paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

JC

Jungwook Choi

ICML 2026×4HPCA 2026效率与系统推理长上下文与架构

新星分资深

30

一作贡献0

核心/参与20

方向广度9

合作网络9

0 一作 · 5 篇 · ICML 2026 / HPCA 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。

2026 顶会论文

5

作者位次 #22/22HPCA 2026Oral· High-Performance Computer Architecture

PIMphony: Overcoming Bandwidth and Capacity Inefficiency in PIM-Based Long-Context LLM Inference System

Hyucksung Kwon · Kyungmo Koo · Janghyeon Kim · Woongkyu Lee · Minjae Lee · Gyeonggeun Jung · Hyungdeok Lee · Yousub Jung · Jaehan Park · Yosub Song · Byeongsu Yang · Haerang Choi · Guhyun Kim · Jongsoon Won · Woojae Shin · Changhyun Kim · Gyeongcheol Shin · Yongkee Kwon · Ilkon Kim · Euicheol Lim · John Kim · Jungwook Choi

效率与系统长上下文与架构OpenReview

作者位次 #7/7ICML 2026Oral

ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training

Janghwan Lee · Sihwa Lee · Jinseok Kim · Yongjik Kim · Jieun Lim · Jinwook Oh · Jungwook Choi

推理效率与系统OpenReview

作者位次 #3/4ICML 2026Poster

LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs

Jung Hyun Lee · June Yong Yang · Jungwook Choi · Eunho Yang

效率与系统OpenReview

作者位次 #4/4ICML 2026Poster· Deep Learning / Large Language Models

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

Janghyeon Kim · Minsoo Kim · Kyuhong Shim · Jungwook Choi

效率与系统推理OpenReview

作者位次 #5/6ICML 2026Spotlight· Deep Learning / Large Language Models

STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control

Priyansh Bhatnagar · Ashkan Moradifirouzabadi · Se-Hyun Yang · SeungJae Lee · Jungwook Choi · Mingu Kang

效率与系统OpenReview

常见合作者

JKJanghyeon Kim×2 HKHyucksung Kwon KKKyungmo Koo WLWoongkyu Lee MLMinjae Lee GJGyeonggeun Jung HLHyungdeok Lee YJYousub Jung JPJaehan Park YSYosub Song BYByeongsu Yang HCHaerang Choi