4 papers
CoreMem: Riemannian Retrieval and Fisher-Guided Distillation for Long-Term Memory in Dialogue Agents
Jiaqi Chen, Yongqin Zeng, Shaoshen Chen +4
Personalized dialogue agents require continuous long-term memory to maintain coherent interactions across multiple sessions. However, deploying these capabilities on consumer-grade…
SemantiCache: Efficient KV Cache Compression via Semantic Chunking and Clustered Merging
Shunlong Wu, Hai Lin, Shaoshen Chen +5
Existing KV cache compression methods generally operate on discrete tokens or non-semantic chunks. However, such approaches often lead to semantic fragmentation, where linguistical…
AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees
Yangning Li, Shaoshen Chen, Yinghui Li +5
The quadratic complexity of self-attention constrains Large Language Models (LLMs) in processing long contexts, a capability essential for many advanced applications. Context compr…
DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens
Shaoshen Chen, Yangning Li, Zishan Xu +4
Large Language Models (LLMs) face computational inefficiencies and redundant processing when handling long context inputs, prompting a focus on compression techniques. While existi…