paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
JF

Jun Fang

ACL 2026×2ICML 2026×2KDD 2026×2智能体与工具推理检索与知识效率与系统对齐与偏好
新星分贡献者
73
一作贡献0
核心/参与45
方向广度16
合作网络12
0 一作 · 6 篇 · ACL 2026 / ICML 2026 / KDD 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

6
作者位次 #2/4ICML 2026Poster· Deep Learning / Large Language Models

Agent-Omit: Adaptive Context Omission for Efficient LLM Agents

Yansong Ning · Jun Fang · Naiqiang Tan · Hao Liu

智能体与工具效率与系统OpenReview
作者位次 #7/9ACL 2026Findings· Findings of ACL

Dual-Reasoner: Bridging Interleaved Atomicity and Streaming Latency via Thinking-while-Talking

Yangzhuo Li · Shengpeng Ji · Yifu Chen · Tianle Liang · Haoyu Yang · Junboli · Jun Fang · Lin Li · Qingyang Hong

摘要

Integrating explicit Chain-of-Thought (CoT) into end-to-end spoken dialogue models enhances intelligence but incurs prohibitive latency. While the “Thinking-while-Talking” paradigm alleviates this delay, it fundamentally compromises block atomicity, severing the logical connection between interle...

推理多模态对齐与偏好OpenReview 项目页
作者位次 #12/15ACL 2026Findings· Findings of ACL

D -Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents

Hongze Mi · Yibo Feng · Wenjie Lu · Yuqi Wang · Jinyuan Li · Song Cao · He Cui · Tengfei Tian · Xuelin Zhang · Haotian Luo · Di Sun · Jun Fang · Hua Chai · Naiqiang Tan · Gang Pan

摘要

Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction. Despite rapid advancements, current approaches are hindered by several critical challenges: data bottleneck in end-to-end training, high cost of delayed error detection, and risk of...

智能体与工具对齐与偏好可解释性OpenReview 项目页

常见合作者