Papers

Filtered to 3D world generation · clear filter

Browse by term

continual learning 83reinforcement learning 50large language models 12benchmarking 11benchmarks 11language models 11vision-language models 11robotics 7natural language processing 6world models 6generative models 5recursive self-improvement 5attention mechanisms 4diffusion Transformers 4multi-agent systems 4multimodal learning 4multimodal models 4on-policy distillation 4self-distillation 4self-supervised learning 4transformers 4video generation 4vision-language-action models 4agent-based systems 3agentic models 3agentic search 3autonomous systems 3coding agents 3diffusion models 3image generation 3

Matching papers

Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States

66 upvotes · 3 SEP 2026 · Kang Liao, Yihang Luo, Xiao-Ming Wu et al.

This paper introduces Puffin-World, a unified multimodal model that combines physics, geometry, and appearance to generate and interact with 3D worlds. Practitioners might care because it enables physically consistent and visually stable world generation for applications like world exploration and simulation.

multimodal models3D world generationnative world statesunified architecturephysics-based renderingreal-world camera calibration

VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?

50 upvotes · 15 AUG 2026 · Yansong Ning, Jingwen Ye, Zhongkai Wu et al.

This paper proposes a framework for training agents to create 3D open worlds based on user queries, and evaluates its performance using a large benchmark dataset. Practitioners might care about this research because it can help develop more capable multimodal agents that can understand user intent and generate realistic 3D environments.

multimodal agents3D world generationcontinual learninginteractive environmentsbenchmarks