大模型推理能力 - arXivDaily 专题

2406.00307 2024-11-04 cs.CV 50%

HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model

Khoa Vo, Thinh Phan, Kashu Yamazaki, Minh Tran, Ngan Le

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted to NeurIPS 2024

2405.00552 2024-10-31 cs.RO cs.HC 50%

Long-Term Human Trajectory Prediction using 3D Dynamic Scene Graphs

Nicolas Gorlo, Lukas Schmid, Luca Carlone

专题命中视觉空间推理：planning(abstract)

Comments 8 pages, 6 figures. Accepted at IEEE Robotics and Automation Letters (RA-L). Code released at: https://github.com/MIT-SPARK/LP2

Journal ref IEEE Robotics and Automation Letters, vol. 9, no. 12, pp. 10978-10985, Dec. 2024

2410.21037 2024-10-29 cs.RO 50%

Exploring the Reliability of Foundation Model-Based Frontier Selection in Zero-Shot Object Goal Navigation

Shuaihang Yuan, Halil Utku Unlu, Hao Huang, Congcong Wen, Anthony Tzes, Yi Fang

专题命中视觉空间推理：reasoning(abstract)

Comments 17 pages, 5 figures, 3 tables

2410.18962 2024-10-25 cs.CV 50%

Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction

Junyi Chen, Di Huang, Weicai Ye, Wanli Ouyang, Tong He

专题命中视觉空间推理：reasoning(abstract)

2410.15496 2024-10-22 cs.CV 50%

Taming Mambas for Voxel Level 3D Medical Image Segmentation

Luca Lumetti, Vittorio Pipoli, Kevin Marchesini, Elisa Ficarra, Costantino Grana, Federico Bolelli

专题命中视觉空间推理：reasoning(abstract)

2409.02253 2024-10-17 cs.CV 50%

How to Determine the Preferred Image Distribution of a Black-Box Vision-Language Model?

Saeid Asgari Taghanaki, Joseph Lambourne, Alana Mongkhounsavath

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted to NeurIPS 2024, Safe Generative AI

2404.19438 2024-10-15 cs.NE 50%

Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction

Guobin Shen, Dongcheng Zhao, Xiang He, Linghao Feng, Yiting Dong, Jihang Wang, Qian Zhang, Yi Zeng

专题命中视觉空间推理：reasoning(abstract)

2410.04302 2024-10-08 cs.RO 50%

PANav: Toward Privacy-Aware Robot Navigation via Vision-Language Models

Bangguo Yu, Hamidreza Kasaei, Ming Cao

专题命中视觉空间推理：planning(abstract)

Comments 7 pages, 6 figures, conference

2410.01925 2024-10-04 cs.RO 50%

Topological mapping for traversability-aware long-range navigation in off-road terrain

Jean-François Tremblay, Julie Alhosh, Louis Petit, Faraz Lotfi, Lara Landauro, David Meger

专题命中视觉空间推理：planning(abstract)

2409.19899 2024-10-01 cs.CV 50%

OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection

Changsheng Lu, Zheyuan Liu, Piotr Koniusz

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted by ECCV 2024

2409.19459 2024-10-01 cs.RO cs.CV 50%

Language-guided Robust Navigation for Mobile Robots in Dynamically-changing Environments

Cody Simons, Zhichao Liu, Brandon Marcus, Amit K. Roy-Chowdhury, Konstantinos Karydis

专题命中视觉空间推理：planning(abstract)

2409.16723 2024-09-27 cs.CV 50%

EAGLE: Towards Efficient Arbitrary Referring Visual Prompts Comprehension for Multimodal Large Language Models

Jiacheng Zhang, Yang Jiao, Shaoxiang Chen, Jingjing Chen, Yu-Gang Jiang

专题命中视觉空间推理：reasoning(abstract)

2409.10906 2024-09-18 cs.RO 50%

Multi-Floor Zero-Shot Object Navigation Policy

Lingfeng Zhang, Hao Wang, Erjia Xiao, Xinyao Zhang, Qiang Zhang, Zixuan Jiang, Renjing Xu

专题命中视觉空间推理：reasoning(abstract)

2408.16662 2024-09-17 cs.CV 50%

Space3D-Bench: Spatial 3D Question Answering Benchmark

Emilia Szymanska, Mihai Dusmanu, Jan-Willem Buurlage, Mahdi Rad, Marc Pollefeys

专题命中视觉空间推理：reasoning(abstract)

2407.14279 2024-09-17 cs.CV 50%

OpenSU3D: Open World 3D Scene Understanding using Foundation Models

Rafay Mohiuddin, Sai Manoj Prakhya, Fiona Collins, Ziyuan Liu, André Borrmann

专题命中视觉空间推理：reasoning(abstract)

Comments Project Page: https://opensu3d.github.io/

2408.12093 2024-09-13 cs.RO cs.CV 50%

LLM-enhanced Scene Graph Learning for Household Rearrangement

Wenhao Li, Zhiyuan Yu, Qijin She, Zhinan Yu, Yuqing Lan, Chenyang Zhu, Ruizhen Hu, Kai Xu

专题命中视觉空间推理：planning(abstract)

Comments SIGGRAPH ASIA 2024 conference accepted

2309.06635 2024-09-12 cs.RO 50%

Collaborative Dynamic 3D Scene Graphs for Automated Driving

Elias Greve, Martin Büchner, Niclas Vödisch, Wolfram Burgard, Abhinav Valada

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted for "IEEE International Conference on Robotics and Automation (ICRA) 2024"

Journal ref IEEE International Conference on Robotics and Automation, 2024, pp. 11118-11124

2409.05593 2024-09-10 cs.RO 50%

StratXplore: Strategic Novelty-seeking and Instruction-aligned Exploration for Vision and Language Navigation

Muraleekrishna Gopinathan, Jumana Abu-Khalaf, David Suter, Martin Masek

专题命中视觉空间推理：planning(abstract)

2409.04214 2024-09-10 cs.CV 50%

Diagram Formalization Enhanced Multi-Modal Geometry Problem Solver

Zeren Zhang, Jo-Ku Cheng, Jingyang Deng, Lu Tian, Jinwen Ma, Ziran Qin, Xiaokai Zhang, Na Zhu, Tuo Leng

专题命中视觉空间推理：reasoning(abstract)

2303.16341 2024-09-10 cs.CV 50%

Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding

Yuanhao Xiong, Long Zhao, Boqing Gong, Ming-Hsuan Yang, Florian Schroff, Ting Liu, Cho-Jui Hsieh, Liangzhe Yuan

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted to ICLR2024, see https://openreview.net/forum?id=5dlfiJIXoh for more details

2409.03966 2024-09-09 cs.RO 50%

Automating Robot Failure Recovery Using Vision-Language Models With Optimized Prompts

Hongyi Chen, Yunchao Yao, Ruixuan Liu, Changliu Liu, Jeffrey Ichnowski

专题命中视觉空间推理：reasoning(abstract)

2407.02392 2024-08-29 cs.CV 50%

TokenPacker: Efficient Visual Projector for Multimodal LLM

Wentong Li, Yuqian Yuan, Jian Liu, Dongqi Tang, Song Wang, Jie Qin, Jianke Zhu, Lei Zhang

专题命中视觉空间推理：reasoning(abstract)

Comments 16 pages, Codes:https://github.com/CircleRadon/TokenPacker

2403.08605 2024-08-26 cs.RO 50%

Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation

Daniel Honerkamp, Martin Büchner, Fabien Despinoy, Tim Welschehold, Abhinav Valada

专题命中视觉空间推理：reasoning(abstract)

Comments Project website: http://moma-llm.cs.uni-freiburg.de, accepted at RA-L

2408.11464 2024-08-22 cs.CV 50%

MambaOcc: Visual State Space Model for BEV-based Occupancy Prediction with Local Adaptive Reordering

Yonglin Tian, Songlin Bai, Zhiyao Luo, Yutong Wang, Yisheng Lv, Fei-Yue Wang

专题命中视觉空间推理：planning(abstract)

2408.06926 2024-08-14 cs.CV 50%

SceneGPT: A Language Model for 3D Scene Understanding

Shivam Chandhok

专题命中视觉空间推理：reasoning(abstract)

Comments UBC Report

2309.00616 2024-08-13 cs.CV 50%

OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation

Zhening Huang, Xiaoyang Wu, Xi Chen, Hengshuang Zhao, Lei Zhu, Joan Lasenby

专题命中视觉空间推理：reasoning(abstract)

Comments ECCV 2024. Project page: https://zheninghuang.github.io/OpenIns3D/

2408.03312 2024-08-07 cs.CV 50%

MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation

Xiaofeng Mao, Zhengkai Jiang, Qilin Wang, Chencan Fu, Jiangning Zhang, Jiafu Wu, Yabiao Wang, Chengjie Wang, Wei Li, Mingmin Chi

专题命中视觉空间推理：reasoning(abstract)

2408.02231 2024-08-06 cs.CV 50%

REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models

Agneet Chatterjee, Yiran Luo, Tejas Gokhale, Yezhou Yang, Chitta Baral

专题命中视觉空间推理：reasoning(abstract)

Comments Accepted to ECCV 2024. Project Page : https://agneetchatterjee.com/revision/

2404.17672 2024-08-06 cs.CV cs.GR 50%

BlenderAlchemy: Editing 3D Graphics with Vision-Language Models

Ian Huang, Guandao Yang, Leonidas Guibas

专题命中视觉空间推理：reasoning(abstract)

2407.21333 2024-08-01 cs.CV 50%

Chat2Layout: Interactive 3D Furniture Layout with a Multimodal LLM

Can Wang, Hongliang Zhong, Menglei Chai, Mingming He, Dongdong Chen, Jing Liao

专题命中视觉空间推理：reasoning(abstract)

Comments Main paper with supplemental materials

1. 视觉空间推理 3363 篇

HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model

Long-Term Human Trajectory Prediction using 3D Dynamic Scene Graphs

Exploring the Reliability of Foundation Model-Based Frontier Selection in Zero-Shot Object Goal Navigation

Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction

Taming Mambas for Voxel Level 3D Medical Image Segmentation

How to Determine the Preferred Image Distribution of a Black-Box Vision-Language Model?

Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction

PANav: Toward Privacy-Aware Robot Navigation via Vision-Language Models

Topological mapping for traversability-aware long-range navigation in off-road terrain

OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection

Language-guided Robust Navigation for Mobile Robots in Dynamically-changing Environments

EAGLE: Towards Efficient Arbitrary Referring Visual Prompts Comprehension for Multimodal Large Language Models

Multi-Floor Zero-Shot Object Navigation Policy

Space3D-Bench: Spatial 3D Question Answering Benchmark

OpenSU3D: Open World 3D Scene Understanding using Foundation Models

LLM-enhanced Scene Graph Learning for Household Rearrangement

Collaborative Dynamic 3D Scene Graphs for Automated Driving

StratXplore: Strategic Novelty-seeking and Instruction-aligned Exploration for Vision and Language Navigation

Diagram Formalization Enhanced Multi-Modal Geometry Problem Solver

Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding

Automating Robot Failure Recovery Using Vision-Language Models With Optimized Prompts

TokenPacker: Efficient Visual Projector for Multimodal LLM

Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation

MambaOcc: Visual State Space Model for BEV-based Occupancy Prediction with Local Adaptive Reordering

SceneGPT: A Language Model for 3D Scene Understanding

OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation

MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation

REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models

BlenderAlchemy: Editing 3D Graphics with Vision-Language Models

Chat2Layout: Interactive 3D Furniture Layout with a Multimodal LLM