Papers with Code 아카이브
Vision-Language Navigation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 1
- 보존된 평가 기록
- 3
Vision-language navigation (VLN) is the task of navigating an embodied agent to carry out natural language instructions inside real 3D environments.
<span style="color:grey; opacity: 0.6">( Image credit: Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation
Survey on Vision-Language-Action Models
Probing a Vision-Language-Action Model for Symbolic States and Integration into a Cognitive Architecture
VLA-Cache: Towards Efficient Vision-Language-Action Model via Adaptive Token Caching in Robotic Manipulation
VL-Nav: Real-time Vision-Language Navigation with Spatial Reasoning
UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent
Improving Vision-Language-Action Model with Online Reinforcement Learning
FAST: Efficient Action Tokenization for Vision-Language-Action Models
UAV-VLA: Vision-Language-Action System for Large Scale Aerial Mission Generation
Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding
Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches
VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks
QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning
RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation
Towards Generalist Robot Policies: What Matters in Building Vision-Language-Action Models
NAVCON: A Cognitively Inspired and Linguistically Grounded Corpus for Vision and Language Navigation
Modality-Driven Design for Multi-Step Dexterous Manipulation: Insights from Neuroscience
Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments
TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method
Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
Agent Journey Beyond RGB: Unveiling Hybrid Semantic-Spatial Environmental Representations for Vision-and-Language Navigation
doScenes: An Autonomous Driving Dataset with Natural Language Instruction for Human Interaction and Vision-Language Navigation
NaVILA: Legged Robot Vision-Language-Action Model for Navigation
Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control
CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-World
GRAPE: Generalizing Robot Policy via Preference Alignment
ShowUI: One Vision-Language-Action Model for GUI Visual Agent
UnitedVLN: Generalizable Gaussian Splatting for Continuous Vision-Language Navigation
Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics
Zero-shot Object-Centric Instruction Following: Integrating Foundation Models with Traditional Navigation
DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.