视觉大模型 / VLM - arXivDaily 专题

2410.18976 2024-10-25 cs.CV cs.AI cs.CL cs.CY cs.LG 67%

CAMEL-Bench: A Comprehensive Arabic LMM Benchmark

Sara Ghaboura, Ahmed Heakl, Omkar Thawakar, Ali Alharthi, Ines Riahi, Abduljalil Saif, Jorma Laaksonen, Fahad S. Khan, Salman Khan, Rao M. Anwer

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments 10 pages, 5 figures, NAACL

2410.14690 2024-10-22 cs.LG cs.AI cs.CV 67%

Rethinking VLMs and LLMs for Image Classification

Avi Cooper, Keizo Kato, Chia-Hsien Shih, Hiroaki Yamane, Kasper Vinken, Kentaro Takemoto, Taro Sunagawa, Hao-Wei Yeh, Jin Yamanaka, Ian Mason, Xavier Boix

专题命中视觉推理：visual language model(abstract)；分类 cs.CV、cs.AI、cs.LG

2402.14899 2024-09-24 cs.CV cs.AI cs.CR cs.LG 67%

Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image

Zefeng Wang, Zhen Han, Shuo Chen, Fan Xue, Zifeng Ding, Xun Xiao, Volker Tresp, Philip Torr, Jindong Gu

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

2409.09039 2024-09-17 cs.LG cs.AI cs.CV 67%

AutoGeo: Automating Geometric Image Dataset Creation for Enhanced Geometry Understanding

Zihan Huang, Tao Wu, Wang Lin, Shengyu Zhang, Jingyuan Chen, Fei Wu

专题命中视觉推理：multimodal large language model(abstract)；分类 cs.CV、cs.AI、cs.LG

2310.10404 2024-07-30 cs.CV cs.AI cs.LG 67%

LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation

Kibum Kim, Kanghoon Yoon, Jaehyeong Jeon, Yeonjun In, Jinyoung Moon, Donghyun Kim, Chanyoung Park

专题命中视觉推理：grounding(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments 8 pages; CVPR 2024

Journal ref CVPR (2024), 28306-28316

2407.01284 2024-07-02 cs.AI cs.CL cs.CV cs.LG cs.SC 67%

We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?

Runqi Qiao, Qiuna Tan, Guanting Dong, Minhui Wu, Chong Sun, Xiaoshuai Song, Zhuoma GongQue, Shanglin Lei, Zhe Wei, Miaoxuan Zhang, Runfeng Qiao, Yifan Zhang, Xiao Zong, Yida Xu, Muxi Diao, Zhimin Bao, Chen Li, Honggang Zhang

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments Work in progress

2406.17806 2024-06-27 cs.CL cs.AI cs.CR cs.CV cs.LG 67%

MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?

Xirui Li, Hengguang Zhou, Ruochen Wang, Tianyi Zhou, Minhao Cheng, Cho-Jui Hsieh

专题命中视觉推理：multimodal large language model(abstract)；分类 cs.CV、cs.AI、cs.LG

2402.13254 2024-06-13 cs.CV cs.AI cs.CL cs.LG 67%

CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples

Jianrui Zhang, Mu Cai, Tengyang Xie, Yong Jae Lee

专题命中视觉推理：LLaVA(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments 15 pages, 6 figures, 12 tables, Project Page: https://countercurate.github.io/

2401.11708 2024-06-05 cs.CV cs.AI cs.LG 67%

Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs

Ling Yang, Zhaochen Yu, Chenlin Meng, Minkai Xu, Stefano Ermon, Bin Cui

专题命中视觉推理：MLLM(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments ICML 2024. Project: https://github.com/YangLing0818/RPG-DiffusionMaster

2311.17076 2024-04-02 cs.CV cs.AI cs.CL cs.LG 67%

Compositional Chain-of-Thought Prompting for Large Multimodal Models

Chancharik Mitra, Brandon Huang, Trevor Darrell, Roei Herzig

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

2307.08506 2023-12-19 cs.CV cs.AI cs.LG 67%

Does Visual Pretraining Help End-to-End Reasoning?

Chen Sun, Calvin Luo, Xingyi Zhou, Anurag Arnab, Cordelia Schmid

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments NeurIPS 2023

2311.08083 2023-11-15 cs.AI cs.CV cs.LG 67%

Solving ARC visual analogies with neural embeddings and vector arithmetic: A generalized method

Luca H. Thoms, Karel A. Veldkamp, Hannes Rosenbusch, Claire E. Stevenson

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments Data and code can be found on https://github.com/foger3/ARC_DeepLearning

2310.18804 2023-10-31 cs.CL cs.AI cs.CV cs.LG 67%

Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting

Hejie Cui, Xinyu Fang, Zihan Zhang, Ran Xu, Xuan Kan, Xin Liu, Yue Yu, Manling Li, Yangqiu Song, Carl Yang

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments Accepted to NeurIPS 2023

2308.15887 2023-08-31 cs.AI cs.CV cs.LG cs.LO 67%

On the Potential of CLIP for Compositional Logical Reasoning

Justin Brody

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments In Proceedings ICLP 2023, arXiv:2308.14898

Journal ref EPTCS 385, 2023, pp. 80-86

2202.08806 2023-08-28 cs.CL cs.AI cs.CV cs.LG 67%

Grammar-Based Grounded Lexicon Learning

Jiayuan Mao, Haoyue Shi, Jiajun Wu, Roger P. Levy, Joshua B. Tenenbaum

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments Minor typo fixes. NeurIPS 2021. Project page: https://g2l2.csail.mit.edu/

2306.16774 2023-06-30 cs.CL 67%

Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages

Yasmine Karoui, Rémi Lebret, Negar Foroutan, Karl Aberer

专题命中视觉推理：vision-language model(abstract)；visual reasoning(abstract)

Comments Accepted to ACL 2023 as short paper

2209.09115 2023-02-28 cs.CV cs.AI cs.LG 67%

Compositional Law Parsing with Latent Random Functions

Fan Shi, Bin Li, Xiangyang Xue

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

2103.00820 2022-12-08 cs.AI cs.CL cs.CV cs.LG 67%

Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues

Hung Le, Nancy F. Chen, Steven C. H. Hoi

专题命中视觉推理：visual question answering(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments Accepted at ICLR (International Conference on Learning Representations) 2021

2209.07000 2022-09-16 cs.CL 67%

VIPHY: Probing "Visible" Physical Commonsense Knowledge

Shikhar Singh, Ehsan Qasemi, Muhao Chen

专题命中视觉推理：vision-language model(abstract)；visual reasoning(abstract)

Comments In Progress (under review)

2110.13214 2022-07-26 cs.CV cs.AI cs.CL cs.LG 67%

IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning

Pan Lu, Liang Qiu, Jiaqi Chen, Tony Xia, Yizhou Zhao, Wei Zhang, Zhou Yu, Xiaodan Liang, Song-Chun Zhu

专题命中视觉推理：visual question answering(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments Corrected typos. Accepted to NeurIPS 2021, 27 pages, 18 figures. Data and code are available at https://iconqa.github.io

2204.11167 2022-06-14 cs.CV cs.AI cs.LG 67%

RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning

Xiaojian Ma, Weili Nie, Zhiding Yu, Huaizu Jiang, Chaowei Xiao, Yuke Zhu, Song-Chun Zhu, Anima Anandkumar

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments ICLR 2022; Code: https://github.com/NVlabs/RelViT

2201.10266 2022-01-26 cs.AI cs.CV cs.LG cs.LO cs.RO 67%

Combining Commonsense Reasoning and Knowledge Acquisition to Guide Deep Learning in Robotics

Mohan Sridharan, Tiago Mota

专题命中视觉推理：grounding(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments 37 pages, 17 figures, 5 tables

2112.05136 2021-12-10 cs.CV cs.AI cs.CL cs.LG 67%

PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning

Yining Hong, Li Yi, Joshua B. Tenenbaum, Antonio Torralba, Chuang Gan

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments NeurIPS 2021. Project page: http://ptr.csail.mit.edu/

2111.13131 2021-11-29 cs.CV cs.AI cs.LG 67%

Scene Graph Generation with Geometric Context

Vishal Kumar, Albert Mundu, Satish Kumar Singh

专题命中视觉推理：visual question answering(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments Paper accepted at 6th IAPR International Conference on Computer Vision & Image Processing (CVIP2021), IIT Ropar, India

2110.00804 2021-10-19 cs.LG cs.AI cs.CV cs.RO 67%

ProTo: Program-Guided Transformer for Program-Guided Tasks

Zelin Zhao, Karan Samel, Binghong Chen, Le Song

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments Accepted in NeurIPS 2021

2004.09406 2021-04-14 cs.CV cs.AI cs.LG q-bio.NC stat.ML 67%

Five Points to Check when Comparing Visual Perception in Humans and Machines

Christina M. Funke, Judy Borowski, Karolina Stosio, Wieland Brendel, Thomas S. A. Wallis, Matthias Bethge

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments V3: minor changes like in published JOV version (https://doi.org/10.1167/jov.21.3.16) V2: New title; added general section (checklist); manuscript restructured such that each case study is one chapter; adversarial examples in first study replaced by different analysis

Journal ref Journal of Vision 21, no. 3 (2021): 16-16

2103.14232 2021-03-29 cs.CV cs.AI cs.LG 67%

ACRE: Abstract Causal REasoning Beyond Covariation

Chi Zhang, Baoxiong Jia, Mark Edmonds, Song-Chun Zhu, Yixin Zhu

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments CVPR 2021 paper. Supplementary: http://wellyzhang.github.io/attach/cvpr21zhang_acre_supp.pdf Project: http://wellyzhang.github.io/project/acre.html

2010.00763 2021-01-06 cs.AI cs.CV cs.LG 67%

Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning

Weili Nie, Zhiding Yu, Lei Mao, Ankit B. Patel, Yuke Zhu, Animashree Anandkumar

专题命中视觉推理：visual reasoning(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments 22 pages, NeurIPS 2020

2009.09154 2020-10-05 cs.CL 67%

CLEVR Parser: A Graph Parser Library for Geometric Learning on Language Grounded Image Scenes

Raeid Saqur, Ameet Deshpande

专题命中视觉推理：visual reasoning(abstract)；grounding(abstract)

Comments Accepted at NLP-OSS, EMNLP 2020 (2nd Workshop for Natural Language Processing Open Source Software)

2006.06649 2020-07-29 stat.ML cs.AI cs.CV cs.LG 67%

Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning

Qing Li, Siyuan Huang, Yining Hong, Yixin Chen, Ying Nian Wu, Song-Chun Zhu

专题命中视觉推理：visual question answering(abstract)；分类 cs.CV、cs.AI、cs.LG

Comments ICML 2020. Project page: https://liqing-ustc.github.io/NGS

1. 视觉推理 4484 篇

CAMEL-Bench: A Comprehensive Arabic LMM Benchmark

Rethinking VLMs and LLMs for Image Classification

Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image

AutoGeo: Automating Geometric Image Dataset Creation for Enhanced Geometry Understanding

LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation

We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?

MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?

CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples

Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs

Compositional Chain-of-Thought Prompting for Large Multimodal Models

Does Visual Pretraining Help End-to-End Reasoning?

Solving ARC visual analogies with neural embeddings and vector arithmetic: A generalized method

Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting

On the Potential of CLIP for Compositional Logical Reasoning

Grammar-Based Grounded Lexicon Learning

Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages

Compositional Law Parsing with Latent Random Functions

Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues

VIPHY: Probing "Visible" Physical Commonsense Knowledge

IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning

RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning

Combining Commonsense Reasoning and Knowledge Acquisition to Guide Deep Learning in Robotics

PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning

Scene Graph Generation with Geometric Context

ProTo: Program-Guided Transformer for Program-Guided Tasks

Five Points to Check when Comparing Visual Perception in Humans and Machines

ACRE: Abstract Causal REasoning Beyond Covariation

Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning

CLEVR Parser: A Graph Parser Library for Geometric Learning on Language Grounded Image Scenes

Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning