5 papers
SDGF: Fusing Static and Multi-Scale Dynamic Correlations for Multivariate Time Series Forecasting
Shaoxun Wang, Xingjun Zhang, Qianyang Li +2
Accurate multivariate time series forecasting hinges on inter-series correlations, which often evolve in complex ways across different temporal scales. Existing methods are limited…
SpecPV: Improving Self-Speculative Decoding for Long-Context Generation via Partial Verification
Zhendong Tan, Xingjun Zhang, Chaoyi Hu +2
Growing demands from tasks like code generation, deep reasoning, and long-document understanding have made long-context generation a crucial capability for large language models (L…
D-CTNet: A Dual-Branch Channel-Temporal Forecasting Network with Frequency-Domain Correction
Shaoxun Wang, Xingjun Zhang, Kun Xia +3
Accurate Multivariate Time Series (MTS) forecasting is crucial for collaborative design of complex systems, Digital Twin building, and maintenance ahead of time. However, the colla…
Adaptive Rectification Sampling for Test-Time Compute Scaling
Zhendong Tan, Xingjun Zhang, Chaoyi Hu +2
The newly released OpenAI-o1 and DeepSeek-R1 have demonstrated that test-time scaling can significantly improve model performance, especially in complex tasks such as logical reaso…
NQKV: A KV Cache Quantization Scheme Based on Normal Distribution Characteristics
Zhihang Cai, Xingjun Zhang, Zhendong Tan +1
Large Language Models (LLMs) have demonstrated remarkable proficiency across a wide range of tasks. However, LLMs often require larger batch sizes to enhance throughput or longer c…