Showing 2026 · cs.LGShow all
3 papers · 2 filters
cs.LG2026
ValueDiff: Value-Geometric KV Cache Eviction for Sink-Suppressed LLMs
Junyoung Park, Jungwook Choi, Mingu Lee
Modern LLMs with QK-normalization, gated attention, learned attention sinks, or logit softcapping exhibit weaker persistent attention sinks, on which existing KV cache eviction met…
cs.LG2026
QUOKA: Query-Oriented KV Selection For Efficient LLM Prefill
Dalton Jones, Junyoung Park, Matthew Morse +3
We present QUOKA: Query-oriented KV selection for efficient attention, a training-free and hardware agnostic sparse attention algorithm for accelerating transformer inference under…
cs.LG2026
Fast Forward: Accelerating LLM Prefill with Predictive FFN Sparsity
Aayush Gautam, Mukul Gagrani, Junyoung Park +3
The prefill stage of large language model (LLM) inference is a key computational bottleneck for long-context workloads. At short-to-moderate context lengths (1K--16K tokens), Feed-…