3 papers
cs.CL2026
Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis
Qingyue Yang, Jie Wang, Xing Li +6
Attention patterns play a crucial role in both training and inference of large language models (LLMs). Prior works have identified individual patterns such as retrieval heads, sink…
cs.CL2025
AttentionPredictor: Temporal Patterns Matter for KV Cache Compression
Qingyue Yang, Jie Wang, Xing Li +8
With the development of large language models (LLMs), efficient inference through Key-Value (KV) cache compression has attracted considerable attention, especially for long-context…
cs.LG2024
MILP-StuDio: MILP Instance Generation via Block Structure Decomposition
Haoyang Liu, Jie Wang, Wanbo Zhang +6
Mixed-integer linear programming (MILP) is one of the most popular mathematical formulations with numerous applications. In practice, improving the performance of MILP solvers ofte…