SOTAVerified

Minecraft

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 236 papers

TitleStatusHype
Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent—0
IDAT: A Multi-Modal Dataset and Toolkit for Building and Evaluating Interactive Task-Solving AgentsCode1
Craftium: An Extensible Framework for Creating Reinforcement Learning EnvironmentsCode2
Collaborative Quest Completion with LLM-driven Non-Player Characters in Minecraft—0
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents—0
Nebula: A discourse aware Minecraft Builder—0
Retrieval-Augmented Code Generation for Situated Action Generation: A Case Study on Minecraft—0
STEVE Series: Step-by-Step Construction of Agent Systems in Minecraft—0
3D Building Generation in Minecraft via Large Language ModelsCode0
World Models with Hints of Large Language Models for Goal Achieving—0
VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in MinecraftCode2
The Embodied World Model Based on LLM with Visual Information and Prediction-Oriented Prompts—0
Crafting a Pogo Stick in Minecraft with Heuristic Search (Extended Abstract)Code0
LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence—0
Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning—0
Luban: Building Open-Ended Creative Agents via Autonomous Embodied Verification—0
DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft—0
MineLand: Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical NeedsCode2
MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World ControlCode2
Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation—0
Your device may know you better than you know yourself -- continuous authentication on novel dataset using machine learning—0
Playing NetHack with LLMs: Potential & Limitations as Zero-Shot AgentsCode1
RL-GPT: Integrating Reinforcement Learning and Code-as-policy—0
Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement LearningCode3
Large Language Models as Minecraft Agents—0
Improving Agent Interactions in Virtual Environments with Language Models—0
Minecraft-ify: Minecraft Style Image Generation with Text-guided Image Editing for In-Game Application—0
S-Agents: Self-organizing Agents in Open-ended EnvironmentsCode1
Vision-Language Models Provide Promptable Representations for Reinforcement Learning—0
ReGAL: Refactoring Programs to Discover Generalizable AbstractionsCode1
Zero-shot Imitation Policy via Search in Demonstration Dataset—0
MinePlanner: A Benchmark for Long-Horizon Planning in Large Minecraft WorldsCode1
MineObserver 2.0: A Deep Learning & In-Game Framework for Assessing Natural Language Descriptions of Minecraft Imagery—0
Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft—0
Learning adaptive planning representations with natural language guidance—0
MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active PerceptionCode0
Creative Agents: Empowering Agents with Imagination for Creative TasksCode1
BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy TasksCode1
Visual Encoders for Data-Efficient Imitation Learning in Modern Video Games—0
Meta-Diversity Search in Complex Systems, A Recipe for Artificial Open-Endedness ?—0
See and Think: Embodied Agent in Virtual Environment—0
JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models—0
Active Reasoning in an Open-World Environment—0
Convolutional State Space Models for Long-Range Spatiotemporal ModelingCode1
Probabilistic Modeling of Human Teams to Infer False Beliefs—0
Progressively Efficient Learning—0
LLaMA Rider: Spurring Large Language Models to Explore the Open World—0
GROOT: Learning to Follow Instructions by Watching Gameplay Videos—0
Towards Evaluating Generalist Agents: An Automated Benchmark in Open WorldCode1
Octopus: Embodied Vision-Language Programmer from Environmental FeedbackCode2
Show:102550
← PrevPage 2 of 5Next →

No leaderboard results yet.