大模型推理能力 - arXivDaily 专题

2412.03980 2024-12-06 eess.AS 50%

Comprehensive Audio Query Handling System with Integrated Expert Models and Contextual Understanding

Vakada Naveen, Arvind Krishna Sridhar, Yinyi Guo, Erik Visser

专题命中推理评测：reasoning(abstract)

2309.11268 2024-12-05 cs.CV 50%

StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding

Renqiu Xia, Haoyang Peng, Hancheng Ye, Mingsheng Li, Xiangchao Yan, Peng Ye, Botian Shi, Yu Qiao, Junchi Yan, Bo Zhang

机构 * Shanghai Jiao Tong University（上海交通大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Fudan University（复旦大学）

专题命中推理评测：reasoning(abstract)

Comments All codes, models and SimChart9K data are available for downloading at: https://github.com/UniModal4Reasoning/ChartVLM and https://github.com/UniModal4Reasoning/SimChart9K

2412.01934 2024-12-04 cs.CY 50%

A Shared Standard for Valid Measurement of Generative AI Systems' Capabilities, Risks, and Impacts

Alexandra Chouldechova, Chad Atalla, Solon Barocas, A. Feder Cooper, Emily Corvi, P. Alex Dow, Jean Garcia-Gathright, Nicholas Pangakis, Stefanie Reed, Emily Sheng, Dan Vann, Matthew Vogel, Hannah Washington, Hanna Wallach

专题命中推理评测：reasoning(abstract)

Comments NeurIPS 2024 Workshop on Statistical Foundations of LLMs and Foundation Models (SFLLM)

2412.00832 2024-12-03 cs.CV 50%

EventGPT: Event Stream Understanding with Multimodal Large Language Models

Shaoyu Liu, Jianing Li, Guanghui Zhao, Yunjian Zhang, Xin Meng, Fei Richard Yu, Xiangyang Ji, Ming Li

机构 * Xidian University（西安电子科技大学）； Tsinghua University（清华大学）； UCAS（中国科学院大学）； Peking University（北京大学）； Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ)（广东省人工智能与数字经济实验室（深圳））

专题命中推理评测：reasoning(abstract)

2405.04788 2024-12-03 cs.CV 50%

SemiCD-VL: Visual-Language Model Guidance Makes Better Semi-supervised Change Detector

Kaiyu Li, Xiangyong Cao, Yupeng Deng, Jiayi Song, Junmin Liu, Deyu Meng, Zhi Wang

机构 * Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）； Pazhou Laboratory (Huangpu)（琶洲实验室（黄埔））

专题命中推理评测：reasoning(abstract)

Comments 13 pages, 6 figures

2411.17794 2024-11-28 cs.CV 50%

NEMO: Can Multimodal LLMs Identify Attribute-Modified Objects?

Jiaxuan Li, Junwen Mo, MinhDuc Vo, Akihiro Sugimoto, Hideki Nakayama

机构 * The University of Tokyo（东京大学）； National Institute of Informatics（信息学研究科（日本））

专题命中推理评测：reasoning(abstract)

2211.15656 2024-11-28 cs.CV cs.RO 50%

SuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map Generation

Hao Dong, Weihao Gu, Xianjing Zhang, Jintao Xu, Rui Ai, Huimin Lu, Juho Kannala, Xieyuanli Chen

机构 * ETH Zürich（苏黎世联邦理工学院）； NUDT（中国人民解放军国防科技大学）； Aalto University（阿尔托大学）

专题命中推理评测：planning(abstract)

Comments ICRA 2024

2411.16031 2024-11-26 cs.SI cs.MA 50%

Agent-Based Modelling Meets Generative AI in Social Network Simulations

Antonino Ferraro, Antonio Galli, Valerio La Gatta, Marco Postiglione, Gian Marco Orlando, Diego Russo, Giuseppe Riccio, Antonio Romano, Vincenzo Moscato

专题命中推理评测：reasoning(abstract)

Comments Accepted at ASONAM2024

2411.14505 2024-11-25 cs.CV 50%

LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval

Weiheng Lu, Jian Li, An Yu, Ming-Ching Chang, Shengpeng Ji, Min Xia

机构 * Peking University（北京大学）； Tencent Youtu（腾讯优图）； University at Albany（奥尔巴尼大学）； Zhejiang University（浙江大学）

专题命中推理评测：reasoning(abstract)

2411.13697 2024-11-22 cs.CV 50%

Decompose and Leverage Preferences from Expert Models for Improving Trustworthiness of MLLMs

Rui Cao, Yuming Jiang, Michael Schlichtkrull, Andreas Vlachos

专题命中推理评测：reasoning(abstract)

2411.11360 2024-11-19 cs.CV 50%

CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset

Zhiming Wang, Mingze Wang, Sheng Xu, Yanjing Li, Baochang Zhang

机构 * Beihang University（北京航空航天大学）

专题命中推理评测：reasoning(abstract)

2411.04348 2024-11-12 cs.CV cs.RO 50%

UEVAVD: A Dataset for Developing UAV's Eye View Active Object Detection

Xinhua Jiang, Tianpeng Liu, Li Liu, Zhen Liu, Yongxiang Liu

机构 * College of Electronic Science, National University of Defense Technology（国防科技大学电子科学学院）

专题命中推理评测：planning(abstract)

2310.01412 2024-11-12 cs.CV cs.RO 50%

DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model

Zhenhua Xu, Yujia Zhang, Enze Xie, Zhen Zhao, Yong Guo, Kwan-Yee. K. Wong, Zhenguo Li, Hengshuang Zhao

机构 * The University of Hong Kong（香港大学）； Zhejiang University（浙江大学）； University of Sydney（悉尼大学）

专题命中推理评测：reasoning(abstract)

Comments Accepted by RA-L. The project page is available at https://tonyxuqaq.github.io/projects/DriveGPT4/

2406.14515 2024-10-31 cs.CV cs.MM 50%

MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding

Xinyu Fang, Kangrui Mao, Haodong Duan, Xiangyu Zhao, Yining Li, Dahua Lin, Kai Chen

机构 * Zhejiang University（浙江大学）； Shanghai AI Laboratory（上海人工智能实验室）； Shanghai Jiao Tong University（上海交通大学）； The Chinese University of Hong Kong（香港中文大学）； CPII under InnoHK（创新香港计划下属CPII机构）

专题命中推理评测：reasoning(abstract)

Comments Accepted in NeurIPS 2024 Datasets and Benchmarks Track

2308.15483 2024-10-29 cs.NI eess.IV eess.SP 50%

Generative AI for Semantic Communication: Architecture, Challenges, and Outlook

Le Xia, Yao Sun, Chengsi Liang, Lei Zhang, Muhammad Ali Imran, Dusit Niyato

专题命中推理评测：reasoning(abstract)

Comments This magazine article has been accepted for publication by IEEE Wireless Communications

2406.06040 2024-10-28 cs.CV 50%

Vript: A Video Is Worth Thousands of Words

Dongjie Yang, Suyuan Huang, Chengqiang Lu, Xiaodong Han, Haoxin Zhang, Yan Gao, Yao Hu, Hai Zhao

专题命中推理评测：reasoning(abstract)

Comments Accepted by NeurIPS Dataset & Benchmark track

2410.18537 2024-10-25 cs.CV 50%

Beyond Color and Lines: Zero-Shot Style-Specific Image Variations with Coordinated Semantics

Jinghao Hu, Yuhe Zhang, GuoHua Geng, Liuyuxin Yang, JiaRui Yan, Jingtao Cheng, YaDong Zhang, Kang Li

专题命中推理评测：reasoning(abstract)

Comments 13 pages,6 figures

2403.08350 2024-10-24 cs.CV 50%

CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language Model

Cheng Chen, Junchen Zhu, Xu Luo, Hengtao Shen, Lianli Gao, Jingkuan Song

专题命中推理评测：reasoning(abstract)

2408.03650 2024-10-22 cs.MM 50%

Towards Multimodal Emotional Support Conversation Systems

Yuqi Chu, Lizi Liao, Zhiyuan Zhou, Chong-Wah Ngo, Richang Hong

专题命中推理评测：reasoning(abstract)

Comments This work has been submitted to the IEEE for possible publication

2410.09738 2024-10-21 cs.SE 50%

Can Large Language Models Generate Geospatial Code?

Shuyang Hou, Zhangxiao Shen, Jianyuan Liang, Anqi Zhao, Zhipeng Gui, Rui Li, Huayi Wu

专题命中推理评测：reasoning(abstract)

2410.13662 2024-10-18 cs.CV 50%

ActionCOMET: A Zero-shot Approach to Learn Image-specific Commonsense Concepts about Actions

Shailaja Keyur Sampat, Yezhou Yang, Chitta Baral

专题命中推理评测：reasoning(abstract)

Comments 15 pages, 3 figures. arXiv admin note: text overlap with arXiv:2004.10796 by other authors

2410.13651 2024-10-18 cs.CV 50%

Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?

Shailaja Keyur Sampat, Maitreya Patel, Yezhou Yang, Chitta Baral

专题命中推理评测：reasoning(abstract)

Comments 14 pages, 7 figures

2410.13437 2024-10-18 cs.CV 50%

Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation

Changcheng Xiao, Qiong Cao, Yujie Zhong, Xiang Zhang, Tao Wang, Canqun Yang, Long Lan

专题命中推理评测：reasoning(abstract)

2408.02181 2024-10-17 cs.CV 50%

AssemAI: Interpretable Image-Based Anomaly Detection for Manufacturing Pipelines

Renjith Prasad, Chathurangi Shyalika, Ramtin Zand, Fadi El Kalach, Revathy Venkataramanan, Ramy Harik, Amit Sheth

专题命中推理评测：reasoning(abstract)

Comments 8 Pages, 6 Figures, 4 Tables, Predictive Models in Engineering Applications special session (MLPMEA )at International Conference on Machine Learning and Applications (ICMLA) 2024

Journal ref Predictive Models in Engineering Applications special session (MLPMEA) at International Conference on Machine Learning and Applications (ICMLA) 2024

2410.11538 2024-10-16 cs.CV 50%

MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes Benchmark

Bin Shan, Xiang Fei, Wei Shi, An-Lan Wang, Guozhi Tang, Lei Liao, Jingqun Tang, Xiang Bai, Can Huang

专题命中推理评测：reasoning(abstract)

Comments 12 pages, 5 figures, project page: https://github.com/xfey/MCTBench?tab=readme-ov-file

2406.06087 2024-10-15 cs.CV 50%

GAIA: Rethinking Action Quality Assessment for AI-Generated Videos

Zijian Chen, Wei Sun, Yuan Tian, Jun Jia, Zicheng Zhang, Jiarui Wang, Ru Huang, Xiongkuo Min, Guangtao Zhai, Wenjun Zhang

专题命中推理评测：reasoning(abstract)

Comments Accepted by NeurIPS2024 Dataset and Benchmark Track as Spotlight. 33 pages, 15 figures

2410.09503 2024-10-15 eess.AS cs.SD 50%

SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs

Wenxi Chen, Ziyang Ma, Xiquan Li, Xuenan Xu, Yuzhe Liang, Zhisheng Zheng, Kai Yu, Xie Chen

专题命中推理评测：reasoning(abstract)

2410.01844 2024-10-15 cs.SI 50%

Urban Anomalies: A Simulated Human Mobility Dataset with Injected Anomalies

Hossein Amiri, Ruochen Kong, Andreas Zufle

专题命中推理评测：planning(abstract)

Comments This is an accepted paper on https://onspatial.github.io/GeoAnomalies24/

2312.17235 2024-10-11 cs.CV 50%

A Simple LLM Framework for Long-Range Video Question-Answering

Ce Zhang, Taixi Lu, Md Mohaiminul Islam, Ziyang Wang, Shoubin Yu, Mohit Bansal, Gedas Bertasius

专题命中推理评测：reasoning(abstract)

Comments EMNLP 2024 main

2407.15272 2024-10-10 cs.CV 50%

MIBench: Evaluating Multimodal Large Language Models over Multiple Images

Haowei Liu, Xi Zhang, Haiyang Xu, Yaya Shi, Chaoya Jiang, Ming Yan, Ji Zhang, Fei Huang, Chunfeng Yuan, Bing Li, Weiming Hu

专题命中推理评测：reasoning(abstract)

Comments EMNLP 2024

1. 推理评测 10577 篇

Comprehensive Audio Query Handling System with Integrated Expert Models and Contextual Understanding

StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding

A Shared Standard for Valid Measurement of Generative AI Systems' Capabilities, Risks, and Impacts

EventGPT: Event Stream Understanding with Multimodal Large Language Models

SemiCD-VL: Visual-Language Model Guidance Makes Better Semi-supervised Change Detector

NEMO: Can Multimodal LLMs Identify Attribute-Modified Objects?

SuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map Generation

Agent-Based Modelling Meets Generative AI in Social Network Simulations

LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval

Decompose and Leverage Preferences from Expert Models for Improving Trustworthiness of MLLMs

CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset

UEVAVD: A Dataset for Developing UAV's Eye View Active Object Detection

DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model

MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding

Generative AI for Semantic Communication: Architecture, Challenges, and Outlook

Vript: A Video Is Worth Thousands of Words

Beyond Color and Lines: Zero-Shot Style-Specific Image Variations with Coordinated Semantics

CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language Model

Towards Multimodal Emotional Support Conversation Systems

Can Large Language Models Generate Geospatial Code?

ActionCOMET: A Zero-shot Approach to Learn Image-specific Commonsense Concepts about Actions

Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?

Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation

AssemAI: Interpretable Image-Based Anomaly Detection for Manufacturing Pipelines

MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes Benchmark

GAIA: Rethinking Action Quality Assessment for AI-Generated Videos

SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs

Urban Anomalies: A Simulated Human Mobility Dataset with Injected Anomalies

A Simple LLM Framework for Long-Range Video Question-Answering

MIBench: Evaluating Multimodal Large Language Models over Multiple Images