Papers with Code 아카이브
Minecraft
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Matrix-Game: Interactive World Foundation Model
TransDreamerV3: Implanting Transformer In DreamerV3
Optimus-3: Towards Generalist Multimodal Minecraft Agents with Scalable Task Experts
Toward Memory-Aided World Models: Benchmarking via Spatial Consistency
MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents
Long-Context State-Space Video World Models
Knowledge Retrieval in LLM Gaming: A Shift from Entity-Centric to Goal-Oriented Graphs
BAR: A Backward Reasoning based Agent for Complex Minecraft Tasks
PLAICraft: Large-Scale Time-Aligned Vision-Speech-Action Dataset for Embodied AI
BeliefNest: A Joint Action Simulator for Embodied Agents with Theory of Mind
D3HRL: A Distributed Hierarchical Reinforcement Learning Approach Based on Causal Discovery and Spurious Correlation Detection
Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning
WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft
AssistanceZero: Scalably Solving Assistance Games
Enabling Rapid Shared Human-AI Mental Model Alignment via the After-Action Review
BugCraft: End-to-End Crash Bug Reproduction Using LLM Agents in Minecraft
JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse
Uncertainty in Action: Confidence Elicitation in Embodied Agents
Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework
Open-World Skill Discovery from Unsegmented Demonstrations
Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems
ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignment
Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy
GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks
Integrating Reinforcement Learning, Action Model Learning, and Numeric Planning for Tackling Complex Tasks
MINDSTORES: Memory-Informed Neural Decision Synthesis for Task-Oriented Reinforcement in Embodied Systems
BAP v2: An Enhanced Task Framework for Instruction Following in Minecraft Dialogues
GameFactory: Creating New Games with Generative Interactive Videos
Plancraft: an evaluation dataset for planning with LLM agents
MineStudio: A Streamlined Package for Minecraft AI Agent Development
TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft
Optimizing Latent Goal by Learning from Trajectory Preference
STEVE-Audio: Expanding the Goal Conditioning Modalities of Embodied Agents in Minecraft
APT: Architectural Planning and Text-to-Blueprint Construction Using Large Language Models for Open-World Agents
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.