检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

515 篇 会议
435 篇 期刊文献
5 册 图书

馆藏范围

955 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

659 篇 工学
- 438 篇 计算机科学与技术...
- 359 篇 软件工程
- 122 篇 控制科学与工程
- 101 篇 生物工程
- 84 篇 信息与通信工程
- 81 篇 电子科学与技术（可...
- 64 篇 电气工程
- 50 篇 生物医学工程（可授...
- 42 篇 动力工程及工程热...
- 40 篇 机械工程
- 35 篇 光学工程
- 28 篇 仪器科学与技术
- 28 篇 化学工程与技术
- 24 篇 建筑学
- 23 篇 材料科学与工程（可...
- 22 篇 安全科学与工程
429 篇 理学
- 234 篇 数学
- 116 篇 生物学
- 96 篇 物理学
- 85 篇 统计学（可授理学、...
- 58 篇 系统科学
- 29 篇 化学
131 篇 管理学
- 77 篇 管理科学与工程(可...
- 57 篇 图书情报与档案管...
- 49 篇 工商管理
43 篇 医学
- 40 篇 临床医学
- 33 篇 基础医学(可授医学...
- 23 篇 药学(可授医学、理...
33 篇 法学
- 29 篇 社会学
20 篇 经济学
- 20 篇 应用经济学
12 篇 教育学
12 篇 农学
3 篇 军事学
2 篇 文学
1 篇 艺术学

主题

22 篇 reinforcement le...
13 篇 deep neural netw...
13 篇 machine learning
12 篇 data mining
12 篇 hardware
11 篇 deep learning
11 篇 predictive model...
11 篇 forecasting
10 篇 computational mo...
10 篇 visualization
9 篇 semantics
9 篇 autonomous vehic...
9 篇 stochastic syste...
9 篇 training
8 篇 computer science
8 篇 task analysis
8 篇 algorithms
8 篇 convex optimizat...
8 篇 data models
7 篇 embedded systems

机构

29 篇 department of el...
24 篇 department of co...
17 篇 department of st...
17 篇 department of el...
16 篇 department of el...
16 篇 department of el...
15 篇 computer science...
14 篇 department of co...
13 篇 department of el...
10 篇 department of co...
9 篇 computer science...
9 篇 uc berkeley depa...
9 篇 department of co...
8 篇 center for embed...
8 篇 department of co...
8 篇 uc berkeley depa...
8 篇 department of el...
8 篇 department of el...
8 篇 openai
7 篇 department of el...

作者

21 篇 abbeel pieter
14 篇 jordan michael i...
13 篇 levine sergey
11 篇 rosing tajana
11 篇 wainwright marti...
10 篇 belkin mikhail
10 篇 mcauley julian
9 篇 yu bin
9 篇 vahid frank
8 篇 chen xi
7 篇 michael i. jorda...
7 篇 shonle macneil
7 篇 sadigh dorsa
7 篇 pedarsani ramtin
7 篇 tajana rosing
6 篇 darrell trevor
6 篇 kastner ryan
6 篇 gupta rajesh
6 篇 waller laura
6 篇 yin ming

语言

893 篇 英文
57 篇 其他
5 篇 中文

检索条件"机构=Computer Science and Engineering Uc"

共 955 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

FUTGA: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation 3

FUTGA: Towards Fine-grained Music Understanding through Temp...

引用

3rd Workshop on NLP for Music and Audio, NLP4MusA 2024, in conjunction with ISMIR 2024

作者： Wu, Junda Novack, Zachary Namburi, Amit Dai, Jiaheng Dong, Hao-Wen Xie, Zhouhang Chen, Carol McAuley, Julian Computer Science and Engineering UC San Diego United States Computer Science Department UC Los Angeles United States

We propose FUTGA, a model equipped with fined-grained music understanding capabilities through learning from generative augmentation with temporal compositions. We leverage existing music caption datasets and large language models (LLMs) to synthesize fine-grained music captions with structural descriptions and time boundaries for full-length songs. Augmented by the proposed synthetic dataset, FUTGA is enabled to identify the music’s temporal changes at key transition points and their musical functions, as well as generate detailed descriptions for each music segment. We further introduce a full-length music caption dataset generated by FUTGA, as the augmentation of the MusicCaps and the Song Describer datasets. The experiments demonstrate the better quality of the generated captions, which capture the time boundaries of long-form music. Generated temporal-aware music descriptions are illustrated in our demonstration https://***/***/. © 2024 NLP4MusA. All Rights Reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

FUTGA-MIR: Enhancing Fine-grained and Temporally-aware Music Understanding with Music Information Retrieval

FUTGA-MIR: Enhancing Fine-grained and Temporally-aware Music...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wu, Junda Novack, Zachary Namburi, Amit Dong, Hao-Wen Chen, Carol Dai, Jiaheng McAuley, Julian Computer Science and Engineering UC San Diego United States Computer Science Department UC Los Angeles United States

ISBN: (纸本)9798350368741

Recent music large language models (music LLMs) have shown great potential in music understanding through large-scale multimodal pre-training. While some existing music LLMs have been augmented with temporally-aware music captions, music information retrieval (MIR) features conventionally do not exist in music caption datasets, thus neglected by music-LLMs. To bridge the gap between recent music LLMs and conventional music information retrieval tasks, we propose FUTGA-MIR (Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation with Music Information Retrieval) to enhance the existing music LLMs by augmenting them with MIR features and aligning with human feedback. We calibrate the original positional distribution of music clips in the created pre-training synthetic music captions, conditioned on MIR features. The redistributed synthetic dataset better respects realistic MIR distributions of music and is tightly aligned with realistic music captions as well. In addition, We incorporate human-annotated music captions and MIR features from the Harmonixset dataset for an additional fine-tuning step, which addresses sim-to-real domain gaps and improves performance on realistic music tracks. We further evaluate FUTGA-MIR on several downstream tasks, including music classification, retrieval, and generation, and demonstrate the versatile capacities of FUTGA-MIR and better generation quality compared with previous music captioning models. Generated temporal-aware music descriptions are illustrated in our demonstration https://***/***/. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CoLLAP: Contrastive Long-form Language-Audio Pretraining with Musical Temporal Structure Augmentation

CoLLAP: Contrastive Long-form Language-Audio Pretraining wit...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wu, Junda Li, Warren Novack, Zachary Namburi, Amit Chen, Carol McAuley, Julian Computer Science and Engineering UC San Diego La Jolla United States Computer Science Department UC Los Angeles Los Angeles United States

ISBN: (纸本)9798350368741

Modeling temporal characteristics plays a significant role in the representation learning of audio waveform. We propose Contrastive Long-form Language-Audio Pretraining (CoLLAP) to significantly extend the perception window for both the input audio (up to 5 minutes) and the language descriptions (exceeding 250 words), while enabling contrastive learning across modalities and temporal dynamics. Leveraging recent Music-LLMs to generate long-form music captions for full-length songs, augmented with musical temporal structures, we collect 51.3K audio-text pairs derived from the large-scale AudioSet training dataset, where the average audio length reaches 288 seconds. We propose a novel contrastive learning architecture that fuses language representations with structured audio representations by segmenting each song into clips and extracting their embeddings. With an attention mechanism, we capture multimodal temporal correlations, allowing the model to automatically weigh and enhance the final fusion score for improved contrastive alignment. Finally, we develop two variants of the CoLLAP model with different types of backbone language models. Through comprehensive experiments on multiple long-form music-text retrieval datasets, we demonstrate consistent performance improvement in retrieval accuracy compared with baselines. We also show the pretrained CoLLAP models can be transferred to various music information retrieval tasks, with heterogeneous long-form multimodal contexts. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

(Invited Paper) White-box logic obfuscation: A Transparent Solution to Hardware Piracy and Reverse engineering 30

(Invited Paper) White-box logic obfuscation: A Transparent S...

引用

30th Asia and South Pacific Design Automation Conference, ASP-DAC 2025

作者： Li, Leon Orailoglu, Alex Department of Computer Science and Engineering Uc San Diego La Jolla CA United States

ISBN: (纸本)9798400706356

Reverse engineering the functional specification from a netlist is a challenging task that enables IP piracy and tampering. Traditional logic locking techniques, which depend on external activation with secrets stored in tamper-proof locations to thwart reverse engineering, have repeatedly been compromised by key recovery attacks. Their vulnerability highlights the flawed assumption of relying on tamper-proof secrets for building hardware security solutions, especially when activated devices are deployed in open environments where they are exposed to attackers for functional queries and probing. This paper presents white-box logic obfuscation (WBLO) as a novel solution to safeguard control logic from functional reverse engineering, even when attackers have full visibility of the operational netlist. WBLO eliminates the need for post-manufacturing activation and reliance on tamper-proof key storage by securing the design with keys that are autonomously updated internally through the legitimate sequential execution of the device. The proposed approach invalidates functional analysis under arbitrary probing and combinational queries. We examine the implementation challenges inherent in the WBLO process and identify critical design considerations that enhance security and efficiency. Building on these insights, we suggest a prioritization for various design transformation and synthesis rules that achieve robust security in the white-box attack model while minimizing implementation overheads. © 2025 Copyright held by the owner/author(s).

关键词： Reverse engineering

来源：评论

学校读者我要写书评

暂无评论

Does the "most sinfully decadent cake ever" taste good? Answering Yes/No Questions from Figurative Contexts

Does the "most sinfully decadent cake ever" taste good? Answ...

引用

2023 International Conference Recent Advances in Natural Language Processing: Large Language Models for Natural Language Processing, RANLP 2023

作者： Rakshit, Geetanjali Flanigan, Jeffrey Computer Science and Engineering Department UC Santa Cruz United States

ISBN: (纸本)9789544520922

Figurative language is commonplace in natural language, and while making communication memorable and creative, can be difficult to understand. In this work, we investigate the robustness of Question Answering (QA) models on figurative text. Yes/no questions, in particular, are a useful probe of figurative language understanding capabilities of large language models. We propose FigurativeQA, a set of 1000 yes/no questions with figurative and nonfigurative contexts, extracted from the domains of restaurant and product reviews. We show that state-of-the-art BERT-based QA models exhibit an average performance drop of up to 15% points when answering questions from figurative contexts, as compared to non-figurative ones. While models like GPT-3 and ChatGPT are better at handling figurative texts, we show that further performance gains can be achieved by automatically simplifying the figurative contexts into their non-figurative (literal) counterparts. We find that the best overall model is ChatGPT with chain-of-thought prompting to generate non-figurative contexts. Our work provides a promising direction for building more robust QA models with figurative language understanding capabilities. © 2023 Incoma Ltd. All rights reserved.

关键词： Computational methods

来源：评论

学校读者我要写书评

暂无评论

Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation 41

Coprocessor Actor Critic: A Model-Based Reinforcement Learni...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Pan, Michelle Schrum, Mariah Myers, Vivek Bıyık, Erdem Dragan, Anca Department of Electrical Engineering and Computer Sciences UC Berkeley United States Department of Computer Science University of Southern California United States

Adaptive brain stimulation can treat neurological conditions such as Parkinson's disease and post-stroke motor deficits by influencing abnormal neural activity. Because of patient heterogeneity, each patient requires a unique stimulation policy to achieve optimal neural responses. Model-free reinforcement learning (MFRL) holds promise in learning effective policies for a variety of similar control tasks, but is limited in domains like brain stimulation by a need for numerous costly environment interactions. In this work we introduce Coprocessor Actor Critic, a novel, model-based reinforcement learning (MBRL) approach for learning neural coprocessor policies for brain stimulation. Our key insight is that coprocessor policy learning is a combination of learning how to act optimally in the world and learning how to induce optimal actions in the world through stimulation of an injured brain. We show that our approach overcomes the limitations of traditional MFRL methods in terms of sample efficiency and task success and outperforms baseline MBRL approaches in a neurologically realistic model of an injured brain. Copyright 2024 by the author(s)

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

HDXpose: Harnessing Hyperdimensional Computing’s Explainability for Adversarial Attacks 24

HDXpose: Harnessing Hyperdimensional Computing’s Explainabi...

引用

43rd International Conference on computer-Aided Design, ICCAD 2024

作者： Asgarinejad, Fatemeh Pozina, Flavio Gungor, Onat Rosing, Tajana Aksanli, Baris Department of Computer Science and Engineering UC San Diego La Jolla CA92093 United States Department of Electrical and Computer Engineering SDSU CA92182 United States

ISBN: (纸本)9798400710773

Hyperdimensional Computing (HDC), a promising alternative to address the limitations of edge devices, is not exempt from the security challenges confronted by machine learning algorithms, in particular, adversarial attacks. The limited body of research exploring the security implications of HDC overlooks its inherent algorithm. In this paper, we propose a novel and effective adversarial attack technique targeting HDC. Our approach analyzes and prioritizes the impact of input features as well as encoded elements on decision boundaries and perturbs the input towards incorrect decisions in a guided manner. We evaluate our method on different datasets and attack models (i.e., untargeted/targeted, white-box/gray-box). Experimental results indicate that our proposed design, HDXpose, significantly outperforms the state-of-the-art attack techniques by achieving higher success rate with smaller distortion and execution time, rendering its efficacy for real-time attack generation. © 2024 Copyright is held by the owner/author(s).

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Mean-field Chaos Diffusion Models 41

Mean-field Chaos Diffusion Models

引用

41st International Conference on Machine Learning, ICML 2024

作者： Park, Sungwoo Kim, Dongjun Alaa, Ahmed M. Department of Electrical Engineering and Computer Sciences UC Berkeley United States Department of Computer Science Stanford United States UCSF United States

In this paper, we introduce a new class of score-based generative models (SGMs) designed to handle high-cardinality data distributions by leveraging concepts from mean-field theory. We present mean-field chaos diffusion models (MF-CDMs), which address the curse of dimensionality inherent in high-cardinality data by utilizing the propagation of chaos property of interacting particles. By treating high-cardinality data as a large stochastic system of interacting particles, we develop a novel score-matching method for infinite-dimensional chaotic particle systems and propose an approximation scheme that employs a subdivision strategy for efficient training. Our theoretical and empirical results demonstrate the scalability and effectiveness of MF-CDMs for managing large high-cardinality data structures, such as 3D point clouds. Copyright 2024 by the author(s)

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

FUTGA-MIR: Enhancing Fine-grained and Temporally-aware Music Understanding with Music Information Retrieval

FUTGA-MIR: Enhancing Fine-grained and Temporally-aware Music...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Junda Wu Zachary Novack Amit Namburi Hao-Wen Dong Carol Chen Jiaheng Dai Julian McAuley Computer Science and Engineering UC San Diego Computer Science Department UC Los Angeles

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

关键词： Large language models Signal processing Acoustics Music information retrieval Speech processing Synthetic data

来源：评论

学校读者我要写书评

暂无评论

PromptHive: Bringing Subject Matter Experts Back to the Forefront with Collaborative Prompt engineering for Educational Content Creation 25

PromptHive: Bringing Subject Matter Experts Back to the Fore...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Reza, Mohi Anastasopoulos, Ioannis Bhandari, Shreya Pardos, Zachary A. Computer Science University of Toronto Toronto ON Canada Berkeley School of Education UC Berkeley Berkeley CA United States Electrical Engineering & Computer Science UC Berkeley Berkeley CA United States

ISBN: (纸本)9798400713941

Involving subject matter experts in prompt engineering can guide LLM outputs toward more helpful, accurate, and tailored content that meets the diverse needs of different domains. However, iterating towards effective prompts can be challenging without adequate interface support for systematic experimentation within specific task contexts. In this work, we introduce PromptHive, a collaborative interface for prompt authoring designed to better connect domain knowledge with prompt engineering through features that encourage rapid iteration on prompt variations. We conducted an evaluation study with ten subject matter experts in math and validated our design through two collaborative prompt writing sessions and a learning gain study with 358 learners. Our results elucidate the prompt iteration process and validate the tool's usability, enabling non-AI experts to craft prompts that generate content comparable to human-authored materials while reducing perceived cognitive load by half and shortening the authoring process from several months to just a few hours. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Content Generation Human-Centered AI LLMs Math Education Prompt engineering

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共96页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：