1 citations · 1 across the 3 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models
Renjie Xie, Juncheng Yang, Aoting Hu +4
Long-context inference retains a growing key--value (KV) cache during decoding, which consumes substantial GPU memory and can reduce generation throughput. This bottleneck remains…
cs.AI2026
HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory
Chengda Lu, Xiaoyu Fan, Wei Xu
While Large Language Models (LLMs) achieve strong performance across diverse tasks, their inference dynamics remain poorly understood because of the limited resolution of existing…