Copertina

Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Yutian, Qiu, Yuheng, Li, Ruogu, Agha, Ali, Omidshafiei, Shayegan, Patrikar, Jay, Scherer, Sebastian
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Robotics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

GrndCtrl: Grounding World Models via Self-Supervised Reward Alignment
di: He, Haoyang, et al.
Pubblicazione: (2025)

MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry
di: Qiu, Yuheng, et al.
Pubblicazione: (2024)

VENTURA: Adapting Image Diffusion Models for Unified Task Conditioned Navigation
di: Zhang, Arthur, et al.
Pubblicazione: (2025)

AirIO: Learning Inertial Odometry with Enhanced IMU Feature Observability
di: Qiu, Yuheng, et al.
Pubblicazione: (2025)

FRAME: A Modular Framework for Autonomous Map Merging: Advancements in the Field
di: Stathoulopoulos, Nikolaos, et al.
Pubblicazione: (2024)

Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis
di: Hu, Yafei, et al.
Pubblicazione: (2023)

UFM: A Simple Path towards Unified Dense Correspondence with Flow
di: Zhang, Yuchen, et al.
Pubblicazione: (2025)

TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigation
di: Patel, Manthan, et al.
Pubblicazione: (2025)

Geometric Multi-Session Map Merging with Learned Local Descriptors
di: Ma, Yanlong, et al.
Pubblicazione: (2025)

SldprtNet: A Large-Scale Multimodal Dataset for CAD Generation in Language-Driven 3D Design
di: Li, Ruogu, et al.
Pubblicazione: (2026)

Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
di: Zheng, Shuhong, et al.
Pubblicazione: (2026)

Pixels-to-Graph: Real-time Integration of Building Information Models and Scene Graphs for Semantic-Geometric Human-Robot Understanding
di: Longo, Antonello, et al.
Pubblicazione: (2025)

Omni-Scan: Creating Visually-Accurate Digital Twin Object Models Using a Bimanual Robot with Handover and Gaussian Splat Merging
di: Qiu, Tianshuang, et al.
Pubblicazione: (2025)

CloSE: A Geometric Shape-Agnostic Cloth State Representation
di: Kamat, Jay, et al.
Pubblicazione: (2025)

Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered
di: Jabbour, Jason, et al.
Pubblicazione: (2025)

Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic Manipulation
di: Gao, Juntao, et al.
Pubblicazione: (2025)

Background Fades, Foreground Leads: Curriculum-Guided Background Pruning for Efficient Foreground-Centric Collaborative Perception
di: Wu, Yuheng, et al.
Pubblicazione: (2025)

Geometry-Informed Distance Candidate Selection for Adaptive Lightweight Omnidirectional Stereo Vision with Fisheye Images
di: Pulling, Conner, et al.
Pubblicazione: (2024)

Attention-Enhanced Cross-modal Localization Between 360 Images and Point Clouds
di: Zhao, Zhipeng, et al.
Pubblicazione: (2022)

World2Rules: A Neuro-Symbolic Framework for Learning World-Governing Safety Rules for Aviation
di: Wang, Haichuan, et al.
Pubblicazione: (2026)

AutoODD: Agentic Audits via Bayesian Red Teaming in Black-Box Models
di: Martin, Rebecca, et al.
Pubblicazione: (2025)

Global Symmetry and Orthogonal Transformations from Geometrical Moment $n$-tuples
di: Tahri, Omar
Pubblicazione: (2026)

Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation
di: Almuzairee, Abdulaziz, et al.
Pubblicazione: (2025)

RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration
di: Alama, Omar, et al.
Pubblicazione: (2025)

SyNeT: Synthetic Negatives for Traversability Learning
di: Kim, Bomena, et al.
Pubblicazione: (2026)

Evaluating Robustness of Visual Representations for Object Assembly Task Requiring Spatio-Geometrical Reasoning
di: Ku, Chahyon, et al.
Pubblicazione: (2023)

SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM
di: Keetha, Nikhil, et al.
Pubblicazione: (2023)

Pixel to Elevation: Learning to Predict Elevation Maps at Long Range using Images for Autonomous Offroad Navigation
di: Chung, Chanyoung, et al.
Pubblicazione: (2024)

NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigation
di: Zeng, Yiming, et al.
Pubblicazione: (2025)

RoadRunner -- Learning Traversability Estimation for Autonomous Off-road Driving
di: Frey, Jonas, et al.
Pubblicazione: (2024)

Efficient Visual Transformer by Learnable Token Merging
di: Wang, Yancheng, et al.
Pubblicazione: (2024)

VLM-Guided Visual Place Recognition for Planet-Scale Geo-Localization
di: Waheed, Sania, et al.
Pubblicazione: (2025)

Semantic and Feature Guided Uncertainty Quantification of Visual Localization for Autonomous Vehicles
di: Wu, Qiyuan, et al.
Pubblicazione: (2025)

Self-Supervised Geometry-Guided Initialization for Robust Monocular Visual Odometry
di: Kanai, Takayuki, et al.
Pubblicazione: (2024)

Efficient Self-Supervised Neuro-Analytic Visual Servoing for Real-time Quadrotor Control
di: Mocanu, Sebastian, et al.
Pubblicazione: (2025)

Perspective from a Higher Dimension: Can 3D Geometric Priors Help Visual Floorplan Localization?
di: Chen, Bolei, et al.
Pubblicazione: (2025)

Towards Perception-based Collision Avoidance for UAVs when Guiding the Visually Impaired
di: Raj, Suman, et al.
Pubblicazione: (2025)

VDT-Auto: End-to-end Autonomous Driving with VLM-Guided Diffusion Transformers
di: Guo, Ziang, et al.
Pubblicazione: (2025)

FIReStereo: Forest InfraRed Stereo Dataset for UAS Depth Perception in Visually Degraded Environments
di: Dhrafani, Devansh, et al.
Pubblicazione: (2024)

Exploring Object-Aware Attention Guided Frame Association for RGB-D SLAM
di: Caglayan, Ali, et al.
Pubblicazione: (2025)