15 papers
MentorPulse: Refreshing Cross-Model Latent Guidance for Long-Form Generation
Ziwu Liu, Guozhong Li, Chen Qiu +2
Cross-model latent guidance lets a frozen large mentor encode an input once and a frozen small student generate from the resulting signal. Existing methods keep this signal fixed,…
KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models
Chen Qiu, Ziwu Liu, Chao Fei +2
KV-cache compression reduces long-context memory, but aggregate task scores reveal neither which correct executions fail nor why. We present KVDiagnosis, a diagnostic dataset and b…
EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision
Chao Fei, Qingyi Si, Kaihua Liang +3
Many methods for automated multi-agent system design optimize prompts and topologies during an initial design stage and then deploy the resulting system unchanged on subsequent sam…
ART: Attention Run-time Termination for Efficient Large Language Model Decoding
Chen Qiu, Guozhong Li, Cristian McGee +2
Long-context decoding in Large Language Models (LLMs) is constrained by the cost of accessing and processing the Key-Value (KV) cache. Despite evidence that attention outputs depen…
PolyKV: Heterogeneous Retention and Allocation for KV Cache Compression
Chao Fei, Panos Kalnis
KV cache compression is essential for reducing the memory cost of long-context large language model inference. Existing approaches, however, typically apply a single compression po…
Can Deep Neural Networks Improve Compression of Very Large Scientific Data?
Muhannad Alhumaidi, Guozhong Li, Spiros Skiadopoulos +1
Error-bounded lossy compression is a fundamental technique for managing the rapidly growing volumes of scientific data produced by modern simulations and observational instruments.…