arXiv subjects

Wu

Publications and source records attributed to Wu.

At least 19 recordsLinked to original sources

arXiv2026

Never the Number: Structural Abstention for AI Systems Whose Answers Are Consumed as Fact

Large language models have made natural language interfaces to databases (NLIDB) newly credible, but LLM text-to-SQL systems fail in a way that matters for deployment: a hallucinated column or a mis-aggregated total yields a fluent wrong answer, indistinguishable at the point of use from a right one. Where the consumer cannot inspect the generated query, as in enterprise AI deployments and operational dashboards, and increasingly where the consumer is a tool-using agent rather than a person, accuracy alone is insufficient: nothing marks which answers to distrust. This is a reliability problem before it is an accuracy problem. We propose an architectural pattern for such systems, a trusted kernel with a generative shell, resting on one invariant: a component that can fabricate may influence which question the system answers, never which value it returns. A generative shell interprets underspecified input and phrases replies; a deterministic kernel matches fully specified questions against a bounded set of answerable question shapes and compiles them to queries by deterministic execution. The two meet at a confirmation the user reads before any value is computed, and requests the kernel cannot express are declined rather than approximated. We call this structural abstention, and distinguish it from the statistical abstention of selective prediction and calibrated confidence: refusal here needs no confidence estimate, because unanswerable requests are unrepresentable. We specify the pattern implementation-independently, give a five-decision recipe and work it across three domains, extend the invariant from returned values to the actions of agentic systems, and report a two-year production case study alongside two generative alternatives, a fine-tuned parser and a tool-retrieval agent. We close against enterprise and reliability benchmarks published since.

cs.AI↗

arXiv2026

Speculating the Impacts of Mediated Social Touch Technology

With growing research on haptic interfaces, Mediated Social Touch (MST) technologies offer the potential to record, synthesise, and reproduce (RSR) touch experiences across space and time, enabling, for instance, a hug from afar and from the past. Although much of the existing research highlights the direct benefits of these systems, such as reducing loneliness and providing emotional support, little attention has been paid to their broader sociotechnical impacts. To address this gap, we used the Future Ripples method to speculate on possible effects of MST. We conducted three workshops with 24 participants, including potential users, domain experts, and haptics researchers. Throughout these sessions, participants collectively envisioned possible future scenarios, alongside opportunities and threats, and proposed actionable responses. Our qualitative analysis organised these insights into four themes and three distinctive challenges. These findings offer haptics researchers intervention points across the RSR pipeline to inform MST design, alongside methodological insights from applying Future Ripples to MST technology.

cs.HC↗

arXiv2026

Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution

Recently, diffusion models (DMs) have made significant strides in high-quality image generation. However, the multi-step denoising process often results in considerable computational overhead, impeding deployment on resource-constrained edge devices. Existing methods mitigate this issue by compressing models and adjusting the time step sequence. However, they overlook input redundancy and require lengthy search times. In this paper, we propose Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution. Recognizing indistinguishable early-stage generated images, we introduce Coarse-to-Fine Denoising (C2F) to reduce computation during coarse feature generation. Furthermore, we design Time Step Sequence Redistribution (TRD) for efficient sampling trajectory adjustment, requiring less than 10 minutes for search. Experimental results demonstrate that the proposed methods achieve near-lossless performance with an 80% to 90% reduction in computation on CIFAR10 and LSUN-Church.

cs.CV↗

arXiv2025

Quick Bypass Mechanism of Zero-Shot Diffusion-Based Image Restoration

Recent advancements in diffusion models have demonstrated remarkable success in various image generation tasks. Building upon these achievements, diffusion models have also been effectively adapted to image restoration tasks, e.g., super-resolution and deblurring, aiming to recover high-quality images from degraded inputs. Although existing zero-shot approaches enable pretrained diffusion models to perform restoration tasks without additional fine-tuning, these methods often suffer from prolonged iteration times in the denoising process. To address this limitation, we propose a Quick Bypass Mechanism (QBM), a strategy that significantly accelerates the denoising process by initializing from an intermediate approximation, effectively bypassing early denoising steps. Furthermore, recognizing that approximation may introduce inconsistencies, we introduce a Revised Reverse Process (RRP), which adjusts the weighting of random noise to enhance the stochasticity and mitigate potential disharmony. We validate proposed methods on ImageNet-1K and CelebA-HQ across multiple image restoration tasks, e.g., super-resolution, deblurring, and compressed sensing. Our experimental results show that the proposed methods can effectively accelerate existing methods while maintaining original performance.

cs.CV↗

arXiv2025

Post-Training Quantization for Vision Mamba with k-Scaled Quantization and Reparameterization

The Mamba model, utilizing a structured state-space model (SSM), offers linear time complexity and demonstrates significant potential. Vision Mamba (ViM) extends this framework to vision tasks by incorporating a bidirectional SSM and patch embedding, surpassing Transformer-based models in performance. While model quantization is essential for efficient computing, existing works have focused solely on the original Mamba model and have not been applied to ViM. Additionally, they neglect quantizing the SSM layer, which is central to Mamba and can lead to substantial error propagation by naive quantization due to its inherent structure. In this paper, we focus on the post-training quantization (PTQ) of ViM. We address the issues with three core techniques: 1) a k-scaled token-wise quantization method for linear and convolutional layers, 2) a reparameterization technique to simplify hidden state quantization, and 3) a factor-determining method that reduces computational overhead by integrating operations. Through these methods, the error caused by PTQ can be mitigated. Experimental results on ImageNet-1k demonstrate only a 0.8-1.2\% accuracy degradation due to PTQ, highlighting the effectiveness of our approach.

eess.IV↗

arXiv2024

SoK: Prompt Hacking of Large Language Models

The safety and robustness of large language models (LLMs) based applications remain critical challenges in artificial intelligence. Among the key threats to these applications are prompt hacking attacks, which can significantly undermine the security and reliability of LLM-based systems. In this work, we offer a comprehensive and systematic overview of three distinct types of prompt hacking: jailbreaking, leaking, and injection, addressing the nuances that differentiate them despite their overlapping characteristics. To enhance the evaluation of LLM-based applications, we propose a novel framework that categorizes LLM responses into five distinct classes, moving beyond the traditional binary classification. This approach provides more granular insights into the AI's behavior, improving diagnostic precision and enabling more targeted enhancements to the system's safety and robustness.

cs.CR↗

arXiv2024

Leveraging Connected Vehicle Data for Near-Crash Detection and Analysis in Urban Environments

Urban traffic safety is a pressing concern in modern transportation systems, especially in rapidly growing metropolitan areas where increased traffic congestion, complex road networks, and diverse driving behaviors exacerbate the risk of traffic incidents. Traditional traffic crash data analysis offers valuable insights but often overlooks a broader range of road safety risks. Near-crash events, which occur more frequently and signal potential collisions, provide a more comprehensive perspective on traffic safety. However, city-scale analysis of near-crash events remains limited due to the significant challenges in large-scale real-world data collection, processing, and analysis. This study utilizes one month of connected vehicle data, comprising billions of records, to detect and analyze near-crash events across the road network in the City of San Antonio, Texas. We propose an efficient framework integrating spatial-temporal buffering and heading algorithms to accurately identify and map near-crash events. A binary logistic regression model is employed to assess the influence of road geometry, traffic volume, and vehicle types on near-crash risks. Additionally, we examine spatial and temporal patterns, including variations by time of day, day of the week, and road category. The findings of this study show that the vehicles on more than half of road segments will be involved in at least one near-crash event. In addition, more than 50% near-crash events involved vehicles traveling at speeds over 57.98 mph, and many occurred at short distances between vehicles. The analysis also found that wider roadbeds and multiple lanes reduced near-crash risks, while single-unit trucks slightly increased the likelihood of near-crash events. Finally, the spatial-temporal analysis revealed that near-crash risks were most prominent during weekday peak hours, especially in downtown areas.

stat.AP↗

arXiv2024

Efficient and Reliable Vector Similarity Search Using Asymmetric Encoding with NAND-Flash for Many-Class Few-Shot Learning

While memory-augmented neural networks (MANNs) offer an effective solution for few-shot learning (FSL) by integrating deep neural networks with external memory, the capacity requirements and energy overhead of data movement become enormous due to the large number of support vectors in many-class FSL scenarios. Various in-memory search solutions have emerged to improve the energy efficiency of MANNs. NAND-based multi-bit content addressable memory (MCAM) is a promising option due to its high density and large capacity. Despite its potential, MCAM faces limitations such as a restricted number of word lines, limited quantization levels, and non-ideal effects like varying string currents and bottleneck effects, which lead to significant accuracy drops. To address these issues, we propose several innovative methods. First, the Multi-bit Thermometer Code (MTMC) leverages the extensive capacity of MCAM to enhance vector precision using cumulative encoding rules, thereby mitigating the bottleneck effect. Second, the Asymmetric vector similarity search (AVSS) reduces the precision of the query vector while maintaining that of the support vectors, thereby minimizing the search iterations and improving efficiency in many-class scenarios. Finally, the Hardware-Aware Training (HAT) method optimizes controller training by modeling the hardware characteristics of MCAM, thus enhancing the reliability of the system. Our integrated framework reduces search iterations by up to 32 times, and increases overall accuracy by 1.58% to 6.94%.

cs.AR↗

arXiv2024

Relay-Assisted Carrier Aggregation (RACA) Uplink System for Enhancing Data Rate of Extended Reality (XR)

In Extended Reality (XR) applications, high data rates and low latency are crucial for immersive experiences. Uplink transmission in XR is challenging due to the limited antennas and power of lightweight XR devices. To improve data transmission rates, we investigate a relay-assisted carrier aggregation (RACA) system. The XR device simultaneously transmits data to an access point (AP) and a relay in proximity over low-frequency and high-frequency bands, respectively. Then, the relay down-converts and amplifies the signals to the AP, effectively acting as an additional transmit antenna for the XR device. In this paper, we propose two algorithms to maximize the data rate of the XR device in their respective protocols. In the centralized protocol, the rate maximization problem is equivalently transformed as a weighted mean square error minimization (WMMSE) problem which can be solved iteratively by alternative optimization. In the distributed protocol, the rate maximization problem is decomposed into two independent sub-problems where the rate of the direct link and the rate of the relay link are maximized by singular value decomposition (SVD)-based methods with water-filling (WF). Simulation results show that the rate of the RACA system is improved by $32\%$ compared to that of the conventional carrier aggregation scheme.

eess.SP↗

arXiv2024

LATTE: Low-Precision Approximate Attention with Head-wise Trainable Threshold for Efficient Transformer

With the rise of Transformer models in NLP and CV domain, Multi-Head Attention has been proven to be a game-changer. However, its expensive computation poses challenges to the model throughput and efficiency, especially for the long sequence tasks. Exploiting the sparsity in attention has been proven to be an effective way to reduce computation. Nevertheless, prior works do not consider the various distributions among different heads and lack a systematic method to determine the threshold. To address these challenges, we propose Low-Precision Approximate Attention with Head-wise Trainable Threshold for Efficient Transformer (LATTE). LATTE employs a headwise threshold-based filter with the low-precision dot product and computation reuse mechanism to reduce the computation of MHA. Moreover, the trainable threshold is introduced to provide a systematic method for adjusting the thresholds and enable end-to-end optimization. Experimental results indicate LATTE can smoothly adapt to both NLP and CV tasks, offering significant computation savings with only a minor compromise in performance. Also, the trainable threshold is shown to be essential for the leverage between the performance and the computation. As a result, LATTE filters up to 85.16% keys with only a 0.87% accuracy drop in the CV task and 89.91% keys with a 0.86 perplexity increase in the NLP task.

eess.IV↗

arXiv2024

MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer

While vision transformers (ViTs) have shown great potential in computer vision tasks, their intense computation and memory requirements pose challenges for practical applications. Existing post-training quantization methods leverage value redistribution or specialized quantizers to address the non-normal distribution in ViTs. However, without considering the asymmetry in activations and relying on hand-crafted settings, these methods often struggle to maintain performance under low-bit quantization. To overcome these challenges, we introduce SmoothQuant with bias term (SQ-b) to alleviate the asymmetry issue and reduce the clamping loss. We also introduce optimal scaling factor ratio search (OPT-m) to determine quantization parameters by a data-dependent mechanism automatically. To further enhance the compressibility, we incorporate the above-mentioned techniques and propose a mixed-precision post-training quantization framework for vision transformers (MPTQ-ViT). We develop greedy mixed-precision quantization (Greedy MP) to allocate layer-wise bit-width considering both model performance and compressibility. Our experiments on ViT, DeiT, and Swin demonstrate significant accuracy improvements compared with SOTA on the ImageNet dataset. Specifically, our proposed methods achieve accuracy improvements ranging from 0.90% to 23.35% on 4-bit ViTs with single-precision and from 3.82% to 78.14% on 5-bit fully quantized ViTs with mixed-precision.

cs.CV↗

arXiv2023

TSPTQ-ViT: Two-scaled post-training quantization for vision transformer

Vision transformers (ViTs) have achieved remarkable performance in various computer vision tasks. However, intensive memory and computation requirements impede ViTs from running on resource-constrained edge devices. Due to the non-normally distributed values after Softmax and GeLU, post-training quantization on ViTs results in severe accuracy degradation. Moreover, conventional methods fail to address the high channel-wise variance in LayerNorm. To reduce the quantization loss and improve classification accuracy, we propose a two-scaled post-training quantization scheme for vision transformer (TSPTQ-ViT). We design the value-aware two-scaled scaling factors (V-2SF) specialized for post-Softmax and post-GeLU values, which leverage the bit sparsity in non-normal distribution to save bit-widths. In addition, the outlier-aware two-scaled scaling factors (O-2SF) are introduced to LayerNorm, alleviating the dominant impacts from outlier values. Our experimental results show that the proposed methods reach near-lossless accuracy drops (<0.5%) on the ImageNet classification task under 8-bit fully quantized ViTs.

eess.IV↗

arXiv2022

C3-SL: Circular Convolution-Based Batch-Wise Compression for Communication-Efficient Split Learning

Most existing studies improve the efficiency of Split learning (SL) by compressing the transmitted features. However, most works focus on dimension-wise compression that transforms high-dimensional features into a low-dimensional space. In this paper, we propose circular convolution-based batch-wise compression for SL (C3-SL) to compress multiple features into one single feature. To avoid information loss while merging multiple features, we exploit the quasi-orthogonality of features in high-dimensional space with circular convolution and superposition. To the best of our knowledge, we are the first to explore the potential of batch-wise compression under the SL scenario. Based on the simulation results on CIFAR-10 and CIFAR-100, our method achieves a 16x compression ratio with negligible accuracy drops compared with the vanilla SL. Moreover, C3-SL significantly reduces 1152x memory and 2.25x computation overhead compared to the state-of-the-art dimension-wise compression method.

cs.LG↗

arXiv2022

Learnable Mixed-precision and Dimension Reduction Co-design for Low-storage Activation

Recently, deep convolutional neural networks (CNNs) have achieved many eye-catching results. However, deploying CNNs on resource-constrained edge devices is constrained by limited memory bandwidth for transmitting large intermediated data during inference, i.e., activation. Existing research utilizes mixed-precision and dimension reduction to reduce computational complexity but pays less attention to its application for activation compression. To further exploit the redundancy in activation, we propose a learnable mixed-precision and dimension reduction co-design system, which separates channels into groups and allocates specific compression policies according to their importance. In addition, the proposed dynamic searching technique enlarges search space and finds out the optimal bit-width allocation automatically. Our experimental results show that the proposed methods improve 3.54%/1.27% in accuracy and save 0.18/2.02 bits per value over existing mixed-precision methods on ResNet18 and MobileNetv2, respectively.

eess.IV↗

arXiv2021

MAUS: A Dataset for Mental Workload Assessmenton N-back Task Using Wearable Sensor

This paper describes an open-access database focusing on the study of mental workload (MW) assessment system for wearable devices. A wristband photoplethysmogram (PPG) was provided as a representative of wearable devices. In addition, a clinical device that can record Electrocardiography (ECG) , galvanic skin response (GSR) and, fingertip PPG was included in the database as a reference. The MW was induced by performing the N-back task with 22 subjects. The participants were asked to answer the Pittsburgh Sleep Quality Index (PSQI) questionnaire at the beginning of the experiment and the NASA Task Load Index (NASA-TLX) questionnaire after each N-back task. The result of data analysis show the potential uses of the recorded modalities and the feasibility of the MW elicitation protocol. Finally the MAUS dataset is now available for academic use (The MAUS dataset is available at IEEE Dataport: https://ieee-dataport.org/open-access/maus-dataset-mental-workload-assessment-n-back-task-using-wearable-sensor). Besides, we also presents a reproducible baseline system as a preliminary benchmark (The code of the baseline system on MAUS dataset is available on Github: https://github.com/rickwu11/MAUS\_dataset\_baseline\_system), which testing accuracy are 71.6 %, 66.7 %, and 59.9 % in ECG, fingertip PPG, wristband PPG, respectively.

eess.SP↗

arXiv2021

Independent Action Models and Prediction of Combination Treatment Effects for Response Rate, Duration of Response and Tumor Size Change in Oncology Drug Development

An unprecedented number of new cancer targets are in development, and most are being developed in combination therapies. Early oncology development is strategically challenged in choosing the best combinations to move forward to late stage development. The most common early endpoints to be assessed in such decision-making include objective response rate, duration of response and tumor size change. In this paper, using independent-drug-action and Bliss-drug-independence concepts as a foundation, we introduce simple models to predict combination therapy efficacy for duration of response and tumor size change. These models complement previous publications using the independent action models (Palmer 2017, Schmidt 2020) to predict progression-free survival and objective response rate and serve as new predictive models to understand drug combinations for early endpoints. The models can be applied to predict the combination treatment effect for early endpoints given monotherapy data, or to estimate the possible effect of one monotherapy in the combination if data are available from the combination therapy and the other monotherapy. Such quantitative work facilitates efficient oncology drug development.

stat.AP↗

arXiv2020

High-resolution global irrigation prediction with Sentinel-2 30m data

An accurate and precise understanding of global irrigation usage is crucial for a variety of climate science efforts. Irrigation is highly energy-intensive, and as population growth continues at its current pace, increases in crop need and water usage will have an impact on climate change. Precise irrigation data can help with monitoring water usage and optimizing agricultural yield, particularly in developing countries. Irrigation data, in tandem with precipitation data, can be used to predict water budgets as well as climate and weather modeling. With our research, we produce an irrigation prediction model that combines unsupervised clustering of Normalized Difference Vegetation Index (NDVI) temporal signatures with a precipitation heuristic to label the months that irrigation peaks for each cropland cluster in a given year. We have developed a novel irrigation model and Python package ("Irrigation30") to generate 30m resolution irrigation predictions of cropland worldwide. With a small crowdsourced test set of cropland coordinates and irrigation labels, using a fraction of the resources used by the state-of-the-art NASA-funded GFSAD30 project with irrigation data limited to India and Australia, our model was able to achieve consistency scores in excess of 97\% and an accuracy of 92\% in a small geo-diverse randomly sampled test set.

cs.CV↗

arXiv2020

MithraDetective: A System for Cherry-picked Trendlines Detection

Given a data set, misleading conclusions can be drawn from it by cherry-picking selected samples. One important class of conclusions is a trend derived from a data set of values over time. Our goal is to evaluate whether the 'trends' described by the extracted samples are representative of the true situation represented in the data. We demonstrate MithraDetective, a system to compute a support score to indicate how cherry-picked a statement is; that is, whether the reported trend is well-supported by the data. The system can also be used to discover more supported alternatives. MithraDetective provides an interactive visual interface for both tasks.

cs.DB↗