大模型推理能力 - arXivDaily 专题

2210.05335 2023-07-21 cs.CV cs.CL cs.MM 57%

MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model

Yatai Ji, Junjie Wang, Yuan Gong, Lin Zhang, Yanru Zhu, Hongfa Wang, Jiaxing Zhang, Tetsuya Sakai, Yujiu Yang

专题命中视觉空间推理：reasoning(abstract)；分类 cs.CL

Comments CVPR 2023 Main Track Long Paper

2307.09636 2023-07-20 cs.CV cs.AI 57%

Traffic-Domain Video Question Answering with Automatic Captioning

Ehsan Qasemi, Jonathan M. Francis, Alessandro Oltramari

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI

Comments Accepted in ITSC2023

2306.16774 2023-06-30 cs.CL 57%

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

Yasmine Karoui, Rémi Lebret, Negar Foroutan, Karl Aberer

专题命中视觉空间推理：reasoning(abstract)；分类 cs.CL

Comments Accepted to ACL 2023 as short paper

2206.08737 2023-06-30 cs.RO cs.AI 57%

N$^2$M$^2$: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments

Daniel Honerkamp, Tim Welschehold, Abhinav Valada

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI

Comments Project website: http://mobile-rl.cs.uni-freiburg.de; Accepted at T-RO

2108.13680 2023-06-05 cs.RO cs.LG 57%

Learning Practically Feasible Policies for Online 3D Bin Packing

Hang Zhao, Chenyang Zhu, Xin Xu, Hui Huang, Kai Xu

专题命中视觉空间推理：planning(abstract)；分类 cs.LG

Comments Science China Information Sciences

2305.18583 2023-05-31 cs.CV cs.AI 57%

Controllable Text-to-Image Generation with GPT-4

Tianjun Zhang, Yi Zhang, Vibhav Vineet, Neel Joshi, Xin Wang

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI

2305.18373 2023-05-31 cs.CV cs.CL 57%

KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language Models

Zhiwei Jia, Pradyumna Narayana, Arjun R. Akula, Garima Pruthi, Hao Su, Sugato Basu, Varun Jampani

专题命中视觉空间推理：reasoning(abstract)；分类 cs.CL

Comments ACL 2023

2302.11089 2023-05-25 cs.RO cs.AI cs.SY eess.SP eess.SY 57%

Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation: A Comprehensive Review

Arman Asgharpoor Golroudbari, Mohammad Hossein Sabour

专题命中视觉空间推理：planning(abstract)；分类 cs.AI

2304.14508 2023-05-01 eess.IV cs.CV cs.LG 57%

3D Brainformer: 3D Fusion Transformer for Brain Tumor Segmentation

Rui Nian, Guoyao Zhang, Yao Sui, Yuqi Qian, Qiuying Li, Mingzhang Zhao, Jianhui Li, Ali Gholipour, Simon K. Warfield

专题命中视觉空间推理：planning(abstract)；分类 cs.LG

Comments 10 pages, 4 figures

2304.06258 2023-04-17 cs.CV cs.LG eess.IV 57%

MProtoNet: A Case-Based Interpretable Model for Brain Tumor Classification with 3D Multi-parametric Magnetic Resonance Imaging

Yuanyuan Wei, Roger Tam, Xiaoying Tang

专题命中视觉空间推理：reasoning(abstract)；分类 cs.LG

Comments 15 pages, 5 figures, 1 table; accepted for oral presentation at MIDL 2023 (https://openreview.net/forum?id=6Wbj3QCo4U4 ); camera-ready version

2304.05402 2023-04-13 cs.CV cs.CR cs.LG cs.MM 57%

Boosting Cross-task Transferability of Adversarial Patches with Visual Relations

Tony Ma, Songze Li, Yisong Xiao, Shunchang Liu

专题命中视觉空间推理：reasoning(abstract)；分类 cs.LG

2303.02814 2023-03-27 cs.CV cs.CR cs.HC cs.LG 57%

Visual Analytics of Neuron Vulnerability to Adversarial Attacks on Convolutional Neural Networks

Yiran Li, Junpeng Wang, Takanori Fujiwara, Kwan-Liu Ma

专题命中视觉空间推理：reasoning(abstract)；分类 cs.LG

Comments Accepted by the Special Issue on Human-Centered Explainable AI, ACM Transactions on Interactive Intelligent Systems

2301.07389 2023-03-22 cs.CV cs.LG 57%

Towards Models that Can See and Read

Roy Ganz, Oren Nuriel, Aviad Aberdam, Yair Kittenplon, Shai Mazor, Ron Litman

专题命中视觉空间推理：reasoning(abstract)；分类 cs.LG

2303.08284 2023-03-16 cs.RO cs.AI 57%

Robot Navigation in Risky, Crowded Environments: Understanding Human Preferences

Aamodh Suresh, Angelique Taylor, Laurel D. Riek, Sonia Martinez

专题命中视觉空间推理：planning(abstract)；分类 cs.AI

Comments Under review

2302.13307 2023-02-28 cs.RO cs.AI 57%

QCQP-Tunneling: Ellipsoidal Constrained Agent Navigation

Sanjeev Sharma

专题命中视觉空间推理：planning(abstract)；分类 cs.AI

Comments In proceedings of the 2nd IASTED International Conference on Robotics, 2011

Journal ref 2nd IASTED International Conference on Robotics, 2011

2302.02921 2023-02-07 cs.RO cs.LG 57%

Holistic Deep-Reinforcement-Learning-based Training of Autonomous Navigation Systems

Linh Kästner, Marvin Meusel, Teham Bhuiyan, Jens Lambrecht

专题命中视觉空间推理：planning(abstract)；分类 cs.LG

Comments 8 pages, 6 figures

2212.07651 2022-12-16 eess.IV cs.CV cs.LG 57%

Two-stage Contextual Transformer-based Convolutional Neural Network for Airway Extraction from CT Images

Yanan Wu, Shuiqing Zhao, Shouliang Qi, Jie Feng, Haowen Pang, Runsheng Chang, Long Bai, Mengqi Li, Shuyue Xia, Wei Qian, Hongliang Ren

专题命中视觉空间推理：planning(abstract)；分类 cs.LG

2207.11717 2022-11-21 cs.LG 57%

A Priority Map for Vision-and-Language Navigation with Trajectory Plans and Feature-Location Cues

Jason Armitage, Leonardo Impett, Rico Sennrich

专题命中视觉空间推理：planning(abstract)；分类 cs.LG

Comments Accepted to WACV 2023

2211.08467 2022-11-17 cs.AI 57%

Structured Exploration Through Instruction Enhancement for Object Navigation

Matthias Hutsebaut-Buysse, Kevin Mets, Tom De Schepper, Steven Latré

专题命中视觉空间推理：planning(abstract)；分类 cs.AI

Comments Paper accepted to the BNAIC/BeNeLearn 2022 conference

2210.08390 2022-10-18 cs.MA cs.AI cs.GT cs.RO 57%

SOCIALMAPF: Optimal and Efficient Multi-Agent Path Finding with Strategic Agents for Social Navigation

Rohan Chandra, Rahul Maligi, Arya Anantula, Joydeep Biswas

专题命中视觉空间推理：planning(abstract)；分类 cs.AI

Comments Full paper submission to R-AL. Shorter Blue Sky paper version available at AIHRI/2022/1016

2208.13628 2022-10-06 cs.CV cs.LG 57%

Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment

Mustafa Shukor, Guillaume Couairon, Matthieu Cord

专题命中视觉空间推理：reasoning(abstract)；分类 cs.LG

Comments BMVC 2022

2209.12723 2022-09-27 cs.CV cs.AI 57%

LOViS: Learning Orientation and Visual Signals for Vision and Language Navigation

Yue Zhang, Parisa Kordjamshidi

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI

2209.07000 2022-09-16 cs.CL 57%

VIPHY: Probing "Visible" Physical Commonsense Knowledge

Shikhar Singh, Ehsan Qasemi, Muhao Chen

专题命中视觉空间推理：reasoning(abstract)；分类 cs.CL

Comments In Progress (under review)

2209.02485 2022-09-07 cs.CV cs.CL 57%

Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors

Xi Wang, Gen Li, Yen-Ling Kuo, Muhammed Kocabas, Emre Aksan, Otmar Hilliges

专题命中视觉空间推理：reasoning(abstract)；分类 cs.CL

2206.01127 2022-09-07 cs.CV cs.CL 57%

VL-BEiT: Generative Vision-Language Pretraining

Hangbo Bao, Wenhui Wang, Li Dong, Furu Wei

专题命中视觉空间推理：reasoning(abstract)；分类 cs.CL

2208.10442 2022-09-01 cs.CV cs.CL 57%

Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks

Wenhui Wang, Hangbo Bao, Li Dong, Johan Bjorck, Zhiliang Peng, Qiang Liu, Kriti Aggarwal, Owais Khan Mohammed, Saksham Singhal, Subhojit Som, Furu Wei

专题命中视觉空间推理：reasoning(abstract)；分类 cs.CL

Comments 18 pages

2207.14287 2022-07-29 cs.CV cs.LG 57%

Depth Field Networks for Generalizable Multi-view Scene Representation

Vitor Guizilini, Igor Vasiljevic, Jiading Fang, Rares Ambrus, Greg Shakhnarovich, Matthew Walter, Adrien Gaidon

专题命中视觉空间推理：reasoning(abstract)；分类 cs.LG

Comments Accepted to ECCV 2022. Project page: https://sites.google.com/view/tri-define

2207.13738 2022-07-29 cs.CV cs.AI 57%

Break and Make: Interactive Structural Understanding Using LEGO Bricks

Aaron Walsman, Muru Zhang, Klemen Kotar, Karthik Desingh, Ali Farhadi, Dieter Fox

专题命中视觉空间推理：reasoning(abstract)；分类 cs.AI

Comments ECCV 2022. LTRON simulator and environment page: https://github.com/aaronwalsman/ltron. Training examples: https://github.com/aaronwalsman/ltron-torch-eccv22

2203.10157 2022-07-22 cs.CV cs.LG 57%

ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers

Jonáš Kulhánek, Erik Derner, Torsten Sattler, Robert Babuška

专题命中视觉空间推理：reasoning(abstract)；分类 cs.LG

Comments ECCV 2022 poster

2206.11610 2022-06-28 cs.CV cs.AI cs.RO 57%

1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)

Dong An, Zun Wang, Yangguang Li, Yi Wang, Yicong Hong, Yan Huang, Liang Wang, Jing Shao

专题命中视觉空间推理：planning(abstract)；分类 cs.AI

Comments Winner of the 2nd RxR-Habitat Competition @ CVPR2022

1. 视觉空间推理 3363 篇

MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model

Traffic-Domain Video Question Answering with Automatic Captioning

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

N$^2$M$^2$: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments

Learning Practically Feasible Policies for Online 3D Bin Packing

Controllable Text-to-Image Generation with GPT-4

KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language Models

Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation: A Comprehensive Review

3D Brainformer: 3D Fusion Transformer for Brain Tumor Segmentation

MProtoNet: A Case-Based Interpretable Model for Brain Tumor Classification with 3D Multi-parametric Magnetic Resonance Imaging

Boosting Cross-task Transferability of Adversarial Patches with Visual Relations

Visual Analytics of Neuron Vulnerability to Adversarial Attacks on Convolutional Neural Networks

Towards Models that Can See and Read

Robot Navigation in Risky, Crowded Environments: Understanding Human Preferences

QCQP-Tunneling: Ellipsoidal Constrained Agent Navigation

Holistic Deep-Reinforcement-Learning-based Training of Autonomous Navigation Systems

Two-stage Contextual Transformer-based Convolutional Neural Network for Airway Extraction from CT Images

A Priority Map for Vision-and-Language Navigation with Trajectory Plans and Feature-Location Cues

Structured Exploration Through Instruction Enhancement for Object Navigation

SOCIALMAPF: Optimal and Efficient Multi-Agent Path Finding with Strategic Agents for Social Navigation

Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment

LOViS: Learning Orientation and Visual Signals for Vision and Language Navigation

VIPHY: Probing "Visible" Physical Commonsense Knowledge

Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors

VL-BEiT: Generative Vision-Language Pretraining

Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks

Depth Field Networks for Generalizable Multi-view Scene Representation

Break and Make: Interactive Structural Understanding Using LEGO Bricks

ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers

1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)