https://github.com/3dcompat200/3dcompat200
공식 코드3DCoMPaT200: Language-Grounded Compositional Understanding of Parts and Materials of 3D Shapes
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
3DCoMPaT200: Language-Grounded Compositional Understanding of Parts and Materials of 3D Shapes
Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks
DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation
Map-based Modular Approach for Zero-shot Embodied Question Answering
SABER: Data-Driven Motion Planner for Autonomously Navigating Heterogeneous Robots
AI-Driven Relocation Tracking in Dynamic Kitchen Environments
Evaluating Robustness over High Level Driving Instruction for Autonomous Driving
Neural Brain: A Neuroscience-inspired Framework for Embodied Agents
Towards Data-centric Graph Machine Learning: Review and Outlook
Integrating Deep Reinforcement Learning with Model-based Path Planners for Automated Driving
Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks
Variable Rate Deep Image Compression with Modulated Autoencoder
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Image Captioning as an Assistive Technology: Lessons Learned from VizWiz 2020 Challenge
BAA-NGP: Bundle-Adjusting Accelerated Neural Graphics Primitives
Belief Aided Navigation using Bayesian Reinforcement Learning for Avoiding Humans in Blind Spots
Navigating Data Heterogeneity in Federated Learning A Semi-Supervised Federated Object Detection
DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
CoNav: A Benchmark for Human-Centered Collaborative Navigation
Modeling the Dynamics of Growth in Master-Planned Communities
Neighbor-view Enhanced Model for Vision and Language Navigation
Vector Field-based Collision Avoidance for Moving Obstacles with Time-Varying Elliptical Shape
Versatile modular neural locomotion control with fast learning
NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLM
Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.