Author

Jae-Joon Kim

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

PReCache: Efficient KV Cache Sharing for Multi-LoRA Agents via Low-Rank Precomputation and Neutral Reconstruction

PReCache is presented, a training-free KV cache sharing framework with two designs, namely PreLRShared and ReBaseShared, that share the base cache computed using the pretrained weights and precompute a compact agent-specific low-rank (LR) cache.

Hyesung Jeon, Hyeongju Ha, Jae-Joon Kim · 0 citations

#machine learning Preprint Sep 2026

WaveFront Decoding: Parallelized Self-Speculative Decoding for Looped Language Models

Looped language models repeatedly apply a weight-shared block to increase effective depth without increasing parameter count, but the resulting T sequential recurrent-block calls per generated token substantially increase decoding latency. To address the issue, we introduce Wavefront Decoding (WFD), a training-free sel...

Hyeongju Ha, Jae-Joon Kim · 1 citation