Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
TideKV: Delayed KV Eviction via Layer-Wise Chunked Prefill for Memory-Efficient Long-Context LLM Inference
Yu Wang, Zhu Wang, Ning Hu +4
Long-context large language model (LLM) inference is important for modern intelligent applications but remains constrained by peak memory during prompt prefill. Existing KV cache c…
cs.LG2026
FSTC-Encoder: Feature--Spatial--Temporal Correlation Learning for Generalizable RF Sensing
Jing Wang, Zhu Wang, Changlong Cheng +2
Heterogeneous RF sensing differs substantially in feature structure, spatial layout, and temporal scale, making existing models difficult to reuse across devices, environments, and…