5 papers
3DCodeVerse: Exploring 3D Worlds as Code
Yipeng Gao, Ziyao Zeng, Jinfa Huang +16
We introduce 3DCodeVerse, a research ecosystem that enables coding agents to create editable and verifiable 3D content at scale. 3DCodeVerse comprises large-scale, high-quality dat…
Grid-Bench: Can LLMs Predict How Discrete Worlds Change?
Zixiang Xu, Zirui Song, Wanrong Zheng +16
Spatial instructions describe how to move objects, transform regions, or modify their surroundings. When several operations are applied in sequence, each acts on a configuration sh…
3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code
Yipeng Gao, Lei Shu, Genzhi Ye +5
Procedural 3D modeling through code is emerging as a versatile paradigm, offering deterministic, engine-ready, and precisely editable assets that neural 3D generators inherently la…
Riemannian-Geometric Fingerprints of Generative Models
Hae Jin Song, Laurent Itti
Recent breakthroughs and rapid integration of generative models (GMs) have sparked interest in the problem of model attribution and their fingerprints. For instance, service provid…
Exploring the Performance of Perforated Backpropagation through Further Experiments
Rorry Brenner, Evan Davis, Rushi Chaudhari +5
Perforated Backpropagation is a neural network optimization technique based on modern understanding of the computational importance of dendrites within biological neurons. This pap…