3 papers
cs.CL2026
ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing
Yongqi An, Chang Lu, Kuan Zhu +5
Large language models (LLMs) face growing challenges in efficient generative inference due to the increasing memory demands of Key-Value (KV) caches, especially for long sequences.…
cs.CL2025
Improving Generalization in LLM Structured Pruning via Function-Aware Neuron Grouping
Tao Yu, Yongqi An, Kuan Zhu +3
Large Language Models (LLMs) demonstrate impressive performance across natural language tasks but incur substantial computational and storage costs due to their scale. Post-trainin…
cs.LG2025
Scaling Linear Attention with Sparse State Expansion
Yuqi Pan, Yongqi An, Zheng Li +6
The Transformer architecture, despite its widespread success, struggles with long-context scenarios due to quadratic computation and linear memory growth. While various linear atte…