Papers

Filtered to coarse-to-fine frameworks · 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

WorldClaw: Agentic 3D Open-World Generation at Scale

58 upvotes · 5 AUG 2026 · Chunchao Guo, Jinpeng Li, Yang Li et al.

This paper develops a system for generating large-scale, open-world 3D environments from text prompts, with a focus on coherence and editability. Practitioners might care about the potential applications of this technology in fields like game development, architecture, and visual effects.

3D scene generationagentic modelsopen-world environmentscoarse-to-fine frameworksprocedural modeling