Cover Image

Theia: Distilling Diverse Vision Foundation Models for Robot Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shang, Jinghuan, Schmeckpeper, Karl, May, Brandon B., Minniti, Maria Vittoria, Kelestemur, Tarik, Watkins, David, Herlant, Laura
Format:	Preprint
Published:	2024
Subjects:	Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Sceniris: A Fast Procedural Scene Generation Framework
by: Shang, Jinghuan, et al.
Published: (2025)

Real-is-Sim: Bridging the Sim-to-Real Gap with a Dynamic Digital Twin
by: Abou-Chakra, Jad, et al.
Published: (2025)

Learning Equivariant Neural-Augmented Object Dynamics From Few Interactions
by: Orozco, Sergio, et al.
Published: (2026)

AnyTask: an Automated Task and Data Generation Framework for Advancing Sim-to-Real Policy Learning
by: Gong, Ran, et al.
Published: (2025)

SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning
by: Schroeder, Philip, et al.
Published: (2026)

CuriousBot: Interactive Mobile Exploration via Actionable 3D Relational Object Graph
by: Wang, Yixuan, et al.
Published: (2025)

Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning
by: Li, Xiang, et al.
Published: (2023)

GenDP: 3D Semantic Fields for Category-Level Generalizable Diffusion Policy
by: Wang, Yixuan, et al.
Published: (2024)

On-Robot Reinforcement Learning with Goal-Contrastive Rewards
by: Biza, Ondrej, et al.
Published: (2024)

LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
by: Li, Xiang, et al.
Published: (2024)

Reinforcement Learning-Based Monocular Vision Approach for Autonomous UAV Landing
by: Houichime, Tarik, et al.
Published: (2025)

D$^3$Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangement
by: Wang, Yixuan, et al.
Published: (2023)

Vision Foundation Models for Domain Generalisable Cross-View Localisation in Planetary Ground-Aerial Robotic Teams
by: Holden, Lachlan, et al.
Published: (2026)

RepSAM: Bridging Foundation Models to Robotic Vision via Representation-Guided Adaptation
by: Chu, Wenhui
Published: (2026)

ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments with Vision Foundation Models
by: Zhang, Ying, et al.
Published: (2025)

DeFM: Learning Foundation Representations from Depth for Robotics
by: Patel, Manthan, et al.
Published: (2026)

VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing
by: Wang, Yixiao, et al.
Published: (2025)

LIDEA: Human-to-Robot Imitation Learning via Implicit Feature Distillation and Explicit Geometry Alignment
by: Xu, Yifu, et al.
Published: (2026)

ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models
by: Ye, Wencheng, et al.
Published: (2025)

Geometry Meets Vision: Revisiting Pretrained Semantics in Distilled Fields
by: Mei, Zhiting, et al.
Published: (2025)

ViTA-Seg: Vision Transformer for Amodal Segmentation in Robotics
by: Caramia, Donato, et al.
Published: (2025)

General Flow as Foundation Affordance for Scalable Robot Learning
by: Yuan, Chengbo, et al.
Published: (2024)

A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning
by: Wen, Xin, et al.
Published: (2025)

Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision
by: Han, Xiaofeng, et al.
Published: (2025)

The Role of Predictive Uncertainty and Diversity in Embodied AI and Robot Learning
by: Senanayake, Ransalu
Published: (2024)

Towards an Accurate and Effective Robot Vision (The Problem of Topological Localization for Mobile Robots)
by: Boros, Emanuela
Published: (2025)

Mobi-$π$: Mobilizing Your Robot Learning Policy
by: Yang, Jingyun, et al.
Published: (2025)

ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models
by: Dey, Sombit, et al.
Published: (2024)

Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation
by: Liao, Yue, et al.
Published: (2025)

Feasibility of Indoor Frame-Wise Lidar Semantic Segmentation via Distillation from Visual Foundation Model
by: Wu, Haiyang, et al.
Published: (2026)

Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models
by: Yang, Yurou, et al.
Published: (2026)

Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation
by: Xing, Youguang, et al.
Published: (2025)

FD-VLA: Force-Distilled Vision-Language-Action Model for Contact-Rich Manipulation
by: Zhao, Ruiteng, et al.
Published: (2026)

FlexVLN: Flexible Adaptation for Diverse Vision-and-Language Navigation Tasks
by: Zhang, Siqi, et al.
Published: (2025)

Language-guided Robust Navigation for Mobile Robots in Dynamically-changing Environments
by: Simons, Cody, et al.
Published: (2024)

RobotPan: A 360$^\circ$ Surround-View Robotic Vision System for Embodied Perception
by: Ma, Jiahao, et al.
Published: (2026)

The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents
by: Yeke, Doguhan, et al.
Published: (2026)

Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
by: Guruprasad, Pranav, et al.
Published: (2024)

LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning
by: Niu, Dantong, et al.
Published: (2024)

Task-Aware Scanning Parameter Configuration for Robotic Inspection Using Vision Language Embeddings and Hyperdimensional Computing
by: Chen, Zhiling, et al.
Published: (2026)