6 papers
CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference
Xiaolin Lin, Jingcun Wang, Olga Kondrateva +3
Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on…
ADRD-Bench: A Preliminary LLM Benchmark for Alzheimer's Disease and Related Dementias
Guangxin Zhao, Jiahao Zheng, Malaz Boustani +4
Large language models (LLMs) have shown great potential for healthcare applications. However, existing evaluation benchmarks provide minimal coverage of Alzheimer's Disease and Rel…
MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
Minghao Guo, Qingyue Jiao, Zeru Shi +14
Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many…
FairLRF: Achieving Fairness through Sparse Low Rank Factorization
Yuanbo Guo, Jun Xia, Yiyu Shi
As deep learning (DL) techniques become integral to various applications, ensuring model fairness while maintaining high performance has become increasingly critical, particularly…
Human Resilience in the AI Era -- What Machines Can't Replace
Shaoshan Liu, Anina Schwarzenbach, Yiyu Shi
AI is displacing tasks, mediating high-stakes decisions, and flooding communication with synthetic content, unsettling work, identity, and social trust. We argue that the decisive…
CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation
Xiaolin Lin, Jingcun Wang, Olga Kondrateva +3
Recent advances in large language models (LLMs) have significantly boosted long-context processing. However, the increasing key-value (KV) cache size poses critical challenges to m…