Publications (27)
SoK: Prompt Hacking of Large Language Models
Baha Rababah, Shang, Wu +3
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…
Upper Limit on the Chiral Magnetic Effect in Isobar Collisions at the Relativistic Heavy-Ion Collider
STAR Collaboration, M. I. Abdulhamid, B. E. Aboona +342
The chiral magnetic effect (CME) is a phenomenon that arises from the QCD anomaly in the presence of an external magnetic field. The experimental search for its evidence has been o…
TSPTQ-ViT: Two-scaled post-training quantization for vision transformer
Yu-Shan Tai, Ming-Guang Lin, An-Yeu +1
Vision transformers (ViTs) have achieved remarkable performance in various computer vision tasks. However, intensive memory and computation requirements impede ViTs from running on…
AdaBoost-assisted Extreme Learning Machine for Efficient Online Sequential Classification
Yi-Ta Chen, Yu-Chuan Chuang, An-Yeu +1
In this paper, we propose an AdaBoost-assisted extreme learning machine for efficient online sequential classification (AOS-ELM). In order to achieve better accuracy in online sequ…
C3-SL: Circular Convolution-Based Batch-Wise Compression for Communication-Efficient Split Learning
Cheng-Yen Hsieh, Yu-Chuan Chuang, An-Yeu +1
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-resolution global irrigation prediction with Sentinel-2 30m data
Weixin, Wu, Sonal Thakkar +3
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 growt…
Boosting Spatial Reuse via Multiple Paths Multi-Hop Scheduling for Directional mmWave WPANs
Yong Niu, Chuhan Gao, Yong Li +4
With huge unlicensed bandwidth available in most parts of the world, millimeter wave (mmWave) communications in the 60 GHz band has been considered as one of the most promising can…
Leveraging Connected Vehicle Data for Near-Crash Detection and Analysis in Urban Environments
Xinyu Li, Dayong, Wu +2
Urban traffic safety is a pressing concern in modern transportation systems, especially in rapidly growing metropolitan areas where increased traffic congestion, complex road netwo…
Estimate of Background Baseline and Upper Limit on the Chiral Magnetic Effect in Isobar Collisions at GeV at the Relativistic Heavy-Ion Collider
STAR Collaboration, M. I. Abdulhamid, B. E. Aboona +342
For the search of the chiral magnetic effect (CME), STAR previously presented the results from isobar collisions (, ${^{96}_{40}\text{Z…
MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer
Yu-Shan Tai, An-Yeu, Wu
While vision transformers (ViTs) have shown great potential in computer vision tasks, their intense computation and memory requirements pose challenges for practical applications.…
Independent Action Models and Prediction of Combination Treatment Effects for Response Rate, Duration of Response and Tumor Size Change in Oncology Drug Development
Linda Z. Sun, Cai, Wu +4
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 c…
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aaron Blakeman +571
We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 t…
Quick Bypass Mechanism of Zero-Shot Diffusion-Based Image Restoration
Yu-Shan Tai, An-Yeu, Wu
Recent advancements in diffusion models have demonstrated remarkable success in various image generation tasks. Building upon these achievements, diffusion models have also been ef…
Electric-triple-layer model based AC electroosmosis flow
Jiang Hongyuan, Li Shanshan, Ren Yukun +2
The paper presents an novel electric triple layer(ETL) model as an improved model of electrical double layer(EDL) to predict electroosmosis flow rate on the electrode surface at lo…
Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution
Yu-Shan Tai, An-Yeu, Wu
Recently, diffusion models (DMs) have made significant strides in high-quality image generation. However, the multi-step denoising process often results in considerable computation…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
Post-Training Quantization for Vision Mamba with k-Scaled Quantization and Reparameterization
Bo-Yun Shi, Yi-Cheng Lo, An-Yeu +2
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…
Learnable Mixed-precision and Dimension Reduction Co-design for Low-storage Activation
Yu-Shan Tai, Cheng-Yang Chang, Chieh-Fang Teng +2
Recently, deep convolutional neural networks (CNNs) have achieved many eye-catching results. However, deploying CNNs on resource-constrained edge devices is constrained by limited…
Speculating the Impacts of Mediated Social Touch Technology
Russian, Wu, Tim Moesgen +7
With growing research on haptic interfaces, Mediated Social Touch (MST) technologies offer the potential to record, synthesise, and reproduce (RSR) touch experiences across space a…
Efficient and Reliable Vector Similarity Search Using Asymmetric Encoding with NAND-Flash for Many-Class Few-Shot Learning
Hao-Wei Chiang, Chi-Tse Huang, Hsiang-Yun Cheng +4
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 requir…
The Amazon Nova Family of Models: Technical Report and Model Card
Amazon AGI, Aaron Langford, Aayush Shah +783
We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highl…
Integration of LiDAR and Hyperspectral Data for Land-cover Classification: A Case Study
Pedram Ghamisi, Gabriele Cavallaro, Dan +3
In this paper, an approach is proposed to fuse LiDAR and hyperspectral data, which considers both spectral and spatial information in a single framework. Here, an extended self-dua…
LATTE: Low-Precision Approximate Attention with Head-wise Trainable Threshold for Efficient Transformer
Jiing-Ping Wang, Ming-Guang Lin, An-Yeu +1
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 mode…
MithraDetective: A System for Cherry-picked Trendlines Detection
Yoko Nagafuchi, Yin Lin, Kaushal Mamgain +5
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 ov…
Relay-Assisted Carrier Aggregation (RACA) Uplink System for Enhancing Data Rate of Extended Reality (XR)
Chi-Wei Chen, Wen-Chiao Tsai, Lung-Sheng Tsai +2
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 a…
MAUS: A Dataset for Mental Workload Assessmenton N-back Task Using Wearable Sensor
Win-Ken Beh, Yi-Hsuan Wu, An-Yeu +1
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…
Solving Modular Model Expansion Tasks
Shahab Tasharrofi, Xiongnan, Wu +1
The work we describe here is a part of a research program of developing foundations of declarative solving of search problems. We consider the model expansion task as the task repr…