3 papers
cs.CL2025
ILRe: Intermediate Layer Retrieval for Context Compression in Causal Language Models
Manlai Liang, Mandi Liu, Jiangzhou Ji +4
Large Language Models (LLMs) have demonstrated success across many benchmarks. However, they still exhibit limitations in long-context scenarios, primarily due to their short effec…
cs.LG2025
LagKV: Lag-Relative Information of the KV Cache Tells Which Tokens Are Important
Manlai Liang, JiaMing Zhang, Xiong Li +1
The increasing size of the Key-Value (KV) cache during the Large Language Models long-context inference is the main obstacle for its balance between the deployment cost and task ac…
cs.CL2025
Lag-Relative Sparse Attention In Long Context Training
Manlai Liang, Wanyi Huang, Mandi Liu +2
Large Language Models (LLMs) have made significant strides in natural language processing and generation, yet their ability to handle long-context input remains constrained by the…