×
验证码:
换一张
忘记密码?
记住我
×
统一认证登录
登录
中文版
|
English
上海科技大学知识管理系统
ShanghaiTech University Knowledge Management System
统一认证登录
登录
注册
ALL
ORCID
题名
作者
发表日期
关键词
文献类型
DOI
出处
存缴日期
收录类别
出版者
学习讨论厅
图片搜索
粘贴图片网址
首页
研究单元&专题
作者
文献类型
学科分类
知识图谱
知识整合
学习讨论厅
在结果中检索
研究单元&专题
信息科学与技术学院 [21]
物质科学与技术学院 [1]
数学科学研究所 [1]
更多...
作者
刘思廷 [3]
哈亚军 [2]
石远明 [2]
袁晓军 [2]
姜伟雄 [2]
周勇 [2]
更多...
文献类型
期刊论文 [13]
会议论文 [9]
预印本 [1]
发表日期
2025 [4]
2024 [6]
2023 [3]
2022 [4]
2021 [2]
2018 [1]
更多...
出处
IEEE TRANS... [2]
IEEE TRANS... [2]
PROCEEDING... [2]
2015 IEEE ... [1]
2022 IEEE ... [1]
2024 DESIG... [1]
更多...
语种
英语 [21]
中文 [1]
资助项目
Central Gu... [1]
National K... [1]
National K... [1]
National N... [1]
National N... [1]
National N... [1]
更多...
资助机构
收录类别
EI [20]
SCI [5]
CPCI-S [3]
SCIE [3]
CPCI [1]
PPRN.PPRN [1]
更多...
状态
已发表 [20]
×
知识图谱
KMS
反馈留言
浏览/检索结果:
共23条,第1-10条
帮助
已选(
0
)
清除
条数/页:
5
10
15
20
25
30
35
40
45
50
55
60
65
70
75
80
85
90
95
100
排序方式:
请选择
作者升序
作者降序
期刊影响因子升序
期刊影响因子降序
发表日期升序
发表日期降序
WOS被引频次升序
WOS被引频次降序
提交时间升序
提交时间降序
题名升序
题名降序
Lookup Table Refactoring: Towards Efficient Logarithmic Number System Addition for Large Language Models
会议论文
2025 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE (DATE), Lyon, France, 31 March-2 April 2025
作者:
Xinkuang Geng
;
Siting Liu
;
Hui Wang
;
Jie Han
;
Honglan Jiang
Adobe PDF(663Kb)
|
收藏
|
浏览/下载:17/1
|
提交时间:2025/05/26
Fixed point arithmetic
Integrated circuit design
Number theory
Approximate computing
Integer quantization
Language model
Large language model
Logarithmic number system
Long-tailed distributions
Lookups
Quantisation
Quantization errors
Refactorings
QuantTPM: Efficient Mixed-Precision Quantization Framework for Tractable Probabilistic Models
期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2025, 卷号: PP, 期号: 99
作者:
Shen Zhang
;
Bin Ning
;
Guangyao Yan
;
Xinzhe Liu
;
Weixiong Jiang
Adobe PDF(9186Kb)
|
收藏
|
浏览/下载:92/2
|
提交时间:2025/03/03
Mixed precision - Mixed precision quantization - Probabilistic inference - Probabilistic models - Product networks - Quantisation - Resource efficiencies - Sum product - Sum-product network - Tractable probabilistic model
Pushing the Limit of Post-Training Quantization
期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2025, 卷号: PP, 期号: 99
作者:
Ruihao Gong
;
Xianglong Liu
;
Yuhang Li
;
Yunqiang Fan
;
Xiuying Wei
Adobe PDF(3735Kb)
|
收藏
|
浏览/下载:55/3
|
提交时间:2025/03/29
'current
Block reconstruction
Deep learning
Flatness
Low-costs
Lower precision
Model compression
Neural-networks
Post-training quantization
Quantisation
COMET: Towards Practical W4A4KV4 LLMs Serving
会议论文
INTERNATIONAL CONFERENCE ON ARCHITECTURAL SUPPORT FOR PROGRAMMING LANGUAGES AND OPERATING SYSTEMS - ASPLOS, Rotterdam, Netherlands, March 30, 2025 - April 3, 2025
作者:
Liu, Lian
;
Cheng, Long
;
Ren, Haimeng
;
Xu, Zhaohui
;
Pan, Yudong
Adobe PDF(2187Kb)
|
收藏
|
浏览/下载:34/1
|
提交时间:2025/05/09
Cache memory
Compaction
Computer graphics equipment
Graphics processing unit
Integrated circuit design
Modeling languages
Problem oriented languages
Algorithm
system co
design
Bit weight
Co
designs
Language model
Large language model serving
Large language model quantization
Mixed precision
Modeling quantizations
Quantisation
Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantization
预印本
2024
作者:
Liu, Weihang
;
Zheng, Xue Xian
;
Yu, Jingyi
;
Lou, Xin
收藏
|
浏览/下载:209/0
|
提交时间:2024/12/04
Radiance fields
Content-aware
Quantization
Model complexity
Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection
会议论文
PROCEEDINGS OF THE AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, Vancouver, BC, Canada, February 20, 2024 - February 27, 2024
作者:
Fan, Yunqian
;
Wei, Xiuying
;
Gong, Ruihao
;
Ma, Yuqing
;
Zhang, Xiangguo
Adobe PDF(574Kb)
|
收藏
|
浏览/下载:412/1
|
提交时间:2024/04/26
Autonomous vehicles
Autonomous driving
Detection models
Detection performance
Labeled data
Lane detection
Limited memory
Post-processing
Quantisation
Quantization errors
Specific semantics
Task-Oriented Sensing, Computation, and Communication Integration for Multi-Device Edge AI
期刊论文
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2024, 卷号: 23, 期号: 3, 页码: 2486-2502
作者:
Dingzhu Wen
;
Peixi Liu
;
Guangxu Zhu
;
Yuanming Shi
;
Jie Xu
Adobe PDF(7791Kb)
|
收藏
|
浏览/下载:549/10
|
提交时间:2023/10/07
Sensors
Task analysis
Quantization (signal)
Servers
Artificial intelligence
Computational modeling
Feature extraction
Convex optimization
Job analysis
Artificial intelligent
Communication integration
Computational modelling
Features extraction
Integrated sensing
Low latency
Multi-devices
Task-oriented
QUQ: Quadruplet Uniform Quantization for Efficient Vision Transformer Inference
会议论文
PROCEEDINGS - DESIGN AUTOMATION CONFERENCE, San Francisco, CA, United states, June 23, 2024 - June 27, 2024
作者:
Geng, Xinkuang
;
Liu, Siting
;
Liu, Leibo
;
Han, Jie
;
Jiang, Honglan
Adobe PDF(860Kb)
|
收藏
|
浏览/下载:212/2
|
提交时间:2024/12/27
Signal encoding
Bit-Width
Data ranges
Inference process
Memory overheads
Performance
Quantisation
Quantized models
Scale Factor
Subrange
Uniform quantization
Compact Powers-of-Two: An Efficient Non-Uniform Quantization for Deep Neural Networks
会议论文
2024 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE), Valencia, Spain, 25-27 March 2024
作者:
Xinkuang Geng
;
Siting Liu
;
Jianfei Jiang
;
Kai Jiang
;
Honglan Jiang
Adobe PDF(407Kb)
|
收藏
|
浏览/下载:287/2
|
提交时间:2024/06/17
Computational efficiency
Data privacy
Table lookup
Bit-Width
Conventional methods
Data characteristics
Hardware implementations
High-accuracy
Intrinsic data
Non-uniform quantization
Power-of-two
Quantisation
Quantization schemes
Drift: Leveraging Distribution-based Dynamic Precision Quantization for Efficient Deep Neural Network Acceleration
会议论文
PROCEEDINGS - DESIGN AUTOMATION CONFERENCE, San Francisco, CA, United states, June 23, 2024 - June 27, 2024
作者:
Liu, Lian
;
Xu, Zhaohui
;
He, Yintao
;
Wang, Ying
;
Li, Huawei
Adobe PDF(809Kb)
|
收藏
|
浏览/下载:145/3
|
提交时间:2024/12/27
Neural network models
Computational costs
Dynamic precision
Evaluation results
Language model
Model size
Neural network model
Neural-networks
Online scheduling
Quantisation
Quantization algorithms
首页
上一页
1
2
3
下一页
末页