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

Sai Qian Zhang

ACL 2026×2ICLR 2026×2CVPR 2026INFOCOM 2026ISCA 2026MICRO 2026效率与系统多模态长上下文与架构强化学习与后训练智能体与工具
新星分资深
34
一作贡献0
核心/参与22
方向广度19
合作网络6
0 一作 · 8 篇 · ACL 2026 / ICLR 2026 / CVPR 2026 / INFOCOM 2026 / ISCA 2026 / MICRO 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

8
作者位次 #3/3ISCA 2026Oral· Computer Architecture

ECHO: Efficient Head-Orientation-Guided Real-Time Sound Spatialization for Virtual Reality

Haiyu Wang · Tianhua Xia · Sai Qian Zhang

效率与系统长上下文与架构OpenReview
作者位次 #4/4ICLR 2026Poster· Deep Learning / Algorithms

WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models

Haiyu Wang · Yutong Wang · Jack Jiang · Sai Qian Zhang

效率与系统多模态OpenReview
作者位次 #4/4MICRO 2026Oral· FPGA / CGRA Accelerators

RAICHU: Rendering Acceleration Integrating CGRA arcHitecture for Unified VR Pipelines

Yanzhou Tang · Haiyu Wang · Cheng Tan · Sai Qian Zhang

长上下文与架构OpenReview
作者位次 #7/7ACL 2026Poster· Natural Language Processing

DREAM - S : Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation

Zining Liu · Yunhai Hu · Tianhua Xia · BO BAO · Eric Sather · Vithursan Thangarasa · Sai Qian Zhang

摘要

Speculative decoding (SD) has proven to be an effective technique for accelerating autoregressive generation in large language models (LLMs), however its application to vision-language models (VLMs) remains relatively unexplored. We propose DREAM-S, a novel SD framework designed specifically for...

多模态效率与系统强化学习与后训练OpenReview 项目页
作者位次 #8/8ACL 2026Findings· Findings of ACL

L ipo A gent: Coordinating Fine-Tuned LLM Agents for Safer Lipid Design

Leshu Li · An Lu · Haiyu Wang · Zhibin Feng · Conghui Duan · Qing Bao · Zongmin Zhao · Sai Qian Zhang

摘要

Lipid nanoparticles (LNPs) are among the most clinically mature platforms for nucleic acid delivery, yet designing lipids that are both effective and biologically safe remains a major bottleneck. In practical screening, toxicity is a decision-level constraint: if a lipid is toxic, its efficiency...

智能体与工具社会与人本推理OpenReview 项目页

常见合作者