https://github.com/MrZihan/NavRAG
공식 코드NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLM
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
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
Large Language Models Are Cross-Lingual Knowledge-Free Reasoners
Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
Measuring Systematic Generalization in Neural Proof Generation with Transformers
Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents
Teaching a Machine to Read Maps with Deep Reinforcement Learning
Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment
Who Relies More on World Knowledge and Bias for Syntactic Ambiguity Resolution: Humans or LLMs?
Priberam at MESINESP Multi-label Classification of Medical Texts Task
Nexus: A Lightweight and Scalable Multi-Agent Framework for Complex Tasks Automation
Improving Reliable Navigation under Uncertainty via Predictions Informed by Non-Local Information
ClaimCompare: A Data Pipeline for Evaluation of Novelty Destroying Patent Pairs
YoloTag: Vision-based Robust UAV Navigation with Fiducial Markers
DER: Dynamically Expandable Representation for Class Incremental Learning
Semantic RL with Action Grammars: Data-Efficient Learning of Hierarchical Task Abstractions
Lander.AI: Adaptive Landing Behavior Agent for Expertise in 3D Dynamic Platform Landings
Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learning
E-Scooter Rider Detection and Classification in Dense Urban Environments
Uncovering Autoregressive LLM Knowledge of Thematic Fit in Event Representation
INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
Run, skeleton, run: skeletal model in a physics-based simulation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.