7 papers
Generalized Radius and Integrated Codebook Transforms for Differentiable Vector Quantization
Haochen You, Heng Zhang, Hongyang He +2
Vector quantization (VQ) underpins modern generative and representation models by turning continuous latents into discrete tokens. Yet hard nearest-neighbor assignments are non-dif…
ReSSFormer: A Recursive Sparse Structured Transformer for Scalable and Long-Context Reasoning
Haochen You, Baojing Liu
While Transformer architectures have demonstrated impressive scalability across domains, they continue to face challenges in long-context reasoning, computational efficiency, and s…
Gradient Shaping Beyond Clipping: A Functional Perspective on Update Magnitude Control
Haochen You, Baojing Liu
Gradient clipping is widely used to stabilize deep network training, but its formulation as a hard, fixed threshold limits flexibility and ignores gradient distribution dynamics. W…
MCIGLE: Multimodal Exemplar-Free Class-Incremental Graph Learning
Haochen You, Baojing Liu
Exemplar-free class-incremental learning enables models to learn new classes over time without storing data from old ones. As multimodal graph-structured data becomes increasingly…
Metric Embedding Initialization-Based Differentially Private and Explainable Graph Clustering
Haochen You, Baojing Liu
Graph clustering under the framework of differential privacy, which aims to process graph-structured data while protecting individual privacy, has been receiving increasing attenti…
Modular MeanFlow: Towards Stable and Scalable One-Step Generative Modeling
Haochen You, Baojing Liu, Hongyang He
One-step generative modeling seeks to generate high-quality data samples in a single function evaluation, significantly improving efficiency over traditional diffusion or flow-base…