← Search

Xiaokang Wei

3 accepted papers

2026

A²Flow: Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operators

AAAI 2026technical

Large language models (LLMs) have shown strong potential in automating the design of agentic workflows. However, existing methods still rely heavily on manually predefined operators, limiting generalization and scalability. To address this issue, we propose A²Flow, a fully automated framework for ag

Cited by 0SourcePDFScholar
2026

PBR3DGen: A VLM-Guided Mesh Generation with High-Quality PBR Texture

AAAI 2026technical

Generating high-quality physically based rendering (PBR) materials is important to achieve realistic rendering in the downstream tasks, yet it remains challenging due to the intertwined effects of materials and lighting. While existing methods have made breakthroughs by incorporating material decomp

Cited by 0SourcePDFScholar
2025

Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation

ICCV 2025poster

Triangle meshes are fundamental to 3D applications. Current automatic mesh generation methods typically rely on intermediate representations that lack the continuous surface quality inherent to meshes. Converting these representations into meshes produces dense, suboptimal outputs. Although recent a…

Cited by 0SourcePDFScholar