paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

FF

Fangcheng Fu

ICML 2026×7效率与系统可解释性强化学习与后训练长上下文与架构多模态

新星分贡献者

70

一作贡献0

核心/参与44

方向广度10

合作网络12

0 一作 · 7 篇 · ICML 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

7

作者位次 #6/7ICML 2026Poster· Deep Learning / Large Language Models

DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning

Yujie Wang · Siwei Chen · Longzan Luo · Xinyi Liu · Xupeng Miao · Fangcheng Fu · Bin Cui

强化学习与后训练OpenReview

作者位次 #3/4ICML 2026Poster· Deep Learning / Attention Mechanisms

SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling

Xiaodong Ji · Hailin Zhang · Fangcheng Fu · Bin Cui

可解释性效率与系统长上下文与架构OpenReview

作者位次 #2/5ICML 2026Poster· Optimization / Large Scale, Parallel and Distributed

OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration

Youhe Jiang · Fangcheng Fu · Taiyi Wang · Guoliang He · Eiko Yoneki

作者位次 #3/10ICML 2026Poster· Deep Learning / Large Language Models

Scheduling LLM Inference with Uncertainty-Aware Output Length Predictions

Haoyu Zheng · Yongqiang Zhang · Fangcheng Fu · Xiaokai Zhou · Hao Luo · Hongchao Zhu · Yuanyuan Zhu · Hao Wang · Xiao Yan · Jiawei Jiang

效率与系统OpenReview

作者位次 #2/10ICML 2026Poster· Deep Learning / Attention Mechanisms

EchoAttention: Exploiting Token-Pair Redundancy and Frame-Block Similarity for Efficient Video Generation

Yifei Xia · Fangcheng Fu · Hao Yuan · Suhan Ling · Xupeng Miao · Huixia Li · Yuxi Ren · Xin Xia · Xuefeng Xiao · Bin Cui

可解释性多模态效率与系统OpenReview

作者位次 #8/9ICML 2026Poster· Optimization / Large Scale, Parallel and Distributed

HexGen-3: A Fully Disaggregated LLM Serving Framework with Fine-Grained Heterogeneous Resource Autoscaling

Youhe Jiang · Wenshuang Li · You Peng · Jintao Zhang · Ran Yan · Jianfei Chen · Xu Han · Fangcheng Fu · Binhang Yuan

作者位次 #7/7ICML 2026Poster· Optimization / Large Scale, Parallel and Distributed

Efficient Multi-round LLM Inference over Disaggregated Serving

Wenhao He · Youhe Jiang · Penghao Zhao · Quanqing Xu · Eiko Yoneki · Bin Cui · Fangcheng Fu

效率与系统OpenReview

常见合作者

BCBin Cui×4 YJYouhe Jiang×3 XMXupeng Miao×2 EYEiko Yoneki×2 YWYujie Wang SCSiwei Chen LLLongzan Luo XLXinyi Liu XJXiaodong Ji HZHailin Zhang TWTaiyi Wang GHGuoliang He