大模型推理能力 - arXivDaily 专题

2401.06437 2024-01-17 cs.GR cs.AI cs.CL 62%

3D-PreMise: Can Large Language Models Generate 3D Shapes with Sharp Features and Parametric Control?

Zeqing Yuan, Haoxuan Lan, Qiang Zou, Junbo Zhao

专题命中视觉空间推理：self-correction(abstract)；分类 cs.CL、cs.AI

Comments 10 pages, 6 figures

2311.05332 2023-11-29 cs.CV cs.AI cs.CL cs.RO 62%

On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving

Licheng Wen, Xuemeng Yang, Daocheng Fu, Xiaofeng Wang, Pinlong Cai, Xin Li, Tao Ma, Yingxuan Li, Linran Xu, Dengke Shang, Zheng Zhu, Shaoyan Sun, Yeqi Bai, Xinyu Cai, Min Dou, Shuanglu Hu, Botian Shi, Yu Qiao

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

2311.16091 2023-11-28 cs.RO cs.AI cs.CV cs.LG cs.MA 62%

Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimation

Jiachen Li, David Isele, Kanghoon Lee, Jinkyoo Park, Kikuo Fujimura, Mykel J. Kochenderfer

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

Comments 18 pages, 14 figures

2311.16038 2023-11-28 cs.CV cs.AI cs.LG 62%

OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving

Wenzhao Zheng, Weiliang Chen, Yuanhui Huang, Borui Zhang, Yueqi Duan, Jiwen Lu

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

Comments Code is available at: https://github.com/wzzheng/OccWorld

2311.12820 2023-11-23 cs.CV cs.AI cs.CL eess.IV 62%

MSG-BART: Multi-granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-grounded Dialogue Generation

Hongcheng Liu, Zhe Chen, Hui Li, Pingjie Wang, Yanfeng Wang, Yu Wang

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

Comments 5 pages,3 figures

2311.10983 2023-11-21 cs.CV cs.AI cs.LG 62%

Multiple View Geometry Transformers for 3D Human Pose Estimation

Ziwei Liao, Jialiang Zhu, Chunyu Wang, Han Hu, Steven L. Waslander

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

Comments 14 pages, 8 figures

2303.12513 2023-11-07 cs.CV cs.CL cs.LG 62%

Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding

Morris Alper, Michael Fiman, Hadar Averbuch-Elor

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

Comments Accepted to CVPR 2023. Project webpage: https://isbertblind.github.io/

2306.17817 2023-10-23 cs.RO cs.AI cs.LG 62%

Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation

Theophile Gervet, Zhou Xian, Nikolaos Gkanatsios, Katerina Fragkiadaki

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

2306.10474 2023-10-16 cs.RO cs.AI cs.CV cs.LG 62%

A Universal Semantic-Geometric Representation for Robotic Manipulation

Tong Zhang, Yingdong Hu, Hanchen Cui, Hang Zhao, Yang Gao

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

Comments CoRL 2023. Project website: https://semantic-geometric-representation.github.io

2310.02172 2023-10-04 cs.HC cs.AI cs.LG 62%

Lyfe Agents: Generative agents for low-cost real-time social interactions

Zhao Kaiya, Michelangelo Naim, Jovana Kondic, Manuel Cortes, Jiaxin Ge, Shuying Luo, Guangyu Robert Yang, Andrew Ahn

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

2309.11382 2023-09-21 cs.RO cs.AI cs.CL cs.CV 62%

Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions

Yuxing Long, Xiaoqi Li, Wenzhe Cai, Hao Dong

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

Comments Submitted to ICRA 2024

2211.06407 2023-07-14 cs.RO cs.AI cs.LG 62%

Control Transformer: Robot Navigation in Unknown Environments through PRM-Guided Return-Conditioned Sequence Modeling

Daniel Lawson, Ahmed H. Qureshi

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

2301.13166 2023-07-07 cs.AI cs.CV cs.LG cs.RO 62%

ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation

Kaiwen Zhou, Kaizhi Zheng, Connor Pryor, Yilin Shen, Hongxia Jin, Lise Getoor, Xin Eric Wang

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

2306.14650 2023-06-29 cs.AI cs.CV cs.LG cs.SC 62%

PhD Thesis: Exploring the role of (self-)attention in cognitive and computer vision architecture

Mohit Vaishnav

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

Comments PhD Thesis, 152 pages, 32 figures, 6 tables

2306.06799 2023-06-13 cs.RO cs.AI cs.LG 62%

On the Efficacy of 3D Point Cloud Reinforcement Learning

Zhan Ling, Yunchao Yao, Xuanlin Li, Hao Su

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

2303.14548 2023-04-10 cs.CV cs.AI cs.LG cs.RO 62%

Viewpoint Equivariance for Multi-View 3D Object Detection

Dian Chen, Jie Li, Vitor Guizilini, Rares Ambrus, Adrien Gaidon

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

Comments 11 pages, 4 figures; accepted to CVPR 2023

2302.14451 2023-03-01 cs.LG cs.AI 62%

Hierarchical Reinforcement Learning in Complex 3D Environments

Bernardo Avila Pires, Feryal Behbahani, Hubert Soyer, Kyriacos Nikiforou, Thomas Keck, Satinder Singh

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

2207.14024 2022-12-08 cs.CV cs.AI cs.LG cs.RO 62%

Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer

Hao Shao, Letian Wang, RuoBing Chen, Hongsheng Li, Yu Liu

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

Comments Accepted at CoRL 2022

2211.11153 2022-11-22 cs.LG cs.CL cs.CV 62%

Unifying Vision-Language Representation Space with Single-tower Transformer

Jiho Jang, Chaerin Kong, Donghyeon Jeon, Seonhoon Kim, Nojun Kwak

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

Comments AAAI 2023, 11 pages

1712.05474 2022-08-29 cs.CV cs.AI cs.LG 62%

AI2-THOR: An Interactive 3D Environment for Visual AI

Eric Kolve, Roozbeh Mottaghi, Winson Han, Eli VanderBilt, Luca Weihs, Alvaro Herrasti, Matt Deitke, Kiana Ehsani, Daniel Gordon, Yuke Zhu, Aniruddha Kembhavi, Abhinav Gupta, Ali Farhadi

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

2206.12675 2022-06-28 cs.CV cs.AI cs.LG 62%

Learning to Infer 3D Shape Programs with Differentiable Renderer

Yichao Liang

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

Comments Technical report written in 2020; 10 pages, 5 figures. arXiv admin note: substantial text overlap with arXiv:1901.02875 by other authors

2206.03970 2022-06-13 cs.CV cs.AI cs.LG cs.RO 62%

Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting

DiJia Su, Bertrand Douillard, Rami Al-Rfou, Cheolho Park, Benjamin Sapp

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

Comments Accepted at ICRA 2022

2108.05713 2022-06-03 cs.RO cs.AI cs.CV cs.LG 62%

Towards real-world navigation with deep differentiable planners

Shu Ishida, João F. Henriques

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

Comments Published in CVPR 2022 (Conference on Computer Vision and Pattern Recognition)

2112.08656 2022-05-06 cs.CL cs.AI 62%

DREAM: Improving Situational QA by First Elaborating the Situation

Yuling Gu, Bhavana Dalvi Mishra, Peter Clark

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

Comments to be published in NAACL 2022

2103.16561 2022-05-05 cs.CV cs.AI cs.CL 62%

Diagnosing Vision-and-Language Navigation: What Really Matters

Wanrong Zhu, Yuankai Qi, Pradyumna Narayana, Kazoo Sone, Sugato Basu, Xin Eric Wang, Qi Wu, Miguel Eckstein, William Yang Wang

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

Comments NAACL 2022

2202.06481 2022-04-29 cs.LG cs.AI 62%

A Survey on Machine Learning Approaches for Modelling Intuitive Physics

Jiafei Duan, Arijit Dasgupta, Jason Fischer, Cheston Tan

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

Comments Paper accepted at IJCAI 2022 (Survey Track)

2111.13152 2022-03-30 cs.CV cs.AI cs.GR cs.LG cs.RO 62%

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

Mehdi S. M. Sajjadi, Henning Meyer, Etienne Pot, Urs Bergmann, Klaus Greff, Noha Radwan, Suhani Vora, Mario Lucic, Daniel Duckworth, Alexey Dosovitskiy, Jakob Uszkoreit, Thomas Funkhouser, Andrea Tagliasacchi

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

Comments Accepted to CVPR 2022, Project website: https://srt-paper.github.io/

Journal ref CVPR 2022

2202.09277 2022-03-29 cs.CV cs.AI cs.LG 62%

(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering

Anoop Cherian, Chiori Hori, Tim K. Marks, Jonathan Le Roux

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

Comments Accepted at AAAI 2022 (Oral)

2201.07050 2022-02-15 cs.AI cs.LG 62%

Combining Fast and Slow Thinking for Human-like and Efficient Navigation in Constrained Environments

Marianna B. Ganapini, Murray Campbell, Francesco Fabiano, Lior Horesh, Jon Lenchner, Andrea Loreggia, Nicholas Mattei, Taher Rahgooy, Francesca Rossi, Biplav Srivastava, Brent Venable

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

Comments arXiv admin note: substantial text overlap with arXiv:2110.01834

2202.01334 2022-02-04 cs.LG cs.AI 62%

Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization

Dianbo Liu, Alex Lamb, Xu Ji, Pascal Notsawo, Mike Mozer, Yoshua Bengio, Kenji Kawaguchi

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

1. 视觉空间推理 3387 篇

3D-PreMise: Can Large Language Models Generate 3D Shapes with Sharp Features and Parametric Control?

On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving

Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimation

OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving

MSG-BART: Multi-granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-grounded Dialogue Generation

Multiple View Geometry Transformers for 3D Human Pose Estimation

Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding

Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation

A Universal Semantic-Geometric Representation for Robotic Manipulation

Lyfe Agents: Generative agents for low-cost real-time social interactions

Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions

Control Transformer: Robot Navigation in Unknown Environments through PRM-Guided Return-Conditioned Sequence Modeling

ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation

PhD Thesis: Exploring the role of (self-)attention in cognitive and computer vision architecture

On the Efficacy of 3D Point Cloud Reinforcement Learning

Viewpoint Equivariance for Multi-View 3D Object Detection

Hierarchical Reinforcement Learning in Complex 3D Environments

Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer

Unifying Vision-Language Representation Space with Single-tower Transformer

AI2-THOR: An Interactive 3D Environment for Visual AI

Learning to Infer 3D Shape Programs with Differentiable Renderer

Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting

Towards real-world navigation with deep differentiable planners

DREAM: Improving Situational QA by First Elaborating the Situation

Diagnosing Vision-and-Language Navigation: What Really Matters

A Survey on Machine Learning Approaches for Modelling Intuitive Physics

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering

Combining Fast and Slow Thinking for Human-like and Efficient Navigation in Constrained Environments

Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization