining datasets has been a pressing concern, particularly when generation includes specific styles. Previous methods either focus on the defense of identical copyrighted outputs or find interpretability by individual tokens with computational burdens. However, the gap between them exists, where direct assessments of how dataset contributions impact LLM outputs are missing. Once the model providers ensure copyright protection for data holders, a more mature LLM community can be established. To address these limitations, we introduce CopyLens, a new framework to analyze how copyrighted datasets may influence LLM responses. Specifically, a two-stage approach is employed: First, based on the uniqueness of pretraining data in the embedding space, token representations are initially fused for potential copyrighted texts, followed by a lightweight LSTM-based network to analyze dataset contributions. With such a prior, a contrastive-learning-based non-copyright OOD detector is designed. Our framework can dynamically face different situations and bridge the gap between current copyright detection methods. Experiments show that CopyLens improves efficiency and accuracy by 15.2% over our proposed baseline, 58.7% over prompt engineering methods, and 0.21 AUC over OOD detection baselines.

Ranking Perspective for Tree-based Methods with Applications to Symbolic Feature Selection

Tree-based methods are powerful nonparametric techniques in statistics and machine learning. However, their effectiveness, particularly in finite-sample settings, is not fully understood. Recent applications have revealed their surprising ability to distinguish transformations (which we call symbolic feature selection) that remain obscure under current theoretical understanding. This work provides a finite-sample analysis of tree-based methods from a ranking perspective. We link oracle partitions in tree methods to response rankings at local splits, offering new insights into their finite-sample behavior in regression and feature selection tasks. Building on this local ranking perspective, we extend our analysis in two ways: (i) We examine the global ranking performance of individual trees and ensembles, including Classification and Regression Trees (CART) and Bayesian Additive Regression Trees (BART), providing finite-sample oracle bounds, ranking consistency, and posterior contraction results. (ii) Inspired by the ranking perspective, we propose concordant divergence statistics $\mathcal{T}_0$ to evaluate symbolic feature mappings and establish their properties. Numerical experiments demonstrate the competitive performance of these statistics in symbolic feature selection tasks compared to existing methods.

Sequence-aware Pre-training for Echocardiography Probe Guidance

Cardiac ultrasound probe guidance aims to help novices adjust the 6-DOF probe pose to obtain high-quality sectional images. Cardiac ultrasound faces two major challenges: (1) the inherently complex structure of the heart, and (2) significant individual variations. Previous works have only learned the population-averaged 2D and 3D structures of the heart rather than personalized cardiac structural features, leading to a performance bottleneck. Clinically, we observed that sonographers adjust their understanding of a patient's cardiac structure based on prior scanning sequences, thereby modifying their scanning strategies. Inspired by this, we propose a sequence-aware self-supervised pre-training method. Specifically, our approach learns personalized 2D and 3D cardiac structural features by predicting the masked-out images and actions in a scanning sequence. We hypothesize that if the model can predict the missing content it has acquired a good understanding of the personalized cardiac structure. In the downstream probe guidance task, we also introduced a sequence modeling approach that models individual cardiac structural information based on the images and actions from historical scan data, enabling more accurate navigation decisions. Experiments on a large-scale dataset with 1.36 million samples demonstrated that our proposed sequence-aware paradigm can significantly reduce navigation errors, with translation errors decreasing by 15.90% to 36.87% and rotation errors decreasing by 11.13% to 20.77%, compared to state-of-the-art methods.

AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference

Mixture-of-Experts (MoE) models are designed to enhance the efficiency of large language models (LLMs) without proportionally increasing the computational demands. However, their deployment on edge devices still faces significant challenges due to high on-demand loading overheads from managing sparsely activated experts. This paper introduces AdapMoE, an algorithm-system co-design framework for efficient MoE inference. AdapMoE features adaptive expert gating and management to reduce the on-demand loading overheads. We observe the heterogeneity of experts loading across layers and tokens, based on which we propose a sensitivity-based strategy to adjust the number of activated experts dynamically. Meanwhile, we also integrate advanced prefetching and cache management techniques to further reduce the loading latency. Through comprehensive evaluations on various platforms, we demonstrate AdapMoE consistently outperforms existing techniques, reducing the average number of activated experts by 25% and achieving a 1.35x speedup without accuracy degradation. Code is available at: https://github.com/PKU-SEC-Lab/AdapMoE.

HG-PIPE: Vision Transformer Acceleration with Hybrid-Grained Pipeline

Vision Transformer (ViT) acceleration with field programmable gate array (FPGA) is promising but challenging. Existing FPGA-based ViT accelerators mainly rely on temporal architectures, which process different operators by reusing the same hardware blocks and suffer from extensive memory access overhead. Pipelined architectures, either coarse-grained or fine-grained, unroll the ViT computation spatially for memory access efficiency. However, they usually suffer from significant hardware resource constraints and pipeline bubbles induced by the global computation dependency of ViT. In this paper, we introduce HG-PIPE, a pipelined FPGA accelerator for high-throughput and low-latency ViT processing. HG-PIPE features a hybrid-grained pipeline architecture to reduce on-chip buffer cost and couples the computation dataflow and parallelism design to eliminate the pipeline bubbles. HG-PIPE further introduces careful approximations to implement both linear and non-linear operators with abundant Lookup Tables (LUTs), thus alleviating resource constraints. On a ZCU102 FPGA, HG-PIPE achieves 2.78 times better throughput and 2.52 times better resource efficiency than the prior-art accelerators, e.g., AutoViTAcc. With a VCK190 FPGA, HG-PIPE realizes end-to-end ViT acceleration on a single device and achieves 7118 images/s, which is 2.81 times faster than a V100 GPU.