大模型推理能力 - arXivDaily 专题

2412.14643 2024-12-20 cs.CV 50%

RefHCM: A Unified Model for Referring Perceptions in Human-Centric Scenarios

Jie Huang, Ruibing Hou, Jiahe Zhao, Hong Chang, Shiguang Shan

专题命中复杂问题求解：reasoning(abstract)

Comments 13 pages

2412.11396 2024-12-17 cs.CV 50%

Leveraging Retrieval-Augmented Tags for Large Vision-Language Understanding in Complex Scenes

Antonio Carlos Rivera, Anthony Moore, Steven Robinson

专题命中复杂问题求解：reasoning(abstract)

2412.10720 2024-12-17 cs.CV 50%

Bridging Vision and Language: Modeling Causality and Temporality in Video Narratives

Ji-jun Park, Soo-joon Choi

专题命中复杂问题求解：reasoning(abstract)

2309.14991 2024-12-10 cs.CV 50%

Robust Sequential DeepFake Detection

Rui Shao, Tianxing Wu, Ziwei Liu

专题命中复杂问题求解：reasoning(abstract)

Comments IJCV 2025. Extension of our ECCV 2022 paper: arXiv:2207.02204. Code: https://github.com/rshaojimmy/SeqDeepFake

2411.17606 2024-12-03 cs.CV 50%

HyperSeg: Towards Universal Visual Segmentation with Large Language Model

Cong Wei, Yujie Zhong, Haoxian Tan, Yong Liu, Zheng Zhao, Jie Hu, Yujiu Yang

专题命中复杂问题求解：reasoning(abstract)

2411.19862 2024-12-02 cs.IR 50%

Cross-Domain Recommendation Meets Large Language Models

Ajay Krishna Vajjala, Dipak Meher, Ziwei Zhu, David S. Rosenblum

专题命中复杂问题求解：reasoning(abstract)

Comments 12 pages

2411.18983 2024-12-02 cs.CV cs.MA 50%

SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing

Rong-Cheng Tu, Wenhao Sun, Zhao Jin, Jingyi Liao, Jiaxing Huang, Dacheng Tao

专题命中复杂问题求解：planning(abstract)

2409.08464 2024-12-02 cs.CV 50%

VLTP: Vision-Language Guided Token Pruning for Task-Oriented Segmentation

Hanning Chen, Yang Ni, Wenjun Huang, Yezi Liu, SungHeon Jeong, Fei Wen, Nathaniel Bastian, Hugo Latapie, Mohsen Imani

专题命中复杂问题求解：reasoning(abstract)

Comments Accepted at WACV 2025

2411.17837 2024-11-28 cs.CV 50%

OracleSage: Towards Unified Visual-Linguistic Understanding of Oracle Bone Scripts through Cross-Modal Knowledge Fusion

Hanqi Jiang, Yi Pan, Junhao Chen, Zhengliang Liu, Yifan Zhou, Peng Shu, Yiwei Li, Huaqin Zhao, Stephen Mihm, Lewis C Howe, Tianming Liu

专题命中复杂问题求解：reasoning(abstract)

2411.15411 2024-11-26 cs.CV 50%

FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity

Hang Hua, Qing Liu, Lingzhi Zhang, Jing Shi, Zhifei Zhang, Yilin Wang, Jianming Zhang, Jiebo Luo

专题命中复杂问题求解：reasoning(abstract)

Comments Preprint

2410.16954 2024-11-26 cs.DC 50%

LoRA-C: Parameter-Efficient Fine-Tuning of Robust CNN for IoT Devices

Chuntao Ding, Xu Cao, Jianhang Xie, Linlin Fan, Shangguang Wang, Zhichao Lu

专题命中复杂问题求解：reasoning(abstract)

Comments 14 pages, 13 figures, https://github.com/alexyyds2024/lora-C

2411.07323 2024-11-13 physics.soc-ph nlin.AO 50%

Mean-field analysis for cognitively-grounded opinion dynamics with confirmation bias

Sven Banisch, Joris Wessels

专题命中复杂问题求解：reasoning(abstract)

2411.02320 2024-11-05 cs.SE 50%

An Empirical Study on the Code Refactoring Capability of Large Language Models

Jonathan Cordeiro, Shayan Noei, Ying Zou

专题命中复杂问题求解：chain-of-thought(abstract)

2411.02093 2024-11-05 cs.SE 50%

Do Advanced Language Models Eliminate the Need for Prompt Engineering in Software Engineering?

Guoqing Wang, Zeyu Sun, Zhihao Gong, Sixiang Ye, Yizhou Chen, Yifan Zhao, Qingyuan Liang, Dan Hao

专题命中复杂问题求解：reasoning(abstract)

2410.09733 2024-10-15 cs.CV 50%

MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models

Hang Hua, Yunlong Tang, Ziyun Zeng, Liangliang Cao, Zhengyuan Yang, Hangfeng He, Chenliang Xu, Jiebo Luo

专题命中复杂问题求解：reasoning(abstract)

Comments 21 pages, 15 figures

2410.07713 2024-10-11 cs.MA cs.CY cs.SI 50%

A Hate Speech Moderated Chat Application: Use Case for GDPR and DSA Compliance

Jan Fillies, Theodoros Mitsikas, Ralph Schäfermeier, Adrian Paschke

专题命中复杂问题求解：reasoning(abstract)

2407.02606 2024-10-10 cs.HC 50%

An AI-Based System Utilizing IoT-Enabled Ambient Sensors and LLMs for Complex Activity Tracking

Yuan Sun, Jorge Ortiz

专题命中复杂问题求解：reasoning(abstract)

2410.01336 2024-10-03 cs.CV 50%

VectorGraphNET: Graph Attention Networks for Accurate Segmentation of Complex Technical Drawings

Andrea Carrara, Stavros Nousias, André Borrmann

专题命中复杂问题求解：planning(abstract)

Comments 27 pages, 13 figures

2405.05885 2024-10-03 cs.RO 50%

VLM-Auto: VLM-based Autonomous Driving Assistant with Human-like Behavior and Understanding for Complex Road Scenes

Ziang Guo, Zakhar Yagudin, Artem Lykov, Mikhail Konenkov, Dzmitry Tsetserukou

专题命中复杂问题求解：planning(abstract)

Comments The paper is accepted by the IEEE conference

2409.14739 2024-09-24 cs.ET cs.SY eess.SY 50%

AmpAgent: An LLM-based Multi-Agent System for Multi-stage Amplifier Schematic Design from Literature for Process and Performance Porting

Chengjie Liu, Weiyu Chen, Anlan Peng, Yuan Du, Li Du, Jun Yang

专题命中复杂问题求解：reasoning(abstract)

2409.09661 2024-09-17 cs.SE cs.CR 50%

ContractTinker: LLM-Empowered Vulnerability Repair for Real-World Smart Contracts

Che Wang, Jiashuo Zhang, Jianbo Gao, Libin Xia, Zhi Guan, Zhong Chen

专题命中复杂问题求解：chain-of-thought(abstract)

Comments 4 pages, and to be accepted in ASE2024

2404.13306 2024-09-10 cs.CV cs.MM 50%

FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models

Yixuan Li, Xuelin Liu, Xiaoyang Wang, Bu Sung Lee, Shiqi Wang, Anderson Rocha, Weisi Lin

专题命中复杂问题求解：reasoning(abstract)

2409.00962 2024-09-04 cs.HC 50%

Mental-Gen: A Brain-Computer Interface-Based Interactive Method for Interior Space Generative Design

Yijiang Liu, Hui Wang

专题命中复杂问题求解：reasoning(abstract)

Comments 18 pages, 8 figures

2408.14594 2024-08-28 cs.CV 50%

MMR: Evaluating Reading Ability of Large Multimodal Models

Jian Chen, Ruiyi Zhang, Yufan Zhou, Ryan Rossi, Jiuxiang Gu, Changyou Chen

专题命中复杂问题求解：reasoning(abstract)

2408.05897 2024-08-13 cs.HC 50%

TRIZ-GPT: An LLM-augmented method for problem-solving

Liuqing Chen, Yaxuan Song, Shixian Ding, Lingyun Sun, Peter Childs, Haoyu Zuo

专题命中复杂问题求解：reasoning(abstract)

2408.04158 2024-08-09 eess.IV cs.CV 50%

Efficient Single Image Super-Resolution with Entropy Attention and Receptive Field Augmentation

Xiaole Zhao, Linze Li, Chengxing Xie, Xiaoming Zhang, Ting Jiang, Wenjie Lin, Shuaicheng Liu, Tianrui Li

专题命中复杂问题求解：reasoning(abstract)

Comments Accepted to ACM MM 2024

2404.11129 2024-08-06 cs.CV 50%

Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales

Minghe Gao, Shuang Chen, Liang Pang, Yuan Yao, Jisheng Dang, Wenqiao Zhang, Juncheng Li, Siliang Tang, Yueting Zhuang, Tat-Seng Chua

专题命中复杂问题求解：reasoning(abstract)

2407.20505 2024-07-31 cs.CV 50%

Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debate

Zheng Lin, Zhenxing Niu, Zhibin Wang, Yinghui Xu

专题命中复杂问题求解：reasoning(abstract)

2402.10698 2024-07-23 cs.CV 50%

Question-Instructed Visual Descriptions for Zero-Shot Video Question Answering

David Romero, Thamar Solorio

专题命中复杂问题求解：reasoning(abstract)

2312.01261 2024-07-18 cs.CV cs.CY 50%

TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models

Aditya Chinchure, Pushkar Shukla, Gaurav Bhatt, Kiri Salij, Kartik Hosanagar, Leonid Sigal, Matthew Turk

专题命中复杂问题求解：reasoning(abstract)

Comments Accepted to ECCV 2024. Code and data available at https://tibet-ai.github.io

1. 复杂问题求解 5035 篇

RefHCM: A Unified Model for Referring Perceptions in Human-Centric Scenarios

Leveraging Retrieval-Augmented Tags for Large Vision-Language Understanding in Complex Scenes

Bridging Vision and Language: Modeling Causality and Temporality in Video Narratives

Robust Sequential DeepFake Detection

HyperSeg: Towards Universal Visual Segmentation with Large Language Model

Cross-Domain Recommendation Meets Large Language Models

SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing

VLTP: Vision-Language Guided Token Pruning for Task-Oriented Segmentation

OracleSage: Towards Unified Visual-Linguistic Understanding of Oracle Bone Scripts through Cross-Modal Knowledge Fusion

FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity

LoRA-C: Parameter-Efficient Fine-Tuning of Robust CNN for IoT Devices

Mean-field analysis for cognitively-grounded opinion dynamics with confirmation bias

An Empirical Study on the Code Refactoring Capability of Large Language Models

Do Advanced Language Models Eliminate the Need for Prompt Engineering in Software Engineering?

MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models

A Hate Speech Moderated Chat Application: Use Case for GDPR and DSA Compliance

An AI-Based System Utilizing IoT-Enabled Ambient Sensors and LLMs for Complex Activity Tracking

VectorGraphNET: Graph Attention Networks for Accurate Segmentation of Complex Technical Drawings

VLM-Auto: VLM-based Autonomous Driving Assistant with Human-like Behavior and Understanding for Complex Road Scenes

AmpAgent: An LLM-based Multi-Agent System for Multi-stage Amplifier Schematic Design from Literature for Process and Performance Porting

ContractTinker: LLM-Empowered Vulnerability Repair for Real-World Smart Contracts

FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models

Mental-Gen: A Brain-Computer Interface-Based Interactive Method for Interior Space Generative Design

MMR: Evaluating Reading Ability of Large Multimodal Models

TRIZ-GPT: An LLM-augmented method for problem-solving

Efficient Single Image Super-Resolution with Entropy Attention and Receptive Field Augmentation

Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales

Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debate

Question-Instructed Visual Descriptions for Zero-Shot Video Question Answering

TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models