works on

From the 2 of 7 linked papers with an AI index.

most citedLightRot: A Light-Weighted Rotation Scheme and Architecture for Accurate Low-Bit Large Language Model Inference

6 citations · 8 across the 3 of their papers we have counts for

collaborators

7 papers

cs.AR2026

EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding

Sangwoo Ha, Hyunwoo Seo, Yurim Jo +2

On-device deployment of Large Language Models (LLMs) has become essential for personalized edge applications. A primary bottleneck is external memory access (EMA) in feed-forward n…

cs.AR20266 cited

LightRot: A Light-Weighted Rotation Scheme and Architecture for Accurate Low-Bit Large Language Model Inference

Sangjin Kim, Yuseon Choi, Jungjun Oh +2

LightRot introduces a lightweight rotation scheme and a dedicated hardware accelerator that enable energy‑efficient, low‑bit inference for large language models such as LLaMA2‑13B…

cs.AR20262 cited

GyRot: Leveraging Hidden Synergy between Rotation and Fine-grained Group Quantization for Low-bit LLM Inference

Sangjin Kim, Yuseon Choi, Byeongcheol Kim +2

GyRot introduces a co-designed quantization framework and hardware accelerator that combine coarse rotation with fine-grained group quantization, enabling accurate 4-bit inference…

cs.LG2026

ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving

Yuseon Choi, Jingu Lee, Jungjun Oh +5

Mixture-of-Experts (MoE) models have become the dominant architecture for large-scale language models, yet on-premises serving remains fundamentally memory-bound as batching turns…

cs.AR2026

SliceMoE: Bit-Sliced Expert Caching under Miss-Rate Constraints for Efficient MoE Inference

Yuseon Choi, Sangjin Kim, Jungjun Oh +3

MoE models offer efficient scaling through conditional computation, but their large parameter size and expensive expert offloading make on-device deployment challenging. Existing a…

cs.LG2026

FlashMoE: Reducing SSD I/O Bottlenecks via ML-Based Cache Replacement for Mixture-of-Experts Inference on Edge Devices

Byeongju Kim, Jungwan Lee, Donghyeon Han +2

Recently, Mixture-of-Experts (MoE) models have gained attention for efficiently scaling large language models. Although these models are extremely large, their sparse activation en…