collaborators

9 papers

cs.AI2026

When AI Designs AI: Innovation or Imitation?

Yikang Yang, Zhengxin Yang, Luzhou Peng +4

Recent advances in LLM agents have made them increasingly capable of designing methods for complex AI tasks. This raises two central questions about agent-designed methods relative…

cs.PF2026

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…

cs.LG2026

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…

cs.CL2026

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…

cs.LG2026

GraDE: A Graph Diffusion Estimator for Frequent Subgraph Discovery in Neural Architectures

Yikang Yang, Zhengxin Yang, Minghao Luo +5

Finding frequently occurring subgraph patterns or network motifs in neural architectures is crucial for optimizing efficiency, accelerating design, and uncovering structural insigh…

cs.LG2026

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…