5 papers
Depth-Attention: Cross-Layer Value Mixing for Language Models
Boyi Zeng, Yiqin Hao, Zitong Wang +7
Self-attention selects information freely across the sequence, but across depth, Transformers merely add each layer's output to the residual stream, so later layers cannot selectiv…
BLEG: LLM Functions as Powerful fMRI Graph-Enhancer for Brain Network Analysis
Rui Dong, Zitong Wang, Jiaxing Li +2
Graph Neural Networks (GNNs) have been widely used in diverse brain network analysis tasks based on preprocessed functional magnetic resonance imaging (fMRI) data. However, their p…
2026 Roadmap on Artificial Intelligence and Machine Learning for Smart Manufacturing
Jay Lee, Hanqi Su, Marco Macchi +50
The evolution of artificial intelligence (AI) and machine learning (ML) is reshaping smart manufacturing by providing new capabilities for efficiency, adaptability, and autonomy ac…
AdaPonderLM: Gated Pondering Language Models with Token-Wise Adaptive Depth
Shixiang Song, He Li, Zitong Wang +6
Test-time scaling via recurrent/iterative Transformers enables large language models to spend more computation at inference, but most pretrained recurrent LMs run a fixed number of…
Delta-K: Boosting Multi-Instance Generation via Cross-Attention Augmentation
Zitong Wang, Zijun Shen, Haohao Xu +2
While Diffusion Models excel in text-to-image synthesis, they often suffer from concept omission when synthesizing complex multi-instance scenes. Existing training-free methods att…