Paper-Conference

CanvasMAR: Improving Masked Autoregressive Video Prediction With Canvas

Z. Li, M. Zhang

Cross Flow: One-Step Generation Across Latent and Pixel Spaces

X. Wang, X. Zhang, Y. Li, R. Jiang, Z. Zhong, L. Bo, M. Zhang

FlashMol: High-Quality Molecule Generation in as Few as Four Steps

X. Wei, Z. Li, S. Yan, C. Zhou, M. Zhang

TabDLM: Free-Form Tabular Data Generation via Joint Numerical–Language Diffusion

D. Cai, J. Feng, Y. Wang, D. Zheng, Y. Chen, M. Zhang

The Expressivity Boundary of Probabilistic Circuits: A Comparison with Large Language Models

Z. Zhao, X. Liu, M. Zhang, A. Liu

Toward Better Geometric Representations for Molecule Generative Models

S. Yan, Z. Li, C. Zhou, Q. Huang, K. Liu, M. Zhang

GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization

J. Wang, L. Chen, X. Wang, S. Kang, H. Yang, D. Zheng, M. Zhang

GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models

J. Feng, D. Cai, Y. Chen, M. Zhang

Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors

J. Zhou, C. Zhou, X. Wang, P. Li, M. Zhang

HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention

Token-level sparse attention mechanisms, exemplified by DeepSeek Sparse Attention (DSA), achieve fine-grained key selection by scoring …

Y. Xu, F. Meng, F. Jiang, Y. Wang, R. Zhou, Z. Wang, J. Wu, Z. Pan, X. Tang, W. Pei, T. Liu, D. Yin, X. Sun, M. Zhang