Publications (17)
Probing Memes in LLMs: A Paradigm for the Entangled Evaluation World
Luzhou Peng, Zhengxin Yang, Honglu Ji +6
Current evaluation paradigms for large language models (LLMs) characterize models and datasets separately, yielding coarse descriptions: items in datasets are treated as pre-labele…
CombinationTS: A Modular Framework for Understanding Time-Series Forecasting Models
Xiaorui Wang, Fanda Fan, Chenxi Wang +9
Recent progress in time-series forecasting has led to rapidly increasing architectural complexity, yet many reported State-of-the-Art gains are statistically fragile or misattribut…
Achieving Consistent and Comparable CPU Evaluation
Chenxi Wang, Lei Wang, Wanling Gao +5
The challenge of CPU evaluation lies in the fact that user-perceived performance metrics can only be measured on an independently running system consisting of the CPU and other ind…
Inference of Component Effect on System Performance
Chenxi Wang, Lei Wang, Wanling Gao +5
In a computer system, multiple components--such as the CPU, memory, and others--work together as a system whose performance can be directly measured. However, the effect of a compo…
AIBench Training: Balanced Industry-Standard AI Training Benchmarking
Fei Tang, Wanling Gao, Jianfeng Zhan +30
Earlier-stage evaluations of a new AI architecture/system need affordable benchmarks. Only using a few AI component benchmarks like MLPerfalone in the other stages may lead to misl…
Hierarchical Masked 3D Diffusion Model for Video Outpainting
Fanda Fan, Chaoxu Guo, Litong Gong +5
Video outpainting aims to adequately complete missing areas at the edges of video frames. Compared to image outpainting, it presents an additional challenge as the model should mai…
On Meta-Evaluation
Hongxiao Li, Chenxi Wang, Fanda Fan +4
Evaluation is the foundation of empirical science, yet the evaluation of evaluation itself -- so-called meta-evaluation -- remains strikingly underdeveloped. While methods such as…
AIBench: An Agile Domain-specific Benchmarking Methodology and an AI Benchmark Suite
Wanling Gao, Fei Tang, Jianfeng Zhan +31
Domain-specific software and hardware co-design is encouraging as it is much easier to achieve efficiency for fewer tasks. Agile domain-specific benchmarking speeds up the process…
A Semantic-based Medical Image Fusion Approach
Fanda Fan, Yunyou Huang, Lei Wang +4
It is necessary for clinicians to comprehensively analyze patient information from different sources. Medical image fusion is a promising approach to providing overall information…
KAIROS: Unified Training for Universal Non-Autoregressive Time Series Forecasting
Kuiye Ding, Fanda Fan, Zheya Wang +5
In the World Wide Web, reliable time series forecasts provide the forward-looking signals that drive resource planning, cache placement, and anomaly response, enabling platforms to…
Landscape of Big Medical Data: A Pragmatic Survey on Prioritized Tasks
Zhifei Zhang, Wanling Gao, Fan Zhang +13
Big medical data poses great challenges to life scientists, clinicians, computer scientists, and engineers. In this paper, a group of life scientists, clinicians, computer scientis…
TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decoding
Kuiye Ding, Fanda Fan, Chunyi Hou +4
Multivariate time series forecasting is essential in domains such as finance, transportation, climate, and energy. However, existing patch-based methods typically adopt fixed-lengt…
AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI
Fanda Fan, Chunjie Luo, Wanling Gao +1
The burgeoning field of Artificial Intelligence Generated Content (AIGC) is witnessing rapid advancements, particularly in video generation. This paper introduces AIGCBench, a pion…
Physics-Aligned Spectral Mamba: Decoupling Semantics and Dynamics for Few-Shot Hyperspectral Target Detection
Luqi Gong, Qixin Xie, Yue Chen +4
Meta-learning facilitates few-shot hyperspectral target detection (HTD), but adapting deep backbones remains challenging. Full-parameter fine-tuning is inefficient and prone to ove…
A veracity preserving model for synthesizing scalable electricity load profiles
Yunyou Huang, Jianfeng Zhan, Chunjie Luo +5
Electricity users are the major players of the electric systems, and electricity consumption is growing at an extraordinary rate. The research on electricity consumption behaviors…
DualSG: A Dual-Stream Explicit Semantic-Guided Multivariate Time Series Forecasting Framework
Kuiye Ding, Fanda Fan, Yao Wang +6
Multivariate Time Series Forecasting plays a key role in many applications. Recent works have explored using Large Language Models for MTSF to take advantage of their reasoning abi…
Tuning-Free Noise Rectification for High Fidelity Image-to-Video Generation
Weijie Li, Litong Gong, Yiran Zhu +4
Image-to-video (I2V) generation tasks always suffer from keeping high fidelity in the open domains. Traditional image animation techniques primarily focus on specific domains such…