大模型推理能力 - arXivDaily 专题

2503.17990 2025-03-25 cs.IR 50%

SUNAR: Semantic Uncertainty based Neighborhood Aware Retrieval for Complex QA

V Venktesh, Mandeep Rathee, Avishek Anand

专题命中复杂问题求解：reasoning(abstract)

Comments Accepted at NAACL 2025 Main Conference

2503.14504 2025-03-25 cs.CV 50%

Aligning Multimodal LLM with Human Preference: A Survey

Tao Yu, Yi-Fan Zhang, Chaoyou Fu, Junkang Wu, Jinda Lu, Kun Wang, Xingyu Lu, Yunhang Shen, Guibin Zhang, Dingjie Song, Yibo Yan, Tianlong Xu, Qingsong Wen, Zhang Zhang, Yan Huang, Liang Wang, Tieniu Tan

专题命中复杂问题求解：reasoning(abstract)

Comments Project page: https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Alignment

2503.13440 2025-03-19 cs.CV 50%

MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling

Yingyue Li, Bencheng Liao, Wenyu Liu, Xinggang Wang

专题命中复杂问题求解：reasoning(abstract)

Comments Code and model are available at http://github.com/hustvl/MaTVLM

2409.16266 2025-03-18 cs.RO 50%

REBEL: Rule-based and Experience-enhanced Learning with LLMs for Initial Task Allocation in Multi-Human Multi-Robot Teaming

Arjun Gupte, Ruiqi Wang, Vishnunandan L. N. Venkatesh, Taehyeon Kim, Dezhong Zhao, Ziqin Yuan, Byung-Cheol Min

专题命中复杂问题求解：reasoning(abstract)

2503.08168 2025-03-12 cs.CV 50%

TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancement

Miao Zhang, Jun Yin, Pengyu Zeng, Yiqing Shen, Shuai Lu, Xueqian Wang

专题命中复杂问题求解：reasoning(abstract)

2503.04103 2025-03-07 cs.HC 50%

Compositional Structures as Substrates for Human-AI Co-creation Environment: A Design Approach and A Case Study

Yining Cao, Yiyi Huang, Anh Truong, Hijung Valentina Shin, Haijun Xia

专题命中复杂问题求解：planning(abstract)

2409.11919 2025-03-07 cs.CV 50%

LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension

Amaia Cardiel, Eloi Zablocki, Elias Ramzi, Oriane Siméoni, Matthieu Cord

专题命中复杂问题求解：reasoning(abstract)

Comments LLM-wrapper (v3) is published as a conference paper at ICLR 2025. (v1 was presented at EVAL-FoMo workshop, ECCV 2024.)

2503.02695 2025-03-05 cs.IR 50%

Zero-Shot Complex Question-Answering on Long Scientific Documents

Wanting Wang

专题命中复杂问题求解：reasoning(abstract)

Comments AAAI 2025 Workshop on Document Understanding and Intelligence

2503.02076 2025-03-05 cs.RO cs.SY eess.SY 50%

CorrA: Leveraging Large Language Models for Dynamic Obstacle Avoidance of Autonomous Vehicles

Shanting Wang, Panagiotis Typaldos, Andreas A. Malikopoulos

专题命中复杂问题求解：reasoning(abstract)

2411.09022 2025-03-05 cs.RO 50%

DART-LLM: Dependency-Aware Multi-Robot Task Decomposition and Execution using Large Language Models

Yongdong Wang, Runze Xiao, Jun Younes Louhi Kasahara, Ryosuke Yajima, Keiji Nagatani, Atsushi Yamashita, Hajime Asama

专题命中复杂问题求解：reasoning(abstract)

Comments The work was first submitted to an IEEE conference on September 15, 2024

2502.16486 2025-02-27 cs.CV 50%

MQADet: A Plug-and-Play Paradigm for Enhancing Open-Vocabulary Object Detection via Multimodal Question Answering

Caixiong Li, Xiongwei Zhao, Jinhang Zhang, Xing Zhang, Qihao Sun, Zhou Wu

专题命中复杂问题求解：reasoning(abstract)

2502.05461 2025-02-25 cs.CR 50%

IllusionCAPTCHA: A CAPTCHA based on Visual Illusion

Ziqi Ding, Gelei Deng, Yi Liu, Junchen Ding, Jieshan Chen, Yulei Sui, Yuekang Li

专题命中复杂问题求解：reasoning(abstract)

2412.09914 2025-02-25 cs.CY 50%

Atomic Learning Objectives Labeling: A High-Resolution Approach for Physics Education

Naiming Liu, Shashank Sonkar, Debshila Basu Mallick, Richard Baraniuk, Zhongzhou Chen

专题命中复杂问题求解：reasoning(abstract)

Comments The paper is accepted to LAK'2025

2502.05728 2025-02-24 cs.RO 50%

Hierarchical Equivariant Policy via Frame Transfer

Haibo Zhao, Dian Wang, Yizhe Zhu, Xupeng Zhu, Owen Howell, Linfeng Zhao, Yaoyao Qian, Robin Walters, Robert Platt

专题命中复杂问题求解：reasoning(abstract)

2410.17809 2025-02-18 cs.CV 50%

An Intelligent Agentic System for Complex Image Restoration Problems

Kaiwen Zhu, Jinjin Gu, Zhiyuan You, Yu Qiao, Chao Dong

专题命中复杂问题求解：reasoning(abstract)

Comments ICLR 2025

2410.20299 2025-02-17 cs.DC 50%

EACO-RAG: Towards Distributed Tiered LLM Deployment using Edge-Assisted and Collaborative RAG with Adaptive Knowledge Update

Jiaxing Li, Chi Xu, Lianchen Jia, Feng Wang, Cong Zhang, Jiangchuan Liu

专题命中复杂问题求解：reasoning(abstract)

2502.07981 2025-02-13 cs.HC 50%

AI Humor Generation: Cognitive, Social and Creative Skills for Effective Humor

Sean Kim, Lydia B. Chilton

专题命中复杂问题求解：reasoning(abstract)

Comments 18 pages, 6 figures

2502.05919 2025-02-11 cs.SI 50%

Can Generative Agent-Based Modeling Replicate the Friendship Paradox in Social Media Simulations?

Gian Marco Orlando, Valerio La Gatta, Diego Russo, Vincenzo Moscato

专题命中复杂问题求解：reasoning(abstract)

Comments Accepted at 17th ACM Web Science Conference 2025 (WebSci'25)

2502.00562 2025-02-04 cs.CE 50%

Assessment of ChatGPT for Engineering Statics Analysis

Benjamin Hope, Jayden Bracey, Sahar Choukir, Derek Warner

专题命中复杂问题求解：reasoning(abstract)

2407.11712 2025-02-04 cs.IR 50%

Fine-tuning Multimodal Large Language Models for Product Bundling

Xiaohao Liu, Jie Wu, Zhulin Tao, Yunshan Ma, Yinwei Wei, Tat-seng Chua

专题命中复杂问题求解：reasoning(abstract)

Comments Accepted by KDD 2025 (CR)

2501.16661 2025-01-29 cs.HC 50%

Jupybara: Operationalizing a Design Space for Actionable Data Analysis and Storytelling with LLMs

Huichen Will Wang, Larry Birnbaum, Vidya Setlur

专题命中复杂问题求解：reasoning(abstract)

Comments Conditionally Accepted at CHI '25

2501.16495 2025-01-29 cs.SE 50%

Explaining GitHub Actions Failures with Large Language Models: Challenges, Insights, and Limitations

Pablo Valenzuela-Toledo, Chuyue Wu, Sandro Hernandez, Alexander Boll, Roman Machacek, Sebastiano Panichella, Timo Kehrer

专题命中复杂问题求解：reasoning(abstract)

Comments Accepted at ICPC-2025

2501.14205 2025-01-27 cs.NI 50%

Serving Long-Context LLMs at the Mobile Edge: Test-Time Reinforcement Learning-based Model Caching and Inference Offloading

Minrui Xu, Dusit Niyato, Christopher G. Brinton

专题命中复杂问题求解：reasoning(abstract)

2312.17345 2025-01-16 cs.CV 50%

3VL: Using Trees to Improve Vision-Language Models' Interpretability

Nir Yellinek, Leonid Karlinsky, Raja Giryes

专题命中复杂问题求解：reasoning(abstract)

Comments accepted to IEEE TIP

2501.07109 2025-01-14 cs.CV 50%

The Quest for Visual Understanding: A Journey Through the Evolution of Visual Question Answering

Anupam Pandey, Deepjyoti Bodo, Arpan Phukan, Asif Ekbal

专题命中复杂问题求解：reasoning(abstract)

2501.04312 2025-01-09 cs.SE 50%

Your Fix Is My Exploit: Enabling Comprehensive DL Library API Fuzzing with Large Language Models

Kunpeng Zhang, Shuai Wang, Jitao Han, Xiaogang Zhu, Xian Li, Shaohua Wang, Sheng Wen

专题命中复杂问题求解：reasoning(abstract)

Journal ref 2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE)

2412.07320 2025-01-09 cs.CV 50%

CoMA: Compositional Human Motion Generation with Multi-modal Agents

Shanlin Sun, Gabriel De Araujo, Jiaqi Xu, Shenghan Zhou, Hanwen Zhang, Ziheng Huang, Chenyu You, Xiaohui Xie

专题命中复杂问题求解：self-correction(abstract)

Comments Project Page: https://gabrie-l.github.io/coma-page/

2501.02192 2025-01-07 cs.SI 50%

EvoPath: Evolutionary Meta-path Discovery with Large Language Models for Complex Heterogeneous Information Networks

Shixuan Liu, Haoxiang Cheng, Yunfei Wang, Yue He, Changjun Fan, Zhong Liu

专题命中复杂问题求解：reasoning(abstract)

2501.01631 2025-01-06 cs.DB 50%

Revisiting Data Analysis with Pre-trained Foundation Models

Chen Liang, Donghua Yang, Zheng Liang, Zhiyu Liang, Tianle Zhang, Boyu Xiao, Yuqing Yang, Wenqi Wang, Hongzhi Wang

专题命中复杂问题求解：reasoning(abstract)

Comments 22 pages, 7 figures

2501.00795 2025-01-03 cs.CV 50%

Multimodal Large Models Are Effective Action Anticipators

Binglu Wang, Yao Tian, Shunzhou Wang, Le Yang

专题命中复杂问题求解：reasoning(abstract)

1. 复杂问题求解 5035 篇

SUNAR: Semantic Uncertainty based Neighborhood Aware Retrieval for Complex QA

Aligning Multimodal LLM with Human Preference: A Survey

MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling

REBEL: Rule-based and Experience-enhanced Learning with LLMs for Initial Task Allocation in Multi-Human Multi-Robot Teaming

TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancement

Compositional Structures as Substrates for Human-AI Co-creation Environment: A Design Approach and A Case Study

LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension

Zero-Shot Complex Question-Answering on Long Scientific Documents

CorrA: Leveraging Large Language Models for Dynamic Obstacle Avoidance of Autonomous Vehicles

DART-LLM: Dependency-Aware Multi-Robot Task Decomposition and Execution using Large Language Models

MQADet: A Plug-and-Play Paradigm for Enhancing Open-Vocabulary Object Detection via Multimodal Question Answering

IllusionCAPTCHA: A CAPTCHA based on Visual Illusion

Atomic Learning Objectives Labeling: A High-Resolution Approach for Physics Education

Hierarchical Equivariant Policy via Frame Transfer

An Intelligent Agentic System for Complex Image Restoration Problems

EACO-RAG: Towards Distributed Tiered LLM Deployment using Edge-Assisted and Collaborative RAG with Adaptive Knowledge Update

AI Humor Generation: Cognitive, Social and Creative Skills for Effective Humor

Can Generative Agent-Based Modeling Replicate the Friendship Paradox in Social Media Simulations?

Assessment of ChatGPT for Engineering Statics Analysis

Fine-tuning Multimodal Large Language Models for Product Bundling

Jupybara: Operationalizing a Design Space for Actionable Data Analysis and Storytelling with LLMs

Explaining GitHub Actions Failures with Large Language Models: Challenges, Insights, and Limitations

Serving Long-Context LLMs at the Mobile Edge: Test-Time Reinforcement Learning-based Model Caching and Inference Offloading

3VL: Using Trees to Improve Vision-Language Models' Interpretability

The Quest for Visual Understanding: A Journey Through the Evolution of Visual Question Answering

Your Fix Is My Exploit: Enabling Comprehensive DL Library API Fuzzing with Large Language Models

CoMA: Compositional Human Motion Generation with Multi-modal Agents

EvoPath: Evolutionary Meta-path Discovery with Large Language Models for Complex Heterogeneous Information Networks

Revisiting Data Analysis with Pre-trained Foundation Models

Multimodal Large Models Are Effective Action Anticipators